Sensors

Research

18 pages, 3491 KiB

Open AccessArticle

RT-4M: Real-Time Mosaicing Manager for Manual Microscopy System

by Nobuhito Mori, Yoshihiro Miyazaki, Tatsuya Oda and Yasuyuki S. Kida

Sensors 2025, 25(10), 2968; https://doi.org/10.3390/s25102968 - 8 May 2025

Viewed by 228

The creation of virtual slides, i.e., high-resolution digital images of biological samples, is expensive, and existing manual methods often suffer from stitching errors and additional reimaging costs. To address these issues, we propose a real-time mosaicing manager for manual microscopy (RT-4M) that performs [...] Read more.

The creation of virtual slides, i.e., high-resolution digital images of biological samples, is expensive, and existing manual methods often suffer from stitching errors and additional reimaging costs. To address these issues, we propose a real-time mosaicing manager for manual microscopy (RT-4M) that performs real-time stitching and allows users to preview slides during imaging using existing manual microscopy systems, thereby reducing the need for reimaging. We install it on two different microscopy systems, successfully creating virtual slides of hematoxylin and eosin- and fluorescent-stained tissues obtained from humans and mice. The fluorescent-stained tissues consist of two colors, requiring the manual switching of the filter and an exposure time of 1.6 s per color. Even in the case of the largest dataset in this study (over 900 images), the entire sample is captured without any omissions. Moreover, RT-4M exhibits a processing time of less than one second per registration, indicating that it does not hinder the user’s imaging workflow. Additionally, the composition process reduces the misalignment rate by a factor of 20 compared to existing software. We believe that the proposed software will prove useful in the fields of pathology and bio-research, particularly for facilities with relatively limited budgets. Full article

(This article belongs to the Special Issue Applications of Biomedical Imaging and Sensing Technologies in Disease Diagnosis)

► Show Figures

Figure 1

26 pages, 3790 KiB

Open AccessArticle

An Enhanced Approach Using AGS Network for Skin Cancer Classification

by Hwanyoung Lee, Seeun Cho, Jiyoon Song, Hoyoung Kim and Youjin Shin

Sensors 2025, 25(2), 394; https://doi.org/10.3390/s25020394 - 10 Jan 2025

Viewed by 1050

Abstract

Skin cancer accounts for over 40% of all cancer diagnoses worldwide. However, accurately diagnosing skin cancer remains challenging for dermatologists, as multiple types of skin cancer often appear visually similar. The diagnostic accuracy of dermatologists ranges between 62% and 80%. Although AI models [...] Read more.

Skin cancer accounts for over 40% of all cancer diagnoses worldwide. However, accurately diagnosing skin cancer remains challenging for dermatologists, as multiple types of skin cancer often appear visually similar. The diagnostic accuracy of dermatologists ranges between 62% and 80%. Although AI models have shown promise in assisting with skin cancer classification in various studies, obtaining the large-scale medical image datasets required for AI model training is not straightforward. To address this limitation, this study proposes the AGS network, designed to overcome the challenges of small datasets and enhance the performance of skin cancer classifiers. The AGS network integrates three key modules: Augmentation (A), GAN (G), and Segmentation (S). It was evaluated using eight deep learning classifiers—GoogLeNet, DenseNet201, ResNet50, MobileNet V3, EfficientNet B0, ViT, EfficientNet V2, and Swin Transformers—on the HAM10000 dataset. Five model configurations were also tested to assess the contribution of each module. The results showed that all eight classifiers demonstrated consistent performance improvements with the AGS network. In particular, EfficientNet V2 + AGS achieved the most significant performance gains over the baseline model, with an increase of +0.1808 in Accuracy and +0.1674 in F1-Score. Among all configurations, ResNet50+AGS achieved the best overall performance, with an Accuracy of 95.87% and an F1-Score of 95.73%. While most previous studies focused on single augmentation methods, this study demonstrates the effectiveness of combining multiple augmentation techniques within an integrated framework. The AGS network demonstrates how integrating diverse methods can improve the performance of skin cancer classification models. Full article

