Submit to Special Issue Submit Abstract to Special Issue Review for Bioengineering Propose a Special Issue

Journal Menu

Journal Browser

► Journal Browser

Application of Deep Learning in Medical Diagnosis

Special Issue Editors
Special Issue Information
Keywords
Benefits of Publishing in a Special Issue
Published Papers

A special issue of Bioengineering (ISSN 2306-5354). This special issue belongs to the section "Biosignal Processing".

Deadline for manuscript submissions: 31 May 2025 | Viewed by 8110

Share This Special Issue

Special Issue Editors

Prof. Dr. Zhanlin Ji

E-Mail Website
Guest Editor

1. Hebei Key Laboratory of Industrial Intelligent Perception, North China University of Science and Technology, Tangshan 063210, China
2. Telecommunications Research Centre (TRC), University of Limerick, V94 T9PX Limerick, Ireland
Interests: the ubiquitous consumer wireless world (UCWW); the Internet of Things (IoT); cloud computing; big data management; data mining
Special Issues, Collections and Topics in MDPI journals

Dr. Li Zhao

E-Mail Website
Guest Editor

The Speech and Language Technology Team (CSLT) of the National Research Center for Information Science and Technology in Beijing, Tsinghua University, Beijing, China
Interests: mobile computing; Internet of Things (IoT); e-health systems; intelligent transportation systems (ITS); home networking; machine learning; digital multimedia

Special Issue Information

Dear Colleagues,

The application of deep learning in medical diagnostics is revolutionizing the field of medicine. Especially in medical imaging diagnosis, the introduction of deep learning methods has had a profound impact on the workflow from image acquisition to diagnostic reporting. These methods excel at automating tedious image analysis tasks and efficiently processing large and complex medical image datasets.

The interventions of deep learning and artificial intelligence provide new possibilities for accelerating medical diagnosis. As hardware and algorithms continue to advance, researchers are better able to understand and predict a patient's condition and link medical images to disease features. Deep learning has shown great potential in the interpretation of medical images, such as in foci segmentation, cancer detection, disease classification, and so on.

However, it is important to note that the correct application of deep learning is crucial in medical diagnosis. With deep learning, the data are analyzed and interpreted with the help of computer-expanded knowledge. The impact of these tools is huge, and the use of AI is helping many stakeholders in the field of smart healthcare. The future of applying deep learning in medical diagnostics is exciting, promising not only to improve diagnostic accuracy but also to potentially provide more precise information for personalized medicine and treatment planning. Developments in this field are pushing medical science to new heights to provide better medical care for patients.

The range of research topics may include, but are not limited to:

Medical image processing;
Focus segmentation based on medical images;
Lesion target detection based on medical images;
Classification of lesion grade and category in medical images;
Natural language processing and knowledge discovery in medical documentation;
Biomedical image reconstruction;
Automatic/computer-aided diagnosis based on deep learning.

Prof. Dr. Zhanlin Ji
Dr. Li Zhao
Guest Editors

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. Bioengineering is an international peer-reviewed open access monthly 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 2700 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

deep learning
artificial intelligence
medical image segmentation
medical image target detection
medical image classification
computer-assisted therapy

Benefits of Publishing in a Special Issue

Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (7 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

15 pages, 685 KiB

Open AccessArticle

Using a Neural Network Architecture for the Prediction of Neurologic Outcome for Out-of-Hospital Cardiac Arrests Using Hospital Level Variables and Novel Physiologic Markers

by Martha Razo, Pavitra Kotini, Jing Li, Shaveta Khosla, Irina A. Buhimschi, Terry Vanden Hoek, Marina Del Rios and Houshang Darabi

Bioengineering 2025, 12(2), 124; https://doi.org/10.3390/bioengineering12020124 - 29 Jan 2025

Viewed by 316

Abstract

Out-of-hospital cardiac arrest (OHCA) is a major public health burden due to its high mortality rate, sudden nature, and long-term impact on survivors. Consequently, there is a crucial need to create prediction models to better understand patient trajectories and assist clinicians and families in making informed decisions. We studied 107 adult OHCA patients admitted at an academic Emergency Department (ED) from 2018–2023. Blood samples and ocular ultrasounds were acquired at 1, 6, and 24 h after return of spontaneous circulation (ROSC). Six classes of clinical and novel variables were used: (1) Vital signs after ROSC, (2) pre-hospital and ED data, (3) hospital admission data, (4) ocular ultrasound parameters, (5) plasma protein biomarkers and (6) sex steroid hormones. A base model was built using 1 h variables in classes 1–3, reasoning these are available in most EDs. Extending from the base model, we evaluated 26 distinct neural network models for prediction of neurological outcome by the cerebral performance category (CPC) score. The top-performing model consisted of all variables at 1 h resulting in an AUROC score of 0.946. We determined a parsimonious set of variables that optimally predicts CPC score. Our research emphasizes the added value of incorporating ocular ultrasound, plasma biomarkers, sex hormones in the development of more robust predictive models for neurological outcome after OHCA. Full article

