Pattern Recognition and Artificial Intelligence in Biomedical Signal Processing

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Biomedical Engineering".

Deadline for manuscript submissions: closed (30 November 2023) | Viewed by 9240

Special Issue Editor

Department of Orthopedics and Traumatology, The University of Hong Kong, Hong Kong, China
Interests: clinical electrophysiology; neural engineering; neuroimaging; neural rehabilitation; biomedical signal processing; medical instrumentation and measurement

Special Issue Information

Dear Colleagues,

Biomedical signal processing is an interdisciplinary field concerned with the extraction of useful information from the biomedical data. Current clinical medicine and healthcare systems are working with various sophisticated devices, such as physiological, biological measurement and medical imaging. A great deal of data are generated from clinical and healthcare systems. Research on biomedical signal processing methods is fundamental for extracting effective information from raw data.

In this context, biomedical signal-processing algorithms with better robustness and effectiveness have become necessary to improving the reliability of health services. In recent years, pattern recognition and artificial intelligence have shown their distinct potential for leading significant progress in the field. Pattern recognition is a class of method for handling biomedical signals that emerged in last decade; it aims to recognize familiar patterns from varied biomedical signals. Compared with traditional methods for pattern recognition, artificial intelligence algorithms enable automatic feature extraction and representation learning, and massive quantities of data are used to improve the performance of these algorithms.

The aim of this Special Issue is to bring together researchers in this area to advance the development of cutting-edge applications of pattern recognition and/or artificial intelligence in biomedical signal processing.

This Special Issue will publish high-quality, original research papers in the following overlapping fields.

Pattern Recognition and Artificial Intelligence in:

  • Cardiovascular signals;
  • Neurological signals;
  • Physiological processes;
  • Medical images;
  • Biomedical signal modeling;
  • Motion control;
  • Audio and acoustic signal processing;
  • E-healthcare;
  • Biomedical signals from wearable sensors and systems;
  • Epidemiological data;
  • Infection information.

Dr. Yong 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 submissions that pass pre-check are 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 2400 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

  • pattern recognition
  • artificial intelligence
  • biomedical signal processing
  • deep learning
  • medical imaging
  • medical data analysis
  • medical robotics

Published Papers (8 papers)

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

Research

16 pages, 2703 KiB  
Article
Automatic Robust Crackle Detection and Localization Approach Using AR-Based Spectral Estimation and Support Vector Machine
by Loredana Daria Mang, Julio José Carabias-Orti, Francisco Jesús Canadas-Quesada, Juan de la Torre-Cruz, Antonio Muñoz-Montoro, Pablo Revuelta-Sanz and Eilas Fernandez Combarro
Appl. Sci. 2023, 13(19), 10683; https://doi.org/10.3390/app131910683 - 26 Sep 2023
Viewed by 816
Abstract
Auscultation primarily relies upon the acoustic expertise of individual doctors in identifying, through the use of a stethoscope, the presence of abnormal sounds such as crackles because the recognition of these sound patterns has critical importance in the context of early detection and [...] Read more.
Auscultation primarily relies upon the acoustic expertise of individual doctors in identifying, through the use of a stethoscope, the presence of abnormal sounds such as crackles because the recognition of these sound patterns has critical importance in the context of early detection and diagnosis of respiratory pathologies. In this paper, we propose a novel method combining autoregressive (AR)-based spectral features and a support vector machine (SVM) classifier to detect the presence of crackle events and their temporal location within the input signal. A preprocessing stage is performed to discard information out of the band of interest and define the segments for short-time signal analysis. The AR parameters are estimated for each segment to be classified by means of support vector machine (SVM) classifier into crackles and normal lung sounds using a set of synthetic crackle waveforms that have been modeled to train the classifier. A dataset composed of simulated and real coarse and fine crackles sound signals was created with several signal-to-noise (SNR) ratios to evaluate the robustness of the proposed method. Each simulated and real signal was mixed with noise that shows the same spectral energy distribution as typically found in breath noise from a healthy subject. This study makes a significant contribution by achieving competitive results. The proposed method yields values ranging from 80% in the lowest signal-to-noise ratio scenario to a perfect 100% in the highest signal-to-noise ratio scenario. Notably, these results surpass those of other methods presented by a margin of at least 15%. The combination of an autoregressive (AR) model with a support vector machine (SVM) classifier offers an effective solution for detecting the presented events. This approach exhibits enhanced robustness against variations in the signal-to-noise ratio that the input signals may encounter. Full article
Show Figures