(This article belongs to the Special Issue Applications of Biomedical Imaging and Sensing Technologies in Disease Diagnosis)

► Show Figures

Figure 1

29 pages, 2915 KiB

Open AccessArticle

Machine Learning Recognizes Stages of Parkinson’s Disease Using Magnetic Resonance Imaging

by Artur Chudzik

Sensors 2024, 24(24), 8152; https://doi.org/10.3390/s24248152 - 20 Dec 2024

Viewed by 1113

Abstract

Neurodegenerative diseases (NDs), such as Alzheimer’s disease (AD) and Parkinson’s disease (PD), are debilitating conditions that affect millions worldwide, and the number of cases is expected to rise significantly in the coming years. Because early detection is crucial for effective intervention strategies, this [...] Read more.

Neurodegenerative diseases (NDs), such as Alzheimer’s disease (AD) and Parkinson’s disease (PD), are debilitating conditions that affect millions worldwide, and the number of cases is expected to rise significantly in the coming years. Because early detection is crucial for effective intervention strategies, this study investigates whether the structural analysis of selected brain regions, including volumes and their spatial relationships obtained from regular T1-weighted MRI scans (N = 168, PPMI database), can model stages of PD using standard machine learning (ML) techniques. Thus, diverse ML models, including Logistic Regression, Random Forest, Support Vector Classifier, and Rough Sets, were trained and evaluated. Models used volumes, Euclidean, and Cosine distances of subcortical brain structures relative to the thalamus to differentiate among control (HC), prodromal (PR), and PD groups. Based on three separate experiments, the Logistic Regression approach was optimal, providing low feature complexity and strong predictive performance (accuracy: 85%, precision: 88%, recall: 85%) in PD-stage recognition. Using interpretable metrics, such as the volume- and centroid-based spatial distances, models achieved high diagnostic accuracy, presenting a promising framework for early-stage PD identification based on MRI scans. Full article

(This article belongs to the Special Issue Applications of Biomedical Imaging and Sensing Technologies in Disease Diagnosis)

► Show Figures

Figure 1

18 pages, 8204 KiB

Open AccessArticle

Low-Quality Sensor Data-Based Semi-Supervised Learning for Medical Image Segmentation

by Hengfan Li, Xuanbo Xu, Ziheng Liu, Qingfeng Xia and Min Xia

Sensors 2024, 24(23), 7799; https://doi.org/10.3390/s24237799 - 5 Dec 2024

Viewed by 827

Abstract

Traditional medical image sensors face multiple challenges. First, these sensors typically rely on large amounts of labeled data, which are time-consuming and costly to obtain. Second, when the data volume and image size are large, traditional sensors have limited computational power, making it [...] Read more.

Traditional medical image sensors face multiple challenges. First, these sensors typically rely on large amounts of labeled data, which are time-consuming and costly to obtain. Second, when the data volume and image size are large, traditional sensors have limited computational power, making it difficult to effectively train and infer models. Additionally, traditional sensors have poor generalization ability and struggle to adapt to datasets with different modalities. This paper devises a novel framework, named LSDSL, and deploys it in the sensor. LSDSL utilizes low-quality sensor data for semi-supervised learning in medical image segmentation. in supervised learning, we devise the hard region exploration (hre) module to enhance the model’s comprehension of low-quality pixels in hard regions. in unsupervised learning, we introduce a pseudo-label sharing (ps) module, which allows low-quality pixels in one network to learn from the high-quality pixels in the other networks. our model outperforms other semi-supervised methods on the datasets of two different modalities (CT and MRI) in medical image sensors, achieving superior inference speed and segmentation accuracy. Full article

(This article belongs to the Special Issue Applications of Biomedical Imaging and Sensing Technologies in Disease Diagnosis)

► Show Figures

Figure 1

15 pages, 6265 KiB

Open AccessArticle

LPC-SonoNet: A Lightweight Network Based on SonoNet and Light Pyramid Convolution for Fetal Ultrasound Standard Plane Detection

by Tianxiang Yu, Po-Hsiang Tsui, Denis Leonov, Shuicai Wu, Guangyu Bin and Zhuhuang Zhou

Sensors 2024, 24(23), 7510; https://doi.org/10.3390/s24237510 - 25 Nov 2024

Viewed by 1014

Abstract

The detection of fetal ultrasound standard planes (FUSPs) is important for the diagnosis of fetal malformation and the prevention of perinatal death. As a promising deep-learning technique in FUSP detection, SonoNet’s network parameters have a large size. In this paper, we introduced a [...] Read more.

The detection of fetal ultrasound standard planes (FUSPs) is important for the diagnosis of fetal malformation and the prevention of perinatal death. As a promising deep-learning technique in FUSP detection, SonoNet’s network parameters have a large size. In this paper, we introduced a light pyramid convolution (LPC) block into SonoNet and proposed LPC-SonoNet with reduced network parameters for FUSP detection. The LPC block used pyramid convolution architecture inspired by SimSPPF from YOLOv6 and was able to extract features from various scales with a small parameter size. Using SonoNet64 as the backbone, the proposed network removed one of the convolutional blocks in SonoNet64 and replaced the others with LPC blocks. The proposed LPC-SonoNet model was trained and tested on a publicly available dataset with 12,400 ultrasound images. The dataset with six categories was further divided into nine categories. The images were randomly divided into a training set, a validation set, and a test set in a ratio of 8:1:1. Data augmentation was conducted on the training set to address the data imbalance issue. In the classification of six categories and nine categories, LPC-SonoNet obtained the accuracy of 97.0% and 91.9% on the test set, respectively, slightly higher than the accuracy of 96.60% and 91.70% by SonoNet64. Compared with SonoNet64 with 14.9 million parameters, LPC-SonoNet had a much smaller parameter size (4.3 million). This study pioneered the deep-learning classification of nine categories of FUSPs. The proposed LPC-SonoNet may be used as a lightweight network for FUSP detection. Full article

(This article belongs to the Special Issue Applications of Biomedical Imaging and Sensing Technologies in Disease Diagnosis)

► Show Figures

Figure 1

10 pages, 8355 KiB

Open AccessCommunication

Triple Spectral Line Imaging of Whole-Body Human Skin: Equipment, Image Processing, and Clinical Data

by Janis Spigulis, Uldis Rubins, Edgars Kviesis-Kipge, Inga Saknite, Ilze Oshina and Egija Vasilisina

Sensors 2024, 24(22), 7348; https://doi.org/10.3390/s24227348 - 18 Nov 2024

Viewed by 934

Abstract

Multispectral imaging can provide objective quantitative data on various clinical pathologies, e.g., abnormal content of bio-substances in human skin. Performance of diagnostics increases with decreased spectral bandwidths of imaging; from this point, ultra-narrowband laser spectral line imaging is well suited for diagnostic applications. [...] Read more.

Multispectral imaging can provide objective quantitative data on various clinical pathologies, e.g., abnormal content of bio-substances in human skin. Performance of diagnostics increases with decreased spectral bandwidths of imaging; from this point, ultra-narrowband laser spectral line imaging is well suited for diagnostic applications. In this study, 40 volunteers participated in clinical validation tests of a newly developed prototype device for triple laser line whole-body skin imaging. The device comprised a vertically movable high-resolution camera coupled with a specific illumination unit—a side-emitting optical fiber spiral that emits simultaneously three RGB laser spectral lines at the wavelengths 450 nm, 520 nm, and 628 nm. The prototype’s design details, skin spectral image processing, and the obtained first clinical data are reported and discussed. Full article

(This article belongs to the Special Issue Applications of Biomedical Imaging and Sensing Technologies in Disease Diagnosis)

► Show Figures

Figure 1

17 pages, 2468 KiB

Open AccessArticle

CRASA: Chili Pepper Disease Diagnosis via Image Reconstruction Using Background Removal and Generative Adversarial Serial Autoencoder

by Jongwook Si and Sungyoung Kim

Sensors 2024, 24(21), 6892; https://doi.org/10.3390/s24216892 - 27 Oct 2024

Cited by 1 | Viewed by 784

Abstract

With the recent development of smart farms, researchers are very interested in such fields. In particular, the field of disease diagnosis is the most important factor. Disease diagnosis belongs to the field of anomaly detection and aims to distinguish whether plants or fruits [...] Read more.

With the recent development of smart farms, researchers are very interested in such fields. In particular, the field of disease diagnosis is the most important factor. Disease diagnosis belongs to the field of anomaly detection and aims to distinguish whether plants or fruits are normal or abnormal. The problem can be solved by binary or multi-classification based on a Convolutional Neural Network (CNN), but it can also be solved by image reconstruction. However, due to the limitation of the performance of image generation, SOTA’s methods propose a score calculation method using a latent vector error. In this paper, we propose a network that focuses on chili peppers and proceeds with background removal through GrabCut. It shows a high performance through an image-based score calculation method. Due to the difficulty of reconstructing the input image, the difference between the input and output images is large. However, the serial autoencoder proposed in this paper uses the difference between the two fake images, instead of the actual input, as a score. We propose a method of generating meaningful images using the GAN structure and classifying three results simultaneously by one discriminator. The proposed method showed a higher performance than previous research, and image-based scores showed the best performance. Full article

(This article belongs to the Special Issue Applications of Biomedical Imaging and Sensing Technologies in Disease Diagnosis)

► Show Figures

Figure 1

16 pages, 5621 KiB

Open AccessArticle

Kinect-Based Gait Analysis System Design and Concurrent Validity in Persons with Anterolateral Shoulder Pain Syndrome, Results from a Pilot Study

by Fredy Bernal, Veronique Feipel and Mauricio Plaza

Sensors 2024, 24(19), 6351; https://doi.org/10.3390/s24196351 - 30 Sep 2024

Viewed by 1105

Abstract

As part of an investigation to detect asymmetries in gait patterns in persons with shoulder injuries, the goal of the present study was to design and validate a Kinect-based motion capture system that would enable the extraction of joint kinematics curves during gait [...] Read more.

As part of an investigation to detect asymmetries in gait patterns in persons with shoulder injuries, the goal of the present study was to design and validate a Kinect-based motion capture system that would enable the extraction of joint kinematics curves during gait and to compare them with the data obtained through a commercial motion capture system. The study included eight male and two female participants, all diagnosed with anterolateral shoulder pain syndrome in their right upper extremity with a minimum 18 months of disorder evolution. The participants had an average age of 31.8 ± 9.8 years, a height of 173 ± 18 cm, and a weight of 81 ± 15 kg. The gait kinematics were sampled simultaneously with the new system and the Clinical 3DMA system. Shoulder, elbow, hip, and knee kinematics were compared between systems for the pathological and non-pathological sides using repeated measures ANOVA and 1D statistical parametric mapping. For most variables, no significant difference was found between systems. Evidence of a significant difference between the newly developed system and the commercial system was found for knee flexion–extension (p < 0.004, between 60 and 80% of the gait cycle), and for shoulder abduction–adduction. The good concurrent validity of the new Kinect-based motion analysis system found in this study opens promising perspectives for clinical motion tracking using an affordable and simple system. Full article

(This article belongs to the Special Issue Applications of Biomedical Imaging and Sensing Technologies in Disease Diagnosis)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Applications of Biomedical Imaging and Sensing Technologies in Disease Diagnosis

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (8 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI