Deep Learning in Medical Image Analysis: Foundations, Techniques, and Applications

A special issue of Information (ISSN 2078-2489). This special issue belongs to the section "Artificial Intelligence".

Deadline for manuscript submissions: 30 April 2025 | Viewed by 6840

Special Issue Editor


E-Mail Website
Guest Editor
Department of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
Interests: machine intelligence; pattern recognition

Special Issue Information

Dear Colleagues,

Deep learning is a state-of-the-art machine learning approach. The success of deep learning in many pattern recognition applications has caused excitement and high expectations, and deep learning can bring revolutionary changes in health care and disease diagnosis. The goal of this Special Issue is to bring together recent advances and cutting-edge research in the use of deep learning in medical image analysis. It also aims to provide a comprehensive overview of the current state of the art and to highlight the challenges, opportunities, and future directions of this rapidly evolving field. The purpose of this Special Issue, “Deep Learning in Medical Image Analysis”, is to present and highlight novel algorithms, architectures, techniques, and applications of deep learning for medical image analysis.

Prof. Dr. Xiaoshuang Shi
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. Information 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 1600 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.

Published Papers (5 papers)

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

Research

13 pages, 5276 KiB  
Article
Edge-Guided Cell Segmentation on Small Datasets Using an Attention-Enhanced U-Net Architecture
by Yiheng Zhou, Kainan Ma, Qian Sun, Zhaoyuxuan Wang and Ming Liu
Information 2024, 15(4), 198; https://doi.org/10.3390/info15040198 - 3 Apr 2024
Viewed by 687
Abstract
Over the past several decades, deep neural networks have been extensively applied to medical image segmentation tasks, achieving significant success. However, the effectiveness of traditional deep segmentation networks is substantially limited by the small scale of medical datasets, a limitation directly stemming from [...] Read more.
Over the past several decades, deep neural networks have been extensively applied to medical image segmentation tasks, achieving significant success. However, the effectiveness of traditional deep segmentation networks is substantially limited by the small scale of medical datasets, a limitation directly stemming from current medical data acquisition capabilities. To this end, we introduce AttEUnet, a medical cell segmentation network enhanced by edge attention, based on the Attention U-Net architecture. It incorporates a detection branch enhanced with edge attention and a learnable fusion gate unit to improve segmentation accuracy and convergence speed on small medical datasets. The AttEUnet allows for the integration of various types of prior information into the backbone network according to different tasks, offering notable flexibility and generalization ability. This method was trained and validated on two public datasets, MoNuSeg and PanNuke. The results show that AttEUnet significantly improves segmentation performance on small medical datasets, especially in capturing edge details, with F1 scores of 0.859 and 0.888 and Intersection over Union (IoU) scores of 0.758 and 0.794 on the respective datasets, outperforming both convolutional neural networks (CNNs) and transformer-based baseline networks. Furthermore, the proposed method demonstrated a convergence speed over 10.6 times faster than that of the baseline networks. The edge attention branch proposed in this study can also be added as an independent module to other classic network structures and can integrate more attention priors based on the task at hand, offering considerable scalability. Full article
Show Figures

Figure 1

21 pages, 6561 KiB  
Article
Bridging the Gap: Exploring Interpretability in Deep Learning Models for Brain Tumor Detection and Diagnosis from MRI Images
by Wandile Nhlapho, Marcellin Atemkeng, Yusuf Brima and Jean-Claude Ndogmo
Information 2024, 15(4), 182; https://doi.org/10.3390/info15040182 - 27 Mar 2024
Viewed by 1138
Abstract
The advent of deep learning (DL) has revolutionized medical imaging, offering unprecedented avenues for accurate disease classification and diagnosis. DL models have shown remarkable promise for classifying brain tumors from Magnetic Resonance Imaging (MRI) scans. However, despite their impressive performance, the opaque nature [...] Read more.
The advent of deep learning (DL) has revolutionized medical imaging, offering unprecedented avenues for accurate disease classification and diagnosis. DL models have shown remarkable promise for classifying brain tumors from Magnetic Resonance Imaging (MRI) scans. However, despite their impressive performance, the opaque nature of DL models poses challenges in understanding their decision-making mechanisms, particularly crucial in medical contexts where interpretability is essential. This paper explores the intersection of medical image analysis and DL interpretability, aiming to elucidate the decision-making rationale of DL models in brain tumor classification. Leveraging ten state-of-the-art DL frameworks with transfer learning, we conducted a comprehensive evaluation encompassing both classification accuracy and interpretability. These models underwent thorough training, testing, and fine-tuning, resulting in EfficientNetB0, DenseNet121, and Xception outperforming the other models. These top-performing models were examined using adaptive path-based techniques to understand the underlying decision-making mechanisms. Grad-CAM and Grad-CAM++ highlighted critical image regions where the models identified patterns and features associated with each class of the brain tumor. The regions where the models identified patterns and features correspond visually to the regions where the tumors are located in the images. This result shows that DL models learn important features and patterns in the regions where tumors are located for decision-making. Full article
Show Figures

Figure 1

12 pages, 2897 KiB  
Article
FUSeg: The Foot Ulcer Segmentation Challenge
by Chuanbo Wang, Amirreza Mahbod, Isabella Ellinger, Adrian Galdran, Sandeep Gopalakrishnan, Jeffrey Niezgoda and Zeyun Yu
Information 2024, 15(3), 140; https://doi.org/10.3390/info15030140 - 1 Mar 2024
Cited by 1 | Viewed by 1431
Abstract
Wound care professionals provide proper diagnosis and treatment with heavy reliance on images and image documentation. Segmentation of wound boundaries in images is a key component of the care and diagnosis protocol since it is important to estimate the area of the wound [...] Read more.
Wound care professionals provide proper diagnosis and treatment with heavy reliance on images and image documentation. Segmentation of wound boundaries in images is a key component of the care and diagnosis protocol since it is important to estimate the area of the wound and provide quantitative measurement for the treatment. Unfortunately, this process is very time-consuming and requires a high level of expertise, hence the need for automatic wound measurement methods. Recently, automatic wound segmentation methods based on deep learning have shown promising performance; yet, they heavily rely on large training datasets. A few wound image datasets were published including the Diabetic Foot Ulcer Challenge dataset, the Medetec wound dataset, and WoundDB. Existing public wound image datasets suffer from small size and a lack of annotation. There is a need to build a fully annotated dataset to benchmark wound segmentation methods. To address these issues, we propose the Foot Ulcer Segmentation Challenge (FUSeg), organized in conjunction with the 2021 International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). It contains 1210 pixel-wise annotated foot ulcer images collected over 2 years from 889 patients. The submitted algorithms are reviewed in this paper and the dataset can be accessed through the Foot Ulcer Segmentation Challenge website. Full article
Show Figures

Figure 1

13 pages, 1546 KiB  
Article
Shape Matters: Detecting Vertebral Fractures Using Differentiable Point-Based Shape Decoding
by Hellena Hempe, Alexander Bigalke and Mattias Paul Heinrich
Information 2024, 15(2), 120; https://doi.org/10.3390/info15020120 - 19 Feb 2024
Viewed by 1139
Abstract
Background: Degenerative spinal pathologies are highly prevalent among the elderly population. Timely diagnosis of osteoporotic fractures and other degenerative deformities enables proactive measures to mitigate the risk of severe back pain and disability. Methods: We explore the use of shape auto-encoders for vertebrae, [...] Read more.
Background: Degenerative spinal pathologies are highly prevalent among the elderly population. Timely diagnosis of osteoporotic fractures and other degenerative deformities enables proactive measures to mitigate the risk of severe back pain and disability. Methods: We explore the use of shape auto-encoders for vertebrae, advancing the state of the art through robust automatic segmentation models trained without fracture labels and recent geometric deep learning techniques. Our shape auto-encoders are pre-trained on a large set of vertebrae surface patches. This pre-training step addresses the label scarcity problem faced when learning the shape information of vertebrae for fracture detection from image intensities directly. We further propose a novel shape decoder architecture: the point-based shape decoder. Results: Employing segmentation masks that were generated using the TotalSegmentator, our proposed method achieves an AUC of 0.901 on the VerSe19 testset. This outperforms image-based and surface-based end-to-end trained models. Our results demonstrate that pre-training the models in an unsupervised manner enhances geometric methods like PointNet and DGCNN. Conclusion: Our findings emphasize the advantages of explicitly learning shape features for diagnosing osteoporotic vertebrae fractures. This approach improves the reliability of classification results and reduces the need for annotated labels. Full article
Show Figures