(This article belongs to the Special Issue Application of Deep Learning in Medical Diagnosis)

► Show Figures

Graphical abstract

42 pages, 7150 KiB

Open AccessArticle

LightweightUNet: Multimodal Deep Learning with GAN-Augmented Imaging Data for Efficient Breast Cancer Detection

by Hari Mohan Rai, Joon Yoo, Saurabh Agarwal and Neha Agarwal

Bioengineering 2025, 12(1), 73; https://doi.org/10.3390/bioengineering12010073 - 15 Jan 2025

Viewed by 767

Abstract

Breast cancer ranks as the second most prevalent cancer globally and is the most frequently diagnosed cancer among women; therefore, early, automated, and precise detection is essential. Most AI-based techniques for breast cancer detection are complex and have high computational costs. Hence, to overcome this challenge, we have presented the innovative LightweightUNet hybrid deep learning (DL) classifier for the accurate classification of breast cancer. The proposed model boasts a low computational cost due to its smaller number of layers in its architecture, and its adaptive nature stems from its use of depth-wise separable convolution. We have employed a multimodal approach to validate the model’s performance, using 13,000 images from two distinct modalities: mammogram imaging (MGI) and ultrasound imaging (USI). We collected the multimodal imaging datasets from seven different sources, including the benchmark datasets DDSM, MIAS, INbreast, BrEaST, BUSI, Thammasat, and HMSS. Since the datasets are from various sources, we have resized them to the uniform size of 256 × 256 pixels and normalized them using the Box-Cox transformation technique. Since the USI dataset is smaller, we have applied the StyleGAN3 model to generate 10,000 synthetic ultrasound images. In this work, we have performed two separate experiments: the first on a real dataset without augmentation and the second on a real + GAN-augmented dataset using our proposed method. During the experiments, we used a 5-fold cross-validation method, and our proposed model obtained good results on the real dataset (87.16% precision, 86.87% recall, 86.84% F1-score, and 86.87% accuracy) without adding any extra data. Similarly, the second experiment provides better performance on the real + GAN-augmented dataset (96.36% precision, 96.35% recall, 96.35% F1-score, and 96.35% accuracy). This multimodal approach, which utilizes LightweightUNet, enhances the performance by 9.20% in precision, 9.48% in recall, 9.51% in F1-score, and a 9.48% increase in accuracy on the combined dataset. The LightweightUNet model we proposed works very well thanks to a creative network design, adding fake images to the data, and a multimodal training method. These results show that the model has a lot of potential for use in clinical settings. Full article

(This article belongs to the Special Issue Application of Deep Learning in Medical Diagnosis)

► Show Figures

Figure 1

12 pages, 6937 KiB

Open AccessArticle

External Validation of Deep Learning Models for Classifying Etiology of Retinal Hemorrhage Using Diverse Fundus Photography Datasets

by Pooya Khosravi, Nolan A. Huck, Kourosh Shahraki, Elina Ghafari, Reza Azimi, So Young Kim, Eric Crouch, Xiaohui Xie and Donny W. Suh

Bioengineering 2025, 12(1), 20; https://doi.org/10.3390/bioengineering12010020 - 29 Dec 2024

Viewed by 750

Abstract

Retinal hemorrhage (RH) is a significant clinical finding with various etiologies, necessitating accurate classification for effective management. This study aims to externally validate deep learning (DL) models, specifically FastVit_SA12 and ResNet18, for distinguishing between traumatic and medical causes of RH using diverse fundus photography datasets. A comprehensive dataset was compiled, including private collections from South Korea and Virginia, alongside publicly available datasets such as RFMiD, BRSET, and DeepEyeNet. The models were evaluated on a total of 2661 images, achieving high performance metrics. FastVit_SA12 demonstrated an overall accuracy of 96.99%, with a precision of 0.9935 and recall of 0.9723 for medical cases, while ResNet18 achieved a 94.66% accuracy with a precision of 0.9893. A Grad-CAM analysis revealed that ResNet18 emphasized global vascular patterns, such as arcuate vessels, while FastVit_SA12 focused on clinically relevant areas, including the optic disk and hemorrhagic regions. Medical cases showed localized activations, whereas trauma-related images displayed diffuse patterns across the fundus. Both models exhibited strong sensitivity and specificity, indicating their potential utility in clinical settings for accurate RH diagnosis. This study underscores the importance of external validation in enhancing the reliability and applicability of AI models in ophthalmology, paving the way for improved patient care and outcomes. Full article

