Special Issue "Medical Artificial Intelligence"

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: closed (28 February 2021).

Special Issue Editor

Prof. Yahan Hu
E-Mail Website
Guest Editor
Department of Information Management and Institute of Healthcare Information Management, National Chung Cheng University, Chiayi 621301, Taiwan
Interests: data mining; text mining; medical informatics; decision support systems

Special Issue Information

Dear Colleagues,

Artificial intelligence (AI) and its applications are now the hottest research areas. In recent years, there have been more and more AI applications in the medical field. AI technology is promoting the development of the medical and health industries. In the medical domain, AI techniques can be used to develop clinical decision support systems to help with medical diagnostics. AI technologies can be also deployed in various medical devices, trackers, and information systems. A huge amount of patient data is recorded in the electronic medical record (EMR) database, including diagnosis, medical history, medications, and lab results. Through the process of extraction, transformation, and loading (ETL), researchers can generate a patient dataset worthy of analysis by AI techniques. In addition to the data analysis using structure data, AI techniques are now used for medical image recognition, medical text, and semantic recognition, and molecular biological testing. The analysis results can be used as a reference for the evaluation of patients by the medical team.

This Special Issue seeks original, high-quality contributions that investigate AI applications in healthcare. The main topics of interest include but are not limited to the following:

  • AI and big data analytics applied in medical domain;
  • AI methodologies for medical data analysis;
  • Administrative data analysis using AI techniques;
  • Medical data acquisition, cleaning and integration using AI methodologies;
  • Medical image recognition using AI technologies;
  • Natural language processing in medical documents.

Prof. Yahan Hu
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2000 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Medical informatics
  • Artificial intelligence
  • Electronic medical records
  • Medical image recognition
  • Data mining
  • Text mining
  • Administrative data
  • Natural language processing

Published Papers (29 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

Article
Diagnosis of Obstructive Sleep Apnea from ECG Signals Using Machine Learning and Deep Learning Classifiers
Appl. Sci. 2021, 11(14), 6622; https://doi.org/10.3390/app11146622 - 19 Jul 2021
Viewed by 483
Abstract
Obstructive sleep apnea (OSA) is a well-known sleep ailment. OSA mostly occurs due to the shortage of oxygen for the human body, which causes several symptoms (i.e., low concentration, daytime sleepiness, and irritability). Discovering the existence of OSA at an early stage can [...] Read more.
Obstructive sleep apnea (OSA) is a well-known sleep ailment. OSA mostly occurs due to the shortage of oxygen for the human body, which causes several symptoms (i.e., low concentration, daytime sleepiness, and irritability). Discovering the existence of OSA at an early stage can save lives and reduce the cost of treatment. The computer-aided diagnosis (CAD) system can quickly detect OSA by examining the electrocardiogram (ECG) signals. Over-serving ECG using a visual procedure is challenging for physicians, time-consuming, expensive, and subjective. In general, automated detection of the ECG signal’s arrhythmia is a complex task due to the complexity of the data quantity and clinical content. Moreover, ECG signals are usually affected by noise (i.e., patient movement and disturbances generated by electric devices or infrastructure), which reduces the quality of the collected data. Machine learning (ML) and Deep Learning (DL) gain a higher interest in health care systems due to its ability of achieving an excellent performance compared to traditional classifiers. We propose a CAD system to diagnose apnea events based on ECG in an automated way in this work. The proposed system follows the following steps: (1) remove noise from the ECG signal using a Notch filter. (2) extract nine features from the ECG signal (3) use thirteen ML and four types of DL models for the diagnosis of sleep apnea. The experimental results show that our proposed approach offers a good performance of DL classifiers to detect OSA. The proposed model achieves an accuracy of 86.25% in the validation stage. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
Unsupervised Cell Segmentation and Labelling in Neural Tissue Images
Appl. Sci. 2021, 11(9), 3733; https://doi.org/10.3390/app11093733 - 21 Apr 2021
Viewed by 538
Abstract
Neurodegenerative diseases are a group of largely incurable disorders characterised by the progressive loss of neurons and for which often the molecular mechanisms are poorly understood. To bridge this gap, researchers employ a range of techniques. A very prominent and useful technique adopted [...] Read more.
Neurodegenerative diseases are a group of largely incurable disorders characterised by the progressive loss of neurons and for which often the molecular mechanisms are poorly understood. To bridge this gap, researchers employ a range of techniques. A very prominent and useful technique adopted across many different fields is imaging and the analysis of histopathological and fluorescent label tissue samples. Although image acquisition has been efficiently automated recently, automated analysis still presents a bottleneck. Although various methods have been developed to automate this task, they tend to make use of single-purpose machine learning models that require extensive training, imposing a significant workload on the experts and introducing variability in the analysis. Moreover, these methods are impractical to audit and adapt, as their internal parameters are difficult to interpret and change. Here, we present a novel unsupervised automated schema for object segmentation of images, exemplified on a dataset of tissue images. Our schema does not require training data, can be fully audited and is based on a series of understandable biological decisions. In order to evaluate and validate our schema, we compared it with a state-of-the-art automated segmentation method for post-mortem tissues of ALS patients. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
Instance Segmentation Based on Deep Convolutional Neural Networks and Transfer Learning for Unconstrained Psoriasis Skin Images
Appl. Sci. 2021, 11(7), 3155; https://doi.org/10.3390/app11073155 - 01 Apr 2021
Viewed by 616
Abstract
In this paper, an efficient instance segmentation scheme based on deep convolutional neural networks is proposed to deal with unconstrained psoriasis images for computer-aided diagnosis. To achieve instance segmentation, the You Only Look At CoefficienTs (YOLACT) network composed of backbone, feature pyramid network [...] Read more.
In this paper, an efficient instance segmentation scheme based on deep convolutional neural networks is proposed to deal with unconstrained psoriasis images for computer-aided diagnosis. To achieve instance segmentation, the You Only Look At CoefficienTs (YOLACT) network composed of backbone, feature pyramid network (FPN), Protonet, and prediction head is used to deal with psoriasis images. The backbone network is used to extract feature maps from an image, and FPN is designed to generate multiscale feature maps for effectively classifying and localizing objects with multiple sizes. The prediction head is used to predict the classification information, bounding box information, and mask coefficients of objects. Some prototypes generated by Protonet are combined with mask coefficients to estimate the pixel-level shapes for objects. To achieve instance segmentation for unconstrained psoriasis images, YOLACT++ with a pretrained model is retrained via transfer learning. To evaluate the performance of the proposed scheme, unconstrained psoriasis images with different severity levels are collected for testing. As for subjective testing, the psoriasis regions and normal skin areas can be located and classified well. The four performance indices of the proposed scheme were higher than 93% after cross validation. About object localization, the Mean Average Precision (mAP) rates of the proposed scheme were at least 85.9% after cross validation. As for efficiency, the frames per second (FPS) rate of the proposed scheme reached up to 15. In addition, the F1_score and the execution speed of the proposed scheme were higher than those of the Mask Region-Based Convolutional Neural Networks (R-CNN)-based method. These results show that the proposed scheme based on YOLACT++ can not only detect psoriasis regions but also distinguish psoriasis pixels from background and normal skin pixels well. Furthermore, the proposed instance segmentation scheme outperforms the Mask R-CNN-based method for unconstrained psoriasis images. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
A Fully Automated Pipeline for a Robust Conjunctival Hyperemia Estimation
Appl. Sci. 2021, 11(7), 2978; https://doi.org/10.3390/app11072978 - 26 Mar 2021
Viewed by 461
Abstract
Purpose: Many semi-automated and fully-automated approaches have been proposed in literature to improve the objectivity of the estimation of conjunctival hyperemia, based on image processing analysis of eyes’ photographs. The purpose is to improve its evaluation using faster fully-automated systems and independent by [...] Read more.
Purpose: Many semi-automated and fully-automated approaches have been proposed in literature to improve the objectivity of the estimation of conjunctival hyperemia, based on image processing analysis of eyes’ photographs. The purpose is to improve its evaluation using faster fully-automated systems and independent by the human subjectivity. Methods: In this work, we introduce a fully-automated analysis of the redness grading scales able to completely automatize the clinical procedure, starting from the acquired image to the redness estimation. In particular, we introduce a neural network model for the conjunctival segmentation followed by an image processing pipeline for the vessels network segmentation. From these steps, we extract some features already known in literature and whose correlation with the conjunctival redness has already been proved. Lastly, we implemented a predictive model for the conjunctival hyperemia using these features. Results: In this work, we used a dataset of images acquired during clinical practice.We trained a neural network model for the conjunctival segmentation, obtaining an average accuracy of 0.94 and a corresponding IoU score of 0.88 on a test set of images. The set of features extracted on these ROIs is able to correctly predict the Efron scale values with a Spearman’s correlation coefficient of 0.701 on a set of not previously used samples. Conclusions: The robustness of our pipeline confirms its possible usage in a clinical practice as a viable decision support system for the ophthalmologists. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
Assessment of Periodontium Temperature Changes under Orthodontic Force by Using Objective and Automatic Classifier
Appl. Sci. 2021, 11(6), 2634; https://doi.org/10.3390/app11062634 - 16 Mar 2021
Cited by 1 | Viewed by 428
Abstract
Background: Orthodontic elastics are used in orthodontic treatment with fixed braces. The effect of class I elastics on changing gingiva temperature as a periodontal component was investigated. Methods: To evaluate the temperature changes, objective and automatic classifiers were used to determine the sensitivity [...] Read more.
Background: Orthodontic elastics are used in orthodontic treatment with fixed braces. The effect of class I elastics on changing gingiva temperature as a periodontal component was investigated. Methods: To evaluate the temperature changes, objective and automatic classifiers were used to determine the sensitivity and specificity of the measurement. Results: Before putting on the elastics, the average gingival temperature of all 120 patients was 34.72 ± 0.7548 °C. Putting on the elastics for 10 min slightly increased the temperature to 34.81 ± 0.5938 °C; however, this is not a statistically significant change (p > 0.05). Conclusion: It is concluded that putting an elastic band on does not significantly affect the gingiva temperature change. The use of class I elastics in orthodontic treatment in patients with healthy periodontium does not significantly change the periodontal temperature, which indirectly proves the production of safe orthodontic forces that can be used in the clinic. The use of artificial intelligence in the assessment of the temperature of the gingiva makes it possible to exclude factors that may disturb the objective thermographic analysis. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
A Novel Method in Predicting Hypertension Using Facial Images
Appl. Sci. 2021, 11(5), 2414; https://doi.org/10.3390/app11052414 - 09 Mar 2021
Viewed by 648
Abstract
Hypertension has been a crucial public health challenge among adults. This study aimed to develop a novel method for non-contact prediction of hypertension using facial characteristics such as facial features and facial color. The data of 1099 subjects (376 men and 723 women) [...] Read more.
Hypertension has been a crucial public health challenge among adults. This study aimed to develop a novel method for non-contact prediction of hypertension using facial characteristics such as facial features and facial color. The data of 1099 subjects (376 men and 723 women) analyzed in this study were obtained from the Korean Constitutional Multicenter Study of Korean medicine Data Center (KDC) at the Korea Institute of Oriental Medicine (KIOM). Facial images were collected and facial variables were extracted using image processing techniques. Analysis of covariance (ANCOVA) and Least Absolute Shrinkage and Selection Operator (LASSO) were performed to compare and identify the facial characteristic variables between the hypertension group and normal group. We found that the most distinct facial feature differences between hypertension patients and normal individuals were facial shape and nose shape for men in addition to eye shape and nose shape for women. In terms of facial colors, cheek color in men, as well as forehead and nose color in women, were the most distinct facial colors between the hypertension groups and normal individuals. Looking at the AUC value, the prediction power for women is better than men. In conclusion, we managed to explore and identify the facial characteristics variables related to hypertension. This study may provide new evidence in the validity of predicting hypertension using facial characteristics. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
Early Detection of Alzheimer’s Disease Using Polar Harmonic Transforms and Optimized Wavelet Neural Network
Appl. Sci. 2021, 11(4), 1574; https://doi.org/10.3390/app11041574 - 09 Feb 2021
Viewed by 568
Abstract
Effective and accurate diagnosis of Alzheimer’s disease (AD), as well as early-stage detection, has gained more and more attention in recent years. For AD classification, we propose a new hybrid method for early detection of Alzheimer’s disease (AD) using Polar Harmonic Transforms (PHT) [...] Read more.