Figure 1

27 pages, 4467 KiB  
Article
Temporal Development GAN (TD-GAN): Crafting More Accurate Image Sequences of Biological Development
by Pedro Celard, Adrián Seara Vieira, José Manuel Sorribes-Fdez, Eva Lorenzo Iglesias and Lourdes Borrajo
Information 2024, 15(1), 12; https://doi.org/10.3390/info15010012 - 24 Dec 2023
Viewed by 1426
Abstract
In this study, we propose a novel Temporal Development Generative Adversarial Network (TD-GAN) for the generation and analysis of videos, with a particular focus on biological and medical applications. Inspired by Progressive Growing GAN (PG-GAN) and Temporal GAN (T-GAN), our approach employs multiple [...] Read more.
In this study, we propose a novel Temporal Development Generative Adversarial Network (TD-GAN) for the generation and analysis of videos, with a particular focus on biological and medical applications. Inspired by Progressive Growing GAN (PG-GAN) and Temporal GAN (T-GAN), our approach employs multiple discriminators to analyze generated videos at different resolutions and approaches. A new Temporal Discriminator (TD) that evaluates the developmental coherence of video content is introduced, ensuring that the generated image sequences follow a realistic order of stages. The proposed TD-GAN is evaluated on three datasets: Mold, Yeast, and Embryo, each with unique characteristics. Multiple evaluation metrics are used to comprehensively assess the generated videos, including the Fréchet Inception Distance (FID), Frechet Video Distance (FVD), class accuracy, order accuracy, and Mean Squared Error (MSE). Results indicate that TD-GAN significantly improves FVD scores, demonstrating its effectiveness in generating more coherent videos. It achieves competitive FID scores, particularly when selecting the appropriate number of classes for each dataset and resolution. Additionally, TD-GAN enhances class accuracy, order accuracy, and reduces MSE compared to the default model, demonstrating its ability to generate more realistic and coherent video sequences. Furthermore, our analysis of stage distribution in the generated videos shows that TD-GAN produces videos that closely match the real datasets, offering promising potential for generating and analyzing videos in different domains, including biology and medicine. Full article
Show Figures

Figure 1

Planned Papers

The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.

Title: A predictive analytics framework for infant mortality rate estimation using a smart healthcare system
Authors: Ali Fida; Muhammad Usman; Tazeen Athar; Alvis Fong
Affiliation: Western Michigan University, Kalamazoo, United States
Abstract: Accurate and timely prediction of vaccine-preventable diseases is always a significant public health matter to reduce child mortality. Pakistan has nationwide different programs for timely treatment of vaccine-preventable diseases, but unluckily, coverage is quite low in spite of the accessibility of free vaccination, and it influences the infant mortality rate (IMR). It’s crucial for decision-makers to design effective strategies timely for a reduction in IMR rate. In terms of prediction model building, the healthcare program datasets have never been integrated in the past to know the variables influencing IMR across various healthcare programs. Most statistical-based methods are implemented in different fields of life but without augmentation of basic domain knowledge, cause tendency, and yield erroneous results. In order to address the aforementioned limitations, an automated and accurate prediction methodology has been proposed in this work, which effectively overcomes the said limitations. The proposed methodology has been validated through an integrated approach by applying different machine learning algorithms. Experimental results have been conducted IMR on datasets taken from Sindh healthcare programs, and supremacy of the proposed methodology has been observed by accurate prediction. Furthermore, comparative analysis based on five regression algorithms shows that fine-tuned Random Forest-based Regressor is performing well compared to other regression algorithms.

Back to TopTop