Figure 1

18 pages, 4459 KiB  
Article
The Efficacy and Utility of Lower-Dimensional Riemannian Geometry for EEG-Based Emotion Classification
by Zubaidah Al-Mashhadani, Nasrin Bayat, Ibrahim F. Kadhim, Renoa Choudhury and Joon-Hyuk Park
Appl. Sci. 2023, 13(14), 8274; https://doi.org/10.3390/app13148274 - 17 Jul 2023
Viewed by 1269
Abstract
Electroencephalography (EEG) signals have diverse applications in brain-computer interfaces (BCIs), neurological condition diagnoses, and emotion recognition across healthcare, education, and entertainment domains. This paper presents a robust method that leverages Riemannian geometry to enhance the accuracy of EEG-based emotion classification. The proposed approach [...] Read more.
Electroencephalography (EEG) signals have diverse applications in brain-computer interfaces (BCIs), neurological condition diagnoses, and emotion recognition across healthcare, education, and entertainment domains. This paper presents a robust method that leverages Riemannian geometry to enhance the accuracy of EEG-based emotion classification. The proposed approach involves adaptive feature extraction using principal component analysis (PCA) in the Euclidean space to capture relevant signal characteristics and improve classification performance. Covariance matrices are derived from the extracted features and projected onto the Riemannian manifold. Emotion classification is performed using the minimum distance to Riemannian mean (MDRM) classifier. The effectiveness of the method was evaluated through experiments on four datasets, DEAP, DREAMER, MAHNOB, and SEED, demonstrating its generalizability and consistent accuracy improvement across different scenarios. The classification accuracy and robustness were compared with several state-of-the-art classification methods, which supports the validity and efficacy of using Riemannian geometry for enhancing the accuracy of EEG-based emotion classification. Full article
Show Figures

Figure 1

21 pages, 803 KiB  
Article
A Feature Construction Method That Combines Particle Swarm Optimization and Grammatical Evolution
by Ioannis G. Tsoulos and Alexandros Tzallas
Appl. Sci. 2023, 13(14), 8124; https://doi.org/10.3390/app13148124 - 12 Jul 2023
Viewed by 823
Abstract
The problem of data classification or data fitting is widely applicable in a multitude of scientific areas, and for this reason, a number of machine learning models have been developed. However, in many cases, these models present problems of overfitting and cannot generalize [...] Read more.
The problem of data classification or data fitting is widely applicable in a multitude of scientific areas, and for this reason, a number of machine learning models have been developed. However, in many cases, these models present problems of overfitting and cannot generalize satisfactorily to unknown data. Furthermore, in many cases, many of the features of the input data do not contribute to learning, or there may even be hidden correlations between the features of the dataset. The purpose of the proposed method is to significantly reduce data classification or regression errors through the usage of a technique that utilizes the particle swarm optimization method and grammatical evolution. This method is divided into two phases. In the first phase, artificial features are constructed using grammatical evolution, and the progress of the creation of these features is controlled by the particle swarm optimization method. In addition, this new technique utilizes penalty factors to limit the generated features to a range of values to make training machine learning models more efficient. In the second phase of the proposed technique, these features are exploited to transform the original dataset, and then any machine learning method can be applied to this dataset. The performance of the proposed method was measured on some benchmark datasets from the relevant literature. Also, the method was tested against a series of widely used machine learning models. The experiments performed showed a significant improvement of 30% on average in the classification datasets and an even greater improvement of 60% in the data fitting datasets. Full article
Show Figures