Effective and accurate diagnosis of Alzheimer’s disease (AD), as well as early-stage detection, has gained more and more attention in recent years. For AD classification, we propose a new hybrid method for early detection of Alzheimer’s disease (AD) using Polar Harmonic Transforms (PHT) and Self-adaptive Differential Evolution Wavelet Neural Network (SaDE-WNN). The orthogonal moments are used for feature extraction from the grey matter tissues of structural Magnetic Resonance Imaging (MRI) data. Irrelevant features are removed by the feature selection process through evaluating the in-class and among-class variance. In recent years, WNNs have gained attention in classification tasks; however, they suffer from the problem of initial parameter tuning, parameter setting. We proposed a WNN with the self-adaptation technique for controlling the Differential Evolution (DE) parameters, i.e., the mutation scale factor (F) and the cross-over rate (CR). Experimental results on the Alzheimer’s disease Neuroimaging Initiative (ADNI) database indicate that the proposed method yields the best overall classification results between AD and mild cognitive impairment (MCI) (93.7% accuracy, 86.0% sensitivity, 98.0% specificity, and 0.97 area under the curve (AUC)), MCI and healthy control (HC) (92.9% accuracy, 95.2% sensitivity, 88.9% specificity, and 0.98 AUC), and AD and HC (94.4% accuracy, 88.7% sensitivity, 98.9% specificity and 0.99 AUC). Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
Attention-Based Transfer Learning for Efficient Pneumonia Detection in Chest X-ray Images
Appl. Sci. 2021, 11(3), 1242; https://doi.org/10.3390/app11031242 - 29 Jan 2021
Cited by 2 | Viewed by 718
Abstract
Pneumonia is a form of acute respiratory infection commonly caused by germs, viruses, and fungi, and can prove fatal at any age. Chest X-rays is the most common technique for diagnosing pneumonia. There have been several attempts to apply transfer learning based on [...] Read more.
Pneumonia is a form of acute respiratory infection commonly caused by germs, viruses, and fungi, and can prove fatal at any age. Chest X-rays is the most common technique for diagnosing pneumonia. There have been several attempts to apply transfer learning based on a Convolutional Neural Network to build a stable model in computer-aided diagnosis. Recently, with the appearance of an attention mechanism that automatically focuses on the critical part of the image that is crucial for the diagnosis of disease, it is possible to increase the performance of previous models. The goal of this study is to improve the accuracy of a computer-aided diagnostic approach that medical professionals can easily use as an auxiliary tool. In this paper, we proposed the attention-based transfer learning framework for efficient pneumonia detection in chest X-ray images. We collected features from three-types of pre-trained models, ResNet152, DenseNet121, ResNet18 as a role of feature extractor. We redefined the classifier for a new task and applied the attention mechanism as a feature selector. As a result, the proposed approach achieved accuracy, F-score, Area Under the Curve(AUC), precision and recall of 96.63%, 0.973, 96.03%, 96.23% and 98.46%, respectively. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
The New York City COVID-19 Spread in the 2020 Spring: A Study on the Potential Role of Particulate Using Time Series Analysis and Machine Learning
Appl. Sci. 2021, 11(3), 1177; https://doi.org/10.3390/app11031177 - 27 Jan 2021
Cited by 4 | Viewed by 646
Abstract
This study investigates the potential association between the daily distribution of the PM2,5 air pollutant and the initial spreading of COVID-19 in New York City. We study the period from 4 March to 22 March 2020, and apply our analysis to all [...] Read more.
This study investigates the potential association between the daily distribution of the PM2,5 air pollutant and the initial spreading of COVID-19 in New York City. We study the period from 4 March to 22 March 2020, and apply our analysis to all five counties, including the city, plus seven neighboring counties, including both urban and peripheral districts. Using the Granger causality methodology, and considering the maximum lag period (14 days) between infection and the correspondent diagnosis, we found that the time series of the new daily infections registered in those 12 counties appear to correlate to the time series of the concentrations of the PM2.5 particulate circulating in the air, with 33 over 36 statistical tests with a p-value less than 0.005, thus confirming such a hypothesis. Moreover, looking for further confirmation of this association, we train four different machine learning algorithms on a portion of those time series. These are able to predict that the number of the new daily infections would have surpassed a given infections threshold for the remaining portion of the series, with an average accuracy ranging from 84% to 95%, depending on the algorithm and/or on the specific county under observation. This is similar to other results obtained from several polluted urban areas, e.g., Wuhan, Xiaogan, and Huanggang in China, and Northern Italy. Our study provides further evidence that ambient air pollutants can be associated with a daily COVID-19 infection incidence. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
Risk-Averse Food Recommendation Using Bayesian Feedforward Neural Networks for Patients with Type 1 Diabetes Doing Physical Activities
Appl. Sci. 2020, 10(22), 8037; https://doi.org/10.3390/app10228037 - 12 Nov 2020
Viewed by 1855
Abstract
Background. Since physical activity has a high impact on patients with type 1 diabetes and the risk of hypoglycemia (low blood glucose levels) is significantly higher during and after physical activities, an automatic method to provide a personalized recommendation is needed to improve [...] Read more.
Background. Since physical activity has a high impact on patients with type 1 diabetes and the risk of hypoglycemia (low blood glucose levels) is significantly higher during and after physical activities, an automatic method to provide a personalized recommendation is needed to improve the blood glucose management and harness the benefits of physical activities. This paper aims to reduce the risk of hypoglycemia and hyperglycemia (high blood glucose levels), and empowers type 1 diabetes patients to make decisions regarding food choices connected with physical activities. Methods. Traditional and Bayesian feedforward neural network models are developed to provide accurate predictions of the blood glucose outcome and the risks of hyperglycemia and hypoglycemia with uncertainty information. Using the proposed models, safe actions that minimize the risk of both hypoglycemia and hyperglycemia are provided as food recommendations to the patient. Results. The predicted blood glucose responses to the optimal and safe food recommendations are significantly better and safer than by taking random food. Conclusions. Simulations conducted on the state-of-the-art UVA/Padova simulator combined with Brenton’s physical activity model show that the proposed methodology is safe and effective in managing blood glucose during and after physical activities. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
Development of a Mortality Risk Model in Elderly Hip Fracture Patients by Different Analytical Approaches
Appl. Sci. 2020, 10(19), 6787; https://doi.org/10.3390/app10196787 - 28 Sep 2020
Viewed by 790
Abstract
Hip fracture is a major health issue that accompanies community aging. The most critical time after a hip fracture should be the first year. Care systems and surgical techniques for hip fractures have improved, so the trend of mortality in elderly hip fracture [...] Read more.
Hip fracture is a major health issue that accompanies community aging. The most critical time after a hip fracture should be the first year. Care systems and surgical techniques for hip fractures have improved, so the trend of mortality in elderly hip fracture could be changed with them. Therefore, we observed the changes in the trend and critical factors for first-year mortality for the hip fractures in an elderly population in Taiwan, and mortality of prognosis prediction model was developed for the early diagnosis using a population-based database in Taiwan (National Health Insurance Research Database, NHIRD). A total of 166,274 elderly subjects with an age greater than 60-years-old from 2001 to 2010 were collected for this study. Cox proportional-hazards (PH) regression and logistic regression were calculated to odds ratio and hazard ratio for mortality of those patients and compared it. Data mining algorithms were also used to generate a risk stratification prediction model. The first-year mortality rate of the overall study group was 21.5% in 2001 and 15.0% in 2010 (p for trend < 0.001). In the male subgroup, the first-year mortality rate was 29.3% in 2001 and decreased to 17.3% in 2010; the trend of standardized mortality ratio was significantly decreased from 4.4 to 2.6 (p for trend < 0.001). By logistic regression, mortality significantly increased with age and male gender. Furthermore, gender, age, patients with diabetes mellitus (DM), cardiovascular (CV), and renal comorbidity, and surgical intervention can be variables for constructing the risk stratification model. The findings of the study will be used for helping related field physicians to predict the prognosis risk of hip fracture patients, and provide evidence-based tailored treatment recommendations for those patients. It may consider to build various models for predicting the prognosis of hip fracture or integrating prediction algorithms into the computerized physician order entry system, thus creating a practical clinical decision support system with warning functions. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
In-Silico Evaluation of Glucose Regulation Using Policy Gradient Reinforcement Learning for Patients with Type 1 Diabetes Mellitus
Appl. Sci. 2020, 10(18), 6350; https://doi.org/10.3390/app10186350 - 11 Sep 2020
Cited by 1 | Viewed by 751
Abstract
In this paper, we test and evaluate policy gradient reinforcement learning for automated blood glucose control in patients with Type 1 Diabetes Mellitus. Recent research has shown that reinforcement learning is a promising approach to accommodate the need for individualized blood glucose level [...] Read more.
In this paper, we test and evaluate policy gradient reinforcement learning for automated blood glucose control in patients with Type 1 Diabetes Mellitus. Recent research has shown that reinforcement learning is a promising approach to accommodate the need for individualized blood glucose level control algorithms. The motivation for using policy gradient algorithms comes from the fact that adaptively administering insulin is an inherently continuous task. Policy gradient algorithms are known to be superior in continuous high-dimensional control tasks. Previously, most of the approaches for automated blood glucose control using reinforcement learning has used a finite set of actions. We use the Trust-Region Policy Optimization algorithm in this work. It represents the state of the art for deep policy gradient algorithms. The experiments are carried out in-silico using the Hovorka model, and stochastic behavior is modeled through simulated carbohydrate counting errors to illustrate the full potential of the framework. Furthermore, we use a model-free approach where no prior information about the patient is given to the algorithm. Our experiments show that the reinforcement learning agent is able to compete with and sometimes outperform state-of-the-art model predictive control in blood glucose regulation. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
A Machine Learning Approach to Predicting Readmission or Mortality in Patients Hospitalized for Stroke or Transient Ischemic Attack
Appl. Sci. 2020, 10(18), 6337; https://doi.org/10.3390/app10186337 - 11 Sep 2020
Cited by 3 | Viewed by 851
Abstract
Readmissions after stroke are not only associated with greater levels of disability and a higher risk of mortality but also increase overall medical costs. Predicting readmission risk and understanding its causes are thus essential for healthcare resource allocation and quality improvement planning. By [...] Read more.
Readmissions after stroke are not only associated with greater levels of disability and a higher risk of mortality but also increase overall medical costs. Predicting readmission risk and understanding its causes are thus essential for healthcare resource allocation and quality improvement planning. By using machine learning techniques on initial admission data, this study aimed to develop prediction models for readmission or mortality after stroke. During model development, resampling methods were implemented to balance the class distribution. Two-layer nested cross-validation was used to build and evaluate the prediction models. A total of 3422 patients were included for analysis. The 90-day rate of readmission or mortality was 17.6%. This study identified several important predictive factors, including age, prior emergency department visits, pre-stroke functional status, stroke severity, body mass index, consciousness level, and use of a nasogastric tube. The Naïve Bayes model with class weighting to compensate for class imbalance achieved the highest discriminatory capacity in terms of the area under the receiver operating characteristic curve (0.661). Despite having room for improvement, the prediction models could be used for early risk assessment of patients with stroke. Identification of patients at high risk for readmission or mortality immediately after admission has the potential of enabling early discharge planning and transitional care interventions. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
Machine Learning in High-Alert Medication Treatment: A Study on the Cardiovascular Drug
Appl. Sci. 2020, 10(17), 5798; https://doi.org/10.3390/app10175798 - 21 Aug 2020
Cited by 1 | Viewed by 688
Abstract
The safety of high-alert medication treatment is still a challenge all over the world. Approximately one-half of adverse drug events (ADEs) are related to high-alert medications, which motivates us to improve the predicament faced in clinical practice. The purpose of this study is [...] Read more.
The safety of high-alert medication treatment is still a challenge all over the world. Approximately one-half of adverse drug events (ADEs) are related to high-alert medications, which motivates us to improve the predicament faced in clinical practice. The purpose of this study is to use machine-learning techniques to predict the risk of high-alert medication treatment. Taking the cardiovascular drug digoxin as an example, we collected the records of 513 patients who received the pertinent therapy during hospitalization at a tertiary medical center in Taiwan. Considering serum digoxin concentration (SDC) is the primary indicator for assessing the risk of digoxin therapy, patients with SDC being controlled at the recommended range before their discharge were defined as a low-risk population; otherwise, patients were defined as the high-risk population. Weka 3.9.4—an open source machine learning software—was adopted to develop binary classification models to predict the risk of digoxin therapy by a number of machine-learning techniques, including k-nearest neighbors (kNN), decision tree (C4.5), support vector machine (SVM), random forest (RF), artificial neural network (ANN) and logistic regression (LGR). The results showed that the performance of RF was the best, followed by C4.5 and ANN; the remaining classifiers performed poorly. This study confirmed that machine-learning techniques can yield favorable prediction effectiveness for high-alert medication treatment, thereby decreasing the risk of ADEs and improving medication safety. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
A Methodology for Open Information Extraction and Representation from Large Scientific Corpora: The CORD-19 Data Exploration Use Case
Appl. Sci. 2020, 10(16), 5630; https://doi.org/10.3390/app10165630 - 13 Aug 2020
Cited by 3 | Viewed by 1676
Abstract
The usefulness of automated information extraction tools in generating structured knowledge from unstructured and semi-structured machine-readable documents is limited by challenges related to the variety and intricacy of the targeted entities, the complex linguistic features of heterogeneous corpora, and the computational availability for [...] Read more.
The usefulness of automated information extraction tools in generating structured knowledge from unstructured and semi-structured machine-readable documents is limited by challenges related to the variety and intricacy of the targeted entities, the complex linguistic features of heterogeneous corpora, and the computational availability for readily scaling to large amounts of text. In this paper, we argue that the redundancy and ambiguity of subject–predicate–object (SPO) triples in open information extraction systems has to be treated as an equally important step in order to ensure the quality and preciseness of generated triples. To this end, we propose a pipeline approach for information extraction from large corpora, encompassing a series of natural language processing tasks. Our methodology consists of four steps: i. in-place coreference resolution, ii. extractive text summarization, iii. parallel triple extraction, and iv. entity enrichment and graph representation. We manifest our methodology on a large medical dataset (CORD-19), relying on state-of-the-art tools to fulfil the aforementioned steps and extract triples that are subsequently mapped to a comprehensive ontology of biomedical concepts. We evaluate the effectiveness of our information extraction method by comparing it in terms of precision, recall, and F1-score with state-of-the-art OIE engines and demonstrate its capabilities on a set of data exploration tasks. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
A CNN CADx System for Multimodal Classification of Colorectal Polyps Combining WL, BLI, and LCI Modalities
Appl. Sci. 2020, 10(15), 5040; https://doi.org/10.3390/app10155040 - 22 Jul 2020
Cited by 1 | Viewed by 821
Abstract
Colorectal polyps are critical indicators of colorectal cancer (CRC). Blue Laser Imaging and Linked Color Imaging are two modalities that allow improved visualization of the colon. In conjunction with the Blue Laser Imaging (BLI) Adenoma Serrated International Classification (BASIC) classification, endoscopists are capable [...] Read more.
Colorectal polyps are critical indicators of colorectal cancer (CRC). Blue Laser Imaging and Linked Color Imaging are two modalities that allow improved visualization of the colon. In conjunction with the Blue Laser Imaging (BLI) Adenoma Serrated International Classification (BASIC) classification, endoscopists are capable of distinguishing benign and pre-malignant polyps. Despite these advancements, this classification still prevails a high misclassification rate for pre-malignant colorectal polyps. This work proposes a computer aided diagnosis (CADx) system that exploits the additional information contained in two novel imaging modalities, enabling more informative decision-making during colonoscopy. We train and benchmark six commonly used CNN architectures and compare the results with 19 endoscopists that employed the standard clinical classification model (BASIC). The proposed CADx system for classifying colorectal polyps achieves an area under the curve (AUC) of 0.97. Furthermore, we incorporate visual explanatory information together with a probability score, jointly computed from White Light, Blue Laser Imaging, and Linked Color Imaging. Our CADx system for automatic polyp malignancy classification facilitates future advances towards patient safety and may reduce time-consuming and costly histology assessment. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
A Machine Learning Approach to Predict an Early Biochemical Recurrence after a Radical Prostatectomy
Appl. Sci. 2020, 10(11), 3854; https://doi.org/10.3390/app10113854 - 01 Jun 2020
Viewed by 707
Abstract
Background: Approximately 20–50% of prostate cancer patients experience biochemical recurrence (BCR) after radical prostatectomy (RP). Among them, cancer recurrence occurs in about 20–30%. Thus, we aim to reveal the utility of machine learning algorithms for the prediction of early BCR after RP. Methods: [...] Read more.
Background: Approximately 20–50% of prostate cancer patients experience biochemical recurrence (BCR) after radical prostatectomy (RP). Among them, cancer recurrence occurs in about 20–30%. Thus, we aim to reveal the utility of machine learning algorithms for the prediction of early BCR after RP. Methods: A total of 104 prostate cancer patients who underwent magnetic resonance imaging and RP were evaluated. Four well-known machine learning algorithms (i.e., k-nearest neighbors (KNN), multilayer perceptron (MLP), decision tree (DT), and auto-encoder) were applied to build a prediction model for early BCR using preoperative clinical and imaging and postoperative pathologic data. The sensitivity, specificity, and accuracy for detection of early BCR of each algorithm were evaluated. Area under the receiver operating characteristics (AUROC) analyses were conducted. Results: A prediction model using an auto-encoder showed the highest prediction ability of early BCR after RP using all data as input (AUC = 0.638) and only preoperative clinical and imaging data (AUC = 0.656), followed by MLP (AUC = 0.607 and 0.598), KNN (AUC = 0.596 and 0.571), and DT (AUC = 0.534 and 0.495). Conclusion: The auto-encoder-based prediction system has the potential for accurate detection of early BCR and could be useful for long-term follow-up planning in prostate cancer patients after RP. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
Multi-Channel Feature Pyramid Networks for Prostate Segmentation, Based on Transrectal Ultrasound Imaging
Appl. Sci. 2020, 10(11), 3834; https://doi.org/10.3390/app10113834 - 31 May 2020
Cited by 1 | Viewed by 901
Abstract
Accurate segmentation for transrectal ultrasound imaging (TRUS) is often a challenging medical image processing task. The problem of weak boundary between adjacent prostate tissue and non-prostate tissue, and high similarity between artifact area and prostate area has always been the difficulty of TRUS [...] Read more.
Accurate segmentation for transrectal ultrasound imaging (TRUS) is often a challenging medical image processing task. The problem of weak boundary between adjacent prostate tissue and non-prostate tissue, and high similarity between artifact area and prostate area has always been the difficulty of TRUS image segmentation. In this paper, we construct a multi-channel feature pyramid network (MFPN) based on deep convolutional neural network-based prostate segmentation method to process multi-scale feature maps. Each level enhances the edge characteristics of the prostate by controlling the scale of the channel. The optimized regression mechanism of the target area was used to accurately locate the prostate. Experimental results showed that the proposed method achieved the key indicator Dice similarity coefficient and average absolute distance of 0.9651 mm and 0.504 mm, which outperformed state-of-the-art approaches. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
3D Liver and Tumor Segmentation with CNNs Based on Region and Distance Metrics
Appl. Sci. 2020, 10(11), 3794; https://doi.org/10.3390/app10113794 - 29 May 2020
Cited by 1 | Viewed by 852
Abstract
Liver and liver tumor segmentation based on abdomen computed tomography (CT) images is an essential step in computer-assisted clinical interventions. However, liver and tumor segmentation remains the difficult issue in the medical image processing field, which is ascribed to the anatomical complexity of [...] Read more.
Liver and liver tumor segmentation based on abdomen computed tomography (CT) images is an essential step in computer-assisted clinical interventions. However, liver and tumor segmentation remains the difficult issue in the medical image processing field, which is ascribed to the anatomical complexity of the liver and the poor demarcation between the liver and other nearby organs on the image. The existing 3D automatic liver and tumor segmentation algorithms based on full convolutional networks, such as V-net, have utilized the loss functions on the basis of integration (summing) over a segmented region (like Dice or cross-entropy). Unfortunately, the number of foreground and background voxels is usually highly imbalanced in liver and tumor segmentation tasks. This greatly varies the value of regional loss between various segmentation classes, and affects the training stability and effect. In the present study, an improved V-net algorithm was applied for 3D liver and tumor segmentation based on region and distance metrics. The distance metric-based loss function utilized a distance metric of the contour (or shape) space rather than the area. The model was jointly trained by the original regional loss and the three distance-based loss functions (including Boundary (BD) loss, Hausdorff (HD) loss, and Signed Distance Map (SDM) loss) to solve the problem of the highly unbalanced liver and tumor segmentation. Besides, the algorithm was tested in two databases LiTS 2017 (Technical University of Munich, Munich, Germany, 2017) and 3D-IRCADb (Research Institute against Digestive Cancer, Strasbourg Cedex, France, 2009), and the results proved the effectiveness of improvement. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
Voice Pathology Detection and Classification Using Convolutional Neural Network Model
Appl. Sci. 2020, 10(11), 3723; https://doi.org/10.3390/app10113723 - 27 May 2020
Cited by 41 | Viewed by 1513
Abstract
Voice pathology disorders can be effectively detected using computer-aided voice pathology classification tools. These tools can diagnose voice pathologies at an early stage and offering appropriate treatment. This study aims to develop a powerful feature extraction voice pathology detection tool based on Deep [...] Read more.
Voice pathology disorders can be effectively detected using computer-aided voice pathology classification tools. These tools can diagnose voice pathologies at an early stage and offering appropriate treatment. This study aims to develop a powerful feature extraction voice pathology detection tool based on Deep Learning. In this paper, a pre-trained Convolutional Neural Network (CNN) was applied to a dataset of voice pathology to maximize the classification accuracy. This study also proposes a distinguished training method combined with various training strategies in order to generalize the application of the proposed system on a wide range of problems related to voice disorders. The proposed system has tested using a voice database, namely the Saarbrücken voice database (SVD). The experimental results show the proposed CNN method for speech pathology detection achieves accuracy up to 95.41%. It also obtains 94.22% and 96.13% for F1-Score and Recall. The proposed system shows a high capability of the real-clinical application that offering a fast-automatic diagnosis and treatment solutions within 3 s to achieve the classification accuracy. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
Endoscopy-Driven Pretraining for Classification of Dysplasia in Barrett’s Esophagus with Endoscopic Narrow-Band Imaging Zoom Videos
Appl. Sci. 2020, 10(10), 3407; https://doi.org/10.3390/app10103407 - 14 May 2020
Cited by 1 | Viewed by 637
Abstract
Endoscopic diagnosis of early neoplasia in Barrett’s Esophagus is generally a two-step process of primary detection in overview, followed by detailed inspection of any visible abnormalities using Narrow Band Imaging (NBI). However, endoscopists struggle with evaluating NBI-zoom imagery of subtle abnormalities. In this [...] Read more.
Endoscopic diagnosis of early neoplasia in Barrett’s Esophagus is generally a two-step process of primary detection in overview, followed by detailed inspection of any visible abnormalities using Narrow Band Imaging (NBI). However, endoscopists struggle with evaluating NBI-zoom imagery of subtle abnormalities. In this work, we propose the first results of a deep learning system for the characterization of NBI-zoom imagery of Barrett’s Esophagus with an accuracy, sensitivity, and specificity of 83.6%, 83.1%, and 84.0%, respectively. We also show that endoscopy-driven pretraining outperforms two models, one without pretraining as well as a model with ImageNet initialization. The final model outperforms absence of pretraining by approximately 10% and the performance is 2% higher in terms of accuracy compared to ImageNet pretraining. Furthermore, the practical deployment of our model is not hampered by ImageNet licensing, thereby paving the way for clinical application. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
Prediction of Diabetic Nephropathy from the Relationship between Fatigue, Sleep and Quality of Life
Appl. Sci. 2020, 10(9), 3282; https://doi.org/10.3390/app10093282 - 08 May 2020
Viewed by 854
Abstract
Fatigue and poor sleep quality are the most common clinical complaints of people with diabetes mellitus (DM). These complaints are early signs of DM and are closely related to diabetic control and the presence of complications, which lead to a decline in the [...] Read more.
Fatigue and poor sleep quality are the most common clinical complaints of people with diabetes mellitus (DM). These complaints are early signs of DM and are closely related to diabetic control and the presence of complications, which lead to a decline in the quality of life. Therefore, an accurate measurement of the relationship between fatigue, sleep status, and the complication of DM nephropathy could lead to a specific definition of fatigue and an appropriate medical treatment. This study recruited 307 people with Type 2 diabetes from two medical centers in Northern Taiwan through a questionnaire survey and a retrospective investigation of medical records. In an attempt to identify the related factors and accurately predict diabetic nephropathy, we applied hybrid research methods, integrated biostatistics, and feature selection methods in data mining and machine learning to compare and verify the results. Consequently, the results demonstrated that patients with diabetic nephropathy have a higher fatigue level and Charlson comorbidity index (CCI) score than without neuropathy, the presence of neuropathy leads to poor sleep quality, lower quality of life, and poor metabolism. Furthermore, by considering feature selection in selecting representative features or variables, we achieved consistence results with a support vector machine (SVM) classifier and merely ten representative factors and a prediction accuracy as high as 74% in predicting the presence of diabetic nephropathy. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
Self-Service Data Science in Healthcare with Automated Machine Learning
Appl. Sci. 2020, 10(9), 2992; https://doi.org/10.3390/app10092992 - 25 Apr 2020
Cited by 2 | Viewed by 1292
Abstract
(1) Background: This work investigates whether and how researcher-physicians can be supported in their knowledge discovery process by employing Automated Machine Learning (AutoML). (2) Methods: We take a design science research approach and select the Tree-based Pipeline Optimization Tool (TPOT) as the AutoML [...] Read more.
(1) Background: This work investigates whether and how researcher-physicians can be supported in their knowledge discovery process by employing Automated Machine Learning (AutoML). (2) Methods: We take a design science research approach and select the Tree-based Pipeline Optimization Tool (TPOT) as the AutoML method based on a benchmark test and requirements from researcher-physicians. We then integrate TPOT into two artefacts: a web application and a notebook. We evaluate these artefacts with researcher-physicians to examine which approach suits researcher-physicians best. Both artefacts have a similar workflow, but different user interfaces because of a conflict in requirements. (3) Results: Artefact A, a web application, was perceived as better for uploading a dataset and comparing results. Artefact B, a Jupyter notebook, was perceived as better regarding the workflow and being in control of model construction. (4) Conclusions: Thus, a hybrid artefact would be best for researcher-physicians. However, both artefacts missed model explainability and an explanation of variable importance for their created models. Hence, deployment of AutoML technologies in healthcare remains currently limited to the exploratory data analysis phase. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Graphical abstract

Article
A Novel Architecture to Classify Histopathology Images Using Convolutional Neural Networks
Appl. Sci. 2020, 10(8), 2929; https://doi.org/10.3390/app10082929 - 23 Apr 2020
Cited by 3 | Viewed by 1430
Abstract
Histopathology is the study of tissue structure under the microscope to determine if the cells are normal or abnormal. Histopathology is a very important exam that is used to determine the patients’ treatment plan. The classification of histopathology images is very difficult to [...] Read more.
Histopathology is the study of tissue structure under the microscope to determine if the cells are normal or abnormal. Histopathology is a very important exam that is used to determine the patients’ treatment plan. The classification of histopathology images is very difficult to even an experienced pathologist, and a second opinion is often needed. Convolutional neural network (CNN), a particular type of deep learning architecture, obtained outstanding results in computer vision tasks like image classification. In this paper, we propose a novel CNN architecture to classify histopathology images. The proposed model consists of 15 convolution layers and two fully connected layers. A comparison between different activation functions was performed to detect the most efficient one, taking into account two different optimizers. To train and evaluate the proposed model, the publicly available PatchCamelyon dataset was used. The dataset consists of 220,000 annotated images for training and 57,000 unannotated images for testing. The proposed model achieved higher performance compared to the state-of-the-art architectures with an AUC of 95.46%. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
A Natural Language Processing Approach to Automated Highlighting of New Information in Clinical Notes
Appl. Sci. 2020, 10(8), 2824; https://doi.org/10.3390/app10082824 - 19 Apr 2020
Viewed by 798
Abstract
Electronic medical records (EMRs) have been used extensively in most medical institutions for more than a decade in Taiwan. However, information overload associated with rapid accumulation of large amounts of clinical narratives has threatened the effective use of EMRs. This situation is further [...] Read more.
Electronic medical records (EMRs) have been used extensively in most medical institutions for more than a decade in Taiwan. However, information overload associated with rapid accumulation of large amounts of clinical narratives has threatened the effective use of EMRs. This situation is further worsened by the use of “copying and pasting”, leading to lots of redundant information in clinical notes. This study aimed to apply natural language processing techniques to address this problem. New information in longitudinal clinical notes was identified based on a bigram language model. The accuracy of automated identification of new information was evaluated using expert annotations as the reference standard. A two-stage cross-over user experiment was conducted to evaluate the impact of highlighting of new information on task demands, task performance, and perceived workload. The automated method identified new information with an F1 score of 0.833. The user experiment found a significant decrease in perceived workload associated with a significantly higher task performance. In conclusion, automated identification of new information in clinical notes is feasible and practical. Highlighting of new information enables healthcare professionals to grasp key information from clinical notes with less perceived workload. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
The Feature Selection Effect on Missing Value Imputation of Medical Datasets
Appl. Sci. 2020, 10(7), 2344; https://doi.org/10.3390/app10072344 - 29 Mar 2020
Cited by 3 | Viewed by 1073
Abstract
In practice, many medical domain datasets are incomplete, containing a proportion of incomplete data with missing attribute values. Missing value imputation can be performed to solve the problem of incomplete datasets. To impute missing values, some of the observed data (i.e., complete data) [...] Read more.
In practice, many medical domain datasets are incomplete, containing a proportion of incomplete data with missing attribute values. Missing value imputation can be performed to solve the problem of incomplete datasets. To impute missing values, some of the observed data (i.e., complete data) are generally used as the reference or training set, and then the relevant statistical and machine learning techniques are employed to produce estimations to replace the missing values. Since the collected dataset usually contains a certain number of feature dimensions, it is useful to perform feature selection for better pattern recognition. Therefore, the aim of this paper is to examine the effect of performing feature selection on missing value imputation of medical datasets. Experiments are carried out on five different medical domain datasets containing various feature dimensions. In addition, three different types of feature selection methods and imputation techniques are employed for comparison. The results show that combining feature selection and imputation is a better choice for many medical datasets. However, the feature selection algorithm should be carefully chosen in order to produce the best result. Particularly, the genetic algorithm and information gain models are suitable for lower dimensional datasets, whereas the decision tree model is a better choice for higher dimensional datasets. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
Child’s Target Height Prediction Evolution
Appl. Sci. 2019, 9(24), 5447; https://doi.org/10.3390/app9245447 - 12 Dec 2019
Cited by 2 | Viewed by 1044
Abstract
This study is a contribution for the improvement of healthcare in children and in society generally. This study aims to predict children’s height when they become adults, also known as “target height”, to allow for a better growth assessment and more personalized healthcare. [...] Read more.
This study is a contribution for the improvement of healthcare in children and in society generally. This study aims to predict children’s height when they become adults, also known as “target height”, to allow for a better growth assessment and more personalized healthcare. The existing literature describes some existing prediction methods, based on longitudinal population studies and statistical techniques, which with few information resources, are able to produce acceptable results. The challenge of this study is in using a new approach based on machine learning to forecast the target height for children and (eventually) improve the existing height prediction accuracy. The goals of the study were achieved. The extreme gradient boosting regression (XGB) and light gradient boosting machine regression (LightGBM) algorithms achieved considerably better results on the height prediction. The developed model can be usefully applied by pediatricians and other clinical professionals in growth assessment. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Review

Jump to: Research

Review
Machine Learning in Chronic Pain Research: A Scoping Review
Appl. Sci. 2021, 11(7), 3205; https://doi.org/10.3390/app11073205 - 02 Apr 2021
Viewed by 570
Abstract
Given the high prevalence and associated cost of chronic pain, it has a significant impact on individuals and society. Improvements in the treatment and management of chronic pain may increase patients’ quality of life and reduce societal costs. In this paper, we evaluate [...] Read more.
Given the high prevalence and associated cost of chronic pain, it has a significant impact on individuals and society. Improvements in the treatment and management of chronic pain may increase patients’ quality of life and reduce societal costs. In this paper, we evaluate state-of-the-art machine learning approaches in chronic pain research. A literature search was conducted using the PubMed, IEEE Xplore, and the Association of Computing Machinery (ACM) Digital Library databases. Relevant studies were identified by screening titles and abstracts for keywords related to chronic pain and machine learning, followed by analysing full texts. Two hundred and eighty-seven publications were identified in the literature search. In total, fifty-three papers on chronic pain research and machine learning were reviewed. The review showed that while many studies have emphasised machine learning-based classification for the diagnosis of chronic pain, far less attention has been paid to the treatment and management of chronic pain. More research is needed on machine learning approaches to the treatment, rehabilitation, and self-management of chronic pain. As with other chronic conditions, patient involvement and self-management are crucial. In order to achieve this, patients with chronic pain need digital tools that can help them make decisions about their own treatment and care. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Review
Transfer Learning with Convolutional Neural Networks for Diabetic Retinopathy Image Classification. A Review
Appl. Sci. 2020, 10(6), 2021; https://doi.org/10.3390/app10062021 - 16 Mar 2020
Cited by 12 | Viewed by 2524
Abstract
Diabetic retinopathy (DR) is a dangerous eye condition that affects diabetic patients. Without early detection, it can affect the retina and may eventually cause permanent blindness. The early diagnosis of DR is crucial for its treatment. However, the diagnosis of DR is a [...] Read more.
Diabetic retinopathy (DR) is a dangerous eye condition that affects diabetic patients. Without early detection, it can affect the retina and may eventually cause permanent blindness. The early diagnosis of DR is crucial for its treatment. However, the diagnosis of DR is a very difficult process that requires an experienced ophthalmologist. A breakthrough in the field of artificial intelligence called deep learning can help in giving the ophthalmologist a second opinion regarding the classification of the DR by using an autonomous classifier. To accurately train a deep learning model to classify DR, an enormous number of images is required, and this is an important limitation in the DR domain. Transfer learning is a technique that can help in overcoming the scarcity of images. The main idea that is exploited by transfer learning is that a deep learning architecture, previously trained on non-medical images, can be fine-tuned to suit the DR dataset. This paper reviews research papers that focus on DR classification by using transfer learning to present the best existing methods to address this problem. This review can help future researchers to find out existing transfer learning methods to address the DR classification task and to show their differences in terms of performance. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Back to TopTop