(This article belongs to the Special Issue Application of Deep Learning in Medical Diagnosis)

► Show Figures

Figure 1

16 pages, 3888 KiB

Open AccessArticle

Impact of Deep Learning-Based Image Reconstruction on Tumor Visibility and Diagnostic Confidence in Computed Tomography

by Marie Bertl, Friedrich-Georg Hahne, Stephanie Gräger and Andreas Heinrich

Bioengineering 2024, 11(12), 1285; https://doi.org/10.3390/bioengineering11121285 - 18 Dec 2024

Viewed by 722

Abstract

Deep learning image reconstruction (DLIR) has shown potential to enhance computed tomography (CT) image quality, but its impact on tumor visibility and adoption among radiologists with varying experience levels remains unclear. This study compared the performance of two deep learning-based image reconstruction methods, DLIR and Pixelshine, an adaptive statistical iterative reconstruction—volume (ASIR-V) method, and filtered back projection (FBP) across 33 contrast-enhanced CT staging examinations, evaluated by 20–24 radiologists. The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were measured for tumor and surrounding organ tissues across DLIR (Low, Medium, High), Pixelshine (Soft, Ultrasoft), ASIR-V (30–100%), and FBP. In two blinded surveys, radiologists ranked eight reconstructions and assessed four using a 5-point Likert scale in arterial and portal venous phases. DLIR consistently outperformed other methods in SNR, CNR, image quality, image interpretation, structural differentiability and diagnostic certainty. Pixelshine performed comparably only to ASIR-V 50%. No significant differences were observed between junior and senior radiologists. In conclusion, DLIR-based techniques have the potential to establish a new benchmark in clinical CT imaging, offering superior image quality for tumor staging, enhanced diagnostic capabilities, and seamless integration into existing workflows without requiring an extensive learning curve. Full article

(This article belongs to the Special Issue Application of Deep Learning in Medical Diagnosis)

► Show Figures

Graphical abstract

11 pages, 1860 KiB

Open AccessArticle

Enhancing Radiomics Reproducibility: Deep Learning-Based Harmonization of Abdominal Computed Tomography (CT) Images

by Seul Bi Lee, Youngtaek Hong, Yeon Jin Cho, Dawun Jeong, Jina Lee, Jae Won Choi, Jae Yeon Hwang, Seunghyun Lee, Young Hun Choi and Jung-Eun Cheon

Bioengineering 2024, 11(12), 1212; https://doi.org/10.3390/bioengineering11121212 - 30 Nov 2024

Viewed by 749

Abstract

We assessed the feasibility of using deep learning-based image harmonization to improve the reproducibility of radiomics features in abdominal CT scans. In CT imaging, harmonization adjusts images from different institutions to ensure consistency despite variations in scanners and acquisition protocols. This process is essential because such differences can lead to variability in radiomics features, affecting reproducibility and accuracy. Harmonizing images minimizes these inconsistencies, supporting more reliable and clinically applicable results across diverse settings. A pre-trained harmonization algorithm was applied to 63 dual-energy abdominal CT images, which were reconstructed into four different types, and 10 regions of interest (ROIs) were analyzed. From the original 455 radiomics features per ROI, 387 were used after excluding redundant features. Reproducibility was measured using the intraclass correlation coefficient (ICC), with a threshold of ICC ≥ 0.85 indicating acceptable reproducibility. The region-based analysis revealed significant improvements in reproducibility post-harmonization, especially in vessel features, which increased from 14% to 69%. Other regions, including the spleen, kidney, muscle, and liver parenchyma, also saw notable improvements, although air reproducibility slightly decreased from 95% to 94%, impacting only a few features. In patient-based analysis, reproducible features increased from 18% to 65%, with an average of 179 additional reproducible features per patient after harmonization. These results demonstrate that deep learning-based harmonization can significantly enhance the reproducibility of radiomics features in abdominal CT, offering promising potential for advancing radiomics development and its clinical applications. Full article