Figure 1

17 pages, 7152 KiB  
Article
Detection of Human Visceral Leishmaniasis Parasites in Microscopy Images from Bone Marrow Parasitological Examination
by Clésio Gonçalves, Armando Borges, Viviane Dias, Júlio Marques, Bruno Aguiar, Carlos Costa and Romuere Silva
Appl. Sci. 2023, 13(14), 8076; https://doi.org/10.3390/app13148076 - 11 Jul 2023
Cited by 1 | Viewed by 979
Abstract
Visceral Leishmaniasis (VL) is a neglected disease that affects between 50,000 and 90,000 new cases annually worldwide. In Brazil, VL causes about 3500 cases/per year. This chronic disease can lead to death in 90% of untreated cases. Thus, it is necessary to study [...] Read more.
Visceral Leishmaniasis (VL) is a neglected disease that affects between 50,000 and 90,000 new cases annually worldwide. In Brazil, VL causes about 3500 cases/per year. This chronic disease can lead to death in 90% of untreated cases. Thus, it is necessary to study safe technologies for diagnosing, treating, and controlling VL. Specialized laboratories carry out the VL diagnosis, and this step has a significant automation power through methods based on computational tools. The gold standard for detecting VL is the microscopy of material aspirated from the bone marrow to search for amastigotes. This work aims to assist in detecting amastigotes from microscopy images using deep learning techniques. The proposed methodology consists of segmenting the Leishmania parasites in the images, precisely indicating the location of the amastigotes in the image. In the detection of VL parasites, in this methodology, a Dice of 80.4% was obtained, Intersection over Union (IoU) of 75.2%, Accuracy of 99.1%, Precision of 81.5%, Sensitivity of 72.2%, Specificity of 99.6%, and Area under the Receiver Operating Characteristics Curve (AUC) of 86.5%. The results are promising and demonstrate that deep learning models trained with images of microscopy slides of biological material can precisely help the specialist detect VL in humans. Full article
Show Figures

Figure 1

13 pages, 2184 KiB  
Article
Dealing with Unreliable Annotations: A Noise-Robust Network for Semantic Segmentation through A Transformer-Improved Encoder and Convolution Decoder
by Ziyang Wang and Irina Voiculescu
Appl. Sci. 2023, 13(13), 7966; https://doi.org/10.3390/app13137966 - 07 Jul 2023
Cited by 2 | Viewed by 1030
Abstract
Conventional deep learning methods have shown promising results in the medical domain when trained on accurate ground truth data. Pragmatically, due to constraints like lack of time or annotator inexperience, the ground truth data obtained from clinical environments may not always be impeccably [...] Read more.
Conventional deep learning methods have shown promising results in the medical domain when trained on accurate ground truth data. Pragmatically, due to constraints like lack of time or annotator inexperience, the ground truth data obtained from clinical environments may not always be impeccably accurate. In this paper, we investigate whether the presence of noise in ground truth data can be mitigated. We propose an innovative and efficient approach that addresses the challenge posed by noise in segmentation labels. Our method consists of four key components within a deep learning framework. First, we introduce a Vision Transformer-based modified encoder combined with a convolution-based decoder for the segmentation network, capitalizing on the recent success of self-attention mechanisms. Second, we consider a public CT spine segmentation dataset and devise a preprocessing step to generate (and even exaggerate) noisy labels, simulating real-world clinical situations. Third, to counteract the influence of noisy labels, we incorporate an adaptive denoising learning strategy (ADL) into the network training. Finally, we demonstrate through experimental results that the proposed method achieves noise-robust performance, outperforming existing baseline segmentation methods across multiple evaluation metrics. Full article
Show Figures

Figure 1

16 pages, 4031 KiB  
Article
Effect of Subject-Specific Region of Interest on Motor Imagery Brain–Computer Interface
by Eltaf Abdalsalam Mohamed, Ibrahim Khalil Adam and Mohd Zuki Yusoff
Appl. Sci. 2023, 13(11), 6364; https://doi.org/10.3390/app13116364 - 23 May 2023
Cited by 1 | Viewed by 777
Abstract
A brain–computer interface (BCI), as a solution to disabled people’s concerns, has drawn attention in biomedical engineering over the last decade. However, the most existing brain–computer interface systems are based on the time or frequency domain of feature extraction, and it is associated [...] Read more.
A brain–computer interface (BCI), as a solution to disabled people’s concerns, has drawn attention in biomedical engineering over the last decade. However, the most existing brain–computer interface systems are based on the time or frequency domain of feature extraction, and it is associated with inaccurate detection of event-related desynchronization (ERD). In this study, a new algorithm relating to subject-specific regions of interest (ROIs) with intrinsic time-scale decomposition (ITD) was investigated to achieve satisfactory classification accuracy. ROI-based discrete wavelet transform (DWT) combined with an artificial neural network was used to validate the ROI-based ITD method. Experimentally recorded data of motor imagery movement tasks (right hand, left hand, both hands and both feet) were collected from 15 subjects. The parameters of the subject-specific regions of interest were investigated and optimized. An optimal condition was observed at a specific region of interest and the accuracy increased by 12.76 to 15.17% compared to that without ROI estimation. ITD showed higher classification accuracy, sensitivity, specificity and Kappa coefficient of 9.47%, 8.99%, 9.79% and 12.09%, respectively, for the four classes of motor imagery movements compared to DWT. The developed ITD model was validated using the dataset from BCI Competition IV. On average, ITD with ROIs showed 8.56% and 7.32% higher classification accuracy compared to common spatial patents (CSP) and DWT with ROIs. Full article
Show Figures

Figure 1

13 pages, 862 KiB  
Article
Characterization of the Intelligibility of Vowel–Consonant–Vowel (VCV) Recordings in Five Languages for Application in Speech-in-Noise Screening in Multilingual Settings
by Giulia Rocco, Giuliano Bernardi, Randall Ali, Toon van Waterschoot, Edoardo Maria Polo, Riccardo Barbieri and Alessia Paglialonga
Appl. Sci. 2023, 13(9), 5344; https://doi.org/10.3390/app13095344 - 25 Apr 2023
Viewed by 1069
Abstract
The purpose of this study is to characterize the intelligibility of a corpus of Vowel–Consonant–Vowel (VCV) stimuli recorded in five languages (English, French, German, Italian and Portuguese) in order to identify a subset of stimuli for screening individuals of unknown language during speech-in-noise [...] Read more.
The purpose of this study is to characterize the intelligibility of a corpus of Vowel–Consonant–Vowel (VCV) stimuli recorded in five languages (English, French, German, Italian and Portuguese) in order to identify a subset of stimuli for screening individuals of unknown language during speech-in-noise tests. The intelligibility of VCV stimuli was estimated by combining the psychometric functions derived from the Short-Time Objective Intelligibility (STOI) measure with those derived from listening tests. To compensate for the potential increase in speech recognition effort in non-native listeners, stimuli were selected based on three criteria: (i) higher intelligibility; (ii) lower variability of intelligibility; and (iii) shallower psychometric function. The observed intelligibility estimates show that the three criteria for application in multilingual settings were fulfilled by the set of VCVs in English (average intelligibility from 1% to 8% higher; SRT from 4.01 to 2.04 dB SNR lower; average variability up to four times lower; slope from 0.35 to 0.68%/dB SNR lower). Further research is needed to characterize the intelligibility of these stimuli in a large sample of non-native listeners with varying degrees of hearing loss and to determine the possible effects of hearing loss and native language on VCV recognition. Full article
Show Figures

Figure 1

18 pages, 951 KiB  
Article
Fuzzy Windows with Gaussian Processed Labels for Ordinal Image Scoring Tasks
by Cheng Kang, Xujing Yao and Daniel Novak
Appl. Sci. 2023, 13(6), 4019; https://doi.org/10.3390/app13064019 - 22 Mar 2023
Cited by 1 | Viewed by 1115
Abstract
In this paper, we propose a Fuzzy Window with the Gaussian Processed Label (FW-GPL) method to mitigate the overlap problem in the neighboring ordinal category when scoring images. Many published conventional methods treat this challenge as a traditional regression problem and make a [...] Read more.
In this paper, we propose a Fuzzy Window with the Gaussian Processed Label (FW-GPL) method to mitigate the overlap problem in the neighboring ordinal category when scoring images. Many published conventional methods treat this challenge as a traditional regression problem and make a strong assumption that each ordinal category owns an adequate intrinsic rank to outline its distribution. Our FW-GPL method aims to refine the ordinal label pattern by using two novel techniques: (1) assembling fuzzy logic to the fully connected layer of convolution neural networks and (2) transforming the ordinal labels with a Gaussian process. Specifically, it incorporates a heuristic fuzzy logic from the ordinal characteristic and simultaneously plugs in ordinal distribution shapes that penalize the difference between the targeted label and its neighbors to ensure a concentrated regional distribution. Accordingly, the function of these proposed windows is leveraged to minimize the influence of majority classes that mislead the prediction of minority samples. Our model is specifically designed to carefully avoid partially missing continuous facial-age segments. It can perform competitively when using the whole continuous facial-age dataset. Extensive experimental results on three facial-aging datasets and one ambiguous medical dataset demonstrate that our FW-GPL can achieve compelling performance results compared to the State-Of-The-Art (SOTA). Full article
Show Figures

Figure 1

Back to TopTop