(This article belongs to the Special Issue Application of Deep Learning in Medical Diagnosis)

► Show Figures

Graphical abstract

19 pages, 5200 KiB

Open AccessArticle

Precision Identification of Locally Advanced Rectal Cancer in Denoised CT Scans Using EfficientNet and Voting System Algorithms

by Chun-Yu Lin, Jacky Chung-Hao Wu, Yen-Ming Kuan, Yi-Chun Liu, Pi-Yi Chang, Jun-Peng Chen, Henry Horng-Shing Lu and Oscar Kuang-Sheng Lee

Bioengineering 2024, 11(4), 399; https://doi.org/10.3390/bioengineering11040399 - 19 Apr 2024

Cited by 1 | Viewed by 1989

Abstract

Background and objective: Local advanced rectal cancer (LARC) poses significant treatment challenges due to its location and high recurrence rates. Accurate early detection is vital for treatment planning. With magnetic resonance imaging (MRI) being resource-intensive, this study explores using artificial intelligence (AI) to interpret computed tomography (CT) scans as an alternative, providing a quicker, more accessible diagnostic tool for LARC. Methods: In this retrospective study, CT images of 1070 T3–4 rectal cancer patients from 2010 to 2022 were analyzed. AI models, trained on 739 cases, were validated using two test sets of 134 and 197 cases. By utilizing techniques such as nonlocal mean filtering, dynamic histogram equalization, and the EfficientNetB0 algorithm, we identified images featuring characteristics of a positive circumferential resection margin (CRM) for the diagnosis of locally advanced rectal cancer (LARC). Importantly, this study employs an innovative approach by using both hard and soft voting systems in the second stage to ascertain the LARC status of cases, thus emphasizing the novelty of the soft voting system for improved case identification accuracy. The local recurrence rates and overall survival of the cases predicted by our model were assessed to underscore its clinical value. Results: The AI model exhibited high accuracy in identifying CRM-positive images, achieving an area under the curve (AUC) of 0.89 in the first test set and 0.86 in the second. In a patient-based analysis, the model reached AUCs of 0.84 and 0.79 using a hard voting system. Employing a soft voting system, the model attained AUCs of 0.93 and 0.88, respectively. Notably, AI-identified LARC cases exhibited a significantly higher five-year local recurrence rate and displayed a trend towards increased mortality across various thresholds. Furthermore, the model’s capability to predict adverse clinical outcomes was superior to those of traditional assessments. Conclusion: AI can precisely identify CRM-positive LARC cases from CT images, signaling an increased local recurrence and mortality rate. Our study presents a swifter and more reliable method for detecting LARC compared to traditional CT or MRI techniques. Full article

(This article belongs to the Special Issue Application of Deep Learning in Medical Diagnosis)

► Show Figures

Graphical abstract

15 pages, 2250 KiB

Open AccessArticle

DTONet a Lightweight Model for Melanoma Segmentation

by Shengnan Hao, Hongzan Wang, Rui Chen, Qinping Liao, Zhanlin Ji, Tao Lyu and Li Zhao

Bioengineering 2024, 11(4), 390; https://doi.org/10.3390/bioengineering11040390 - 18 Apr 2024

Cited by 1 | Viewed by 1850

Abstract

With the further development of neural networks, automatic segmentation techniques for melanoma are becoming increasingly mature, especially under the conditions of abundant hardware resources. This allows for the accuracy of segmentation to be improved by increasing the complexity and computational capacity of the model. However, a new problem arises when it comes to actual applications, as there may not be the high-end hardware available, especially in hospitals and among the general public, who may have limited computing resources. In response to this situation, this paper proposes a lightweight deep learning network that can achieve high segmentation accuracy with minimal resource consumption. We introduce a network called DTONet (double-tailed octave network), which was specifically designed for this purpose. Its computational parameter count is only 30,859, which is 1/256th of the mainstream UNet model. Despite its reduced complexity, DTONet demonstrates superior performance in terms of accuracy, with an IOU improvement over other similar models. To validate the generalization capability of this model, we conducted tests on the PH2 dataset, and the results still outperformed existing models. Therefore, the proposed DTONet network exhibits excellent generalization ability and is sufficiently outstanding. Full article

(This article belongs to the Special Issue Application of Deep Learning in Medical Diagnosis)

► Show Figures

Journal Menu

Journal Browser

Application of Deep Learning in Medical Diagnosis

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (7 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI