Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.9
3.3
Journals
Diagnostics
Special Issues
Medical Image Analysis and Machine Learning
share announcement

Medical Image Analysis and Machine Learning

A special issue of Diagnostics (ISSN 2075-4418). This special issue belongs to the section "Medical Imaging and Theranostics".

Deadline for manuscript submissions: 21 April 2026 | Viewed by 2100

Special Issue Editors

Dr. Inzamam Nasir

E-Mail Website
Guest Editor
Faculty of Informatics, Kaunas University of Technology, Kaunas, Lithuania
Interests: AI explainability; intelligent systems; data intelligence; deep learning; medical imaging
Prof. Dr. Costin Teodor Streba

E-Mail Website
Guest Editor
Department of Research Methodology, University of Medicine and Pharmacy of Craiova, 200533 Craova, Romania
Interests: artificial neural network; medical image analysis; biomedical image processing; medical image processing; biomedical image technologies; pulmonology; lung disease; gastroenterology; liver; pancreas; histology; computerized morphometry; microscopic image analysis; computer-assisted image analysis; cell image analysis
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Medical image analysis, when combined with machine learning, has transformed the landscape of diagnostic medicine by enabling more accurate, efficient, and early disease detection. Despite the growing prevalence of machine learning applications in medicine, there remains a significant gap in translating algorithmic advances into clinically viable tools that can assist healthcare professionals across various specialties. This Special Issue of Diagnostics aims to attract cutting-edge contributions that demonstrate novel methodologies, robust validation frameworks, and real-world applications of machine learning and deep learning in medical image interpretation.

Medical images—ranging from radiological scans (MRI, CT, PET) to microscopic histopathological slides and digital retinal images—contain complex patterns and hidden features that require advanced analytical tools to decode. Machine learning has shown considerable promise in automating feature extraction, enhancing diagnostic accuracy, enabling early disease detection, and predicting treatment response. However, the success of such tools is dependent on high-quality data, interpretable models, cross-domain collaborations, and rigorous benchmarking against clinical standards.

This Special Issue will explore all aspects of image-based diagnostics, including classical computer vision techniques, convolutional neural networks (CNNs), transformers, radiomics, and multimodal fusion strategies. We also welcome research focusing on longitudinal analysis, transfer learning for low-resource settings, privacy-preserving models, explainable AI (XAI), and the integration of imaging biomarkers with genomics or electronic health records. A particular emphasis will be placed on frameworks that enable reproducibility, generalizability, and ethical use of AI in healthcare.

We invite original research articles, comprehensive reviews, and relevant clinical case studies that provide deep insights into state-of-the-art machine learning techniques tailored for medical image analysis. Submissions with translational potential and interdisciplinary collaboration between clinicians, computer scientists, and bioengineers are especially encouraged.

Dr. Inzamam Nasir
Prof. Dr. Costin Teodor Streba
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 250 words) can be sent to the Editorial Office for assessment.

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. Diagnostics 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 2600 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

  • AI-enhanced clinical imaging workflows
  • deep learning for disease classification and segmentation
  • radiomics and multi-omics integration
  • federated learning and privacy-preserving analytics
  • next-generation medical image annotation techniques
  • explainable AI in diagnostic imaging
  • high-throughput screening in digital pathology
  • cross-domain adaptation and transfer learning in healthcare
  • prognostic and predictive imaging biomarkers
  • clinical decision support systems using machine learning

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.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

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

Published Papers (4 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

30 pages, 3640 KB  
Article
Modified EfficientNet-B0 Architecture Optimized with Quantum-Behaved Algorithm for Skin Cancer Lesion Assessment
by Abdul Rehman Altaf, Abdullah Altaf and Faizan Ur Rehman
Diagnostics 2025, 15(24), 3245; https://doi.org/10.3390/diagnostics15243245 - 18 Dec 2025
Viewed by 66
Abstract
Background/Objectives: Skin cancer is one of the most common diseases in the world, whose early and accurate detection can have a survival rate more than 90% while the chance of mortality is almost 80% in case of late diagnostics. Methods: A [...] Read more.
Background/Objectives: Skin cancer is one of the most common diseases in the world, whose early and accurate detection can have a survival rate more than 90% while the chance of mortality is almost 80% in case of late diagnostics. Methods: A modified EfficientNet-B0 is developed based on mobile inverted bottleneck convolution with squeeze and excitation approach. The 3 × 3 convolutional layer is used to capture low-level visual features while the core features are extracted using a sequence of Mobile Inverted Bottleneck Convolution blocks having both 3 × 3 and 5 × 5 kernels. They not only balance fine-grained extraction with broader contextual representation but also increase the network’s learning capacity while maintaining computational cost. The proposed architecture hyperparameters and extracted feature vectors of standard benchmark datasets (HAM10000, ISIC 2019 and MSLD v2.0) of dermoscopic images are optimized with the quantum-behaved particle swarm optimization algorithm (QBPSO). The merit function is formulated by the training loss given in the form of standard classification cross-entropy with label smoothing, mean fitness value (mfval), average accuracy (mAcc), mean computational time (mCT) and other standard performance indicators. Results: Comprehensive scenario-based simulations were performed using the proposed framework on a publicly available dataset and found an mAcc of 99.62% and 92.5%, mfval of 2.912 × 10−10 and 1.7921 × 10−8, mCT of 501.431 s and 752.421 s for HAM10000 and ISIC2019 datasets, respectively. The results are compared with state of the art, pre-trained existing models like EfficentNet-B4, RegNetY-320, ResNetXt-101, EfficentNetV2-M, VGG-16, Deep Lab V3 as well as reported techniques based on Mask RCCN, Deep Belief Net, Ensemble CNN, SCDNet and FixMatch-LS techniques having varying accuracies from 85% to 94.8%. The reliability of the proposed architecture and stability of QBPSO is examined through Monte Carlo simulation of 100 independent runs and their statistical soundings. Conclusions: The proposed framework reduces diagnostic errors and assists dermatologists in clinical decisions for an improved patient outcomes despite the challenges like data imbalance and interpretability. Full article
(This article belongs to the Special Issue Medical Image Analysis and Machine Learning)
►▼ Show Figures

Figure 1

18 pages, 2235 KB  
Article
3D Latent Diffusion Model for MR-Only Radiotherapy: Accurate and Consistent Synthetic CT Generation
by Mohammed A. Mahdi, Mohammed Al-Shalabi, Ehab T. Alnfrawy, Reda Elbarougy, Muhammad Usman Hadi and Rao Faizan Ali
Diagnostics 2025, 15(23), 3010; https://doi.org/10.3390/diagnostics15233010 - 26 Nov 2025
Viewed by 441
Abstract
Background: The clinical imperative to reduce patient ionizing radiation exposure during diagnosis and treatment planning necessitates robust, high-fidelity synthetic imaging solutions. Current cross-modal synthesis techniques, primarily based on GANs and deterministic CNNs, exhibit instability and critical errors in modeling high-contrast tissues, thereby [...] Read more.
Background: The clinical imperative to reduce patient ionizing radiation exposure during diagnosis and treatment planning necessitates robust, high-fidelity synthetic imaging solutions. Current cross-modal synthesis techniques, primarily based on GANs and deterministic CNNs, exhibit instability and critical errors in modeling high-contrast tissues, thereby hindering their reliability for safety-critical applications such as radiotherapy. Objectives: Our primary objective was to develop a stable, high accuracy framework for 3D Magnetic Resonance Imaging (MRI) to Computed Tomography (CT) synthesis capable of generating clinically equivalent synthetic CTs (sCTs) across multiple anatomical sites. Methods: We introduce a novel 3D Latent Diffusion Model (3DLDM) that operates in a compressed latent space, mitigating the computational burden of 3D diffusion while leveraging the stability of the denoising objective. Results: Across the Head & Neck, Thorax, and Abdomen, the 3DLDM achieved a Mean Absolute Error (MAE) of 56.44 Hounsfield Units (HU). This result demonstrates a significant 3.63% reduction in overall error compared to the strongest adversarial baseline, CycleGAN (MAE = 60.07 HU, p < 0.05), a 10.76% reduction compared to NNUNet (MAE = 67.20 HU, p < 0.01), and a 20.79% reduction compared to the transformer-based SwinUNeTr (MAE = 77.23 HU, p < 0.0001). The model also achieved the highest structural similarity (SSIM = 0.885 ± 0.031), significantly exceeding SwinUNeTr (p < 0.0001), NNUNet (p < 0.01), and Pix2Pix (p < 0.0001). Likewise, the 3D-LDM achieved the highest peak signal-to-noise ratio (PSNR = 29.73 ± 1.60 dB), with statistically significant gains over CycleGAN (p < 0.01), NNUNet (p < 0.001), and SwinUNeTr (p < 0.0001). Conclusions: This work validates a scalable, accurate approach for volumetric synthesis, positioning the 3DLDM to enable MR-only radiotherapy planning and accelerate radiation-free multi-modal imaging in the clinic. Full article
(This article belongs to the Special Issue Medical Image Analysis and Machine Learning)
►▼ Show Figures

Figure 1

15 pages, 1070 KB  
Article
Exploring the Role of CT-Based Delta-Radiomics in Unresectable Vulvar Cancer
by Abdulla Alzibdeh, Bara M. Hammadeh, Rahaf Alnajjar, Mohammad Abd Al-Raheem, Rima Mheidat, Alzahra’a Al Matairi, Mohamed Qamber, Hanan Almasri, Bayan Altalla’, Amal Al-Omari and Fawzi Abuhijla
Diagnostics 2025, 15(23), 2972; https://doi.org/10.3390/diagnostics15232972 - 23 Nov 2025
Viewed by 488
Abstract
Background/Objectives: To explore the prognostic potential of gross tumor volume (GTV)-based delta-radiomic features from CT simulation scans in patients with locally advanced unresectable vulvar cancer. Methods: A total of 21 patients (between 2019 and 2024) undergoing definitive radiotherapy were included, with baseline and [...] Read more.
Background/Objectives: To explore the prognostic potential of gross tumor volume (GTV)-based delta-radiomic features from CT simulation scans in patients with locally advanced unresectable vulvar cancer. Methods: A total of 21 patients (between 2019 and 2024) undergoing definitive radiotherapy were included, with baseline and post-phase I (after 25 fractions) CT simulation scans analyzed. Radiomic features (n = 107) were extracted from GTVs using PyRadiomics, and delta features were calculated as the relative change between scans. A multi-step selection pipeline (univariable Cox screening (p < 0.10), correlation filtering, and Lasso–Cox) was applied for each endpoint: local control (LC), regional control, distant metastasis-free survival, progression-free survival, and overall survival (OS). Model discrimination was assessed via 500-iteration bootstrapped concordance index (C-index), and calibration was plotted at 24 months. Results: Median follow-up was 50.0 months. The 2-year LC and OS rates were 56.2% and 55.9%, respectively. Final multivariable models retained a sole texture Δ feature for LC (HR = 2.62, 95% CI = 1.05–6.52, p = 0.039; C-index = 0.748) and six Δ features for OS (C-index = 0.864). No features were retained for other endpoints. For LC, increased run-length non-uniformity after phase I predicted poorer control. For OS, increased texture/shape complexity predicted worse survival, whereas increased uniformity predicted better survival. Conclusions: CT-based delta-radiomic features, particularly shape and texture metrics, may predict LC and OS in unresectable vulvar cancer. Despite the small sample size, these findings highlight the potential for delta-radiomics as a noninvasive biomarker for risk stratification. Validation in larger cohorts and exploring potential in adaptive radiotherapy are warranted. Full article
(This article belongs to the Special Issue Medical Image Analysis and Machine Learning)
►▼ Show Figures

Figure 1

26 pages, 1451 KB  
Article
Hierarchical Multi-Stage Attention and Dynamic Expert Routing for Explainable Gastrointestinal Disease Diagnosis
by Muhammad John Abbas, Hend Alshaya, Wided Bouchelligua, Nehal Hassan and Inzamam Mashood Nasir
Diagnostics 2025, 15(21), 2714; https://doi.org/10.3390/diagnostics15212714 - 27 Oct 2025
Cited by 1 | Viewed by 527
Abstract
Purpose: Gastrointestinal (GI) illness demands precise and efficient diagnostics, yet conventional approaches (e.g., endoscopy and histopathology) are time-consuming and prone to reader variability. This work presents GID-Xpert, a deep learning framework designed to improve feature learning, accuracy, and interpretability for GI disease classification. [...] Read more.
Purpose: Gastrointestinal (GI) illness demands precise and efficient diagnostics, yet conventional approaches (e.g., endoscopy and histopathology) are time-consuming and prone to reader variability. This work presents GID-Xpert, a deep learning framework designed to improve feature learning, accuracy, and interpretability for GI disease classification. Methods: GID-Xpert integrates a hierarchical, multi-stage attention-driven mixture of experts with dynamic routing. The architecture couples spatial–channel attention mechanisms with specialized expert blocks; a routing module adaptively selects expert paths to enhance representation quality and reduce redundancy. The model is trained and evaluated on three benchmark datasets—WCEBleedGen, GastroEndoNet, and the King Abdulaziz University Hospital Capsule (KAUHC) dataset. Comparative experiments against state-of-the-art baselines and ablation studies (removing attention, expert blocks, and routing) are conducted to quantify the contribution of each component. Results: GID-Xpert achieves superior performance with 100% accuracy on WCEBleedGen, 99.98% on KAUHC, and 75.32% on GastroEndoNet. Comparative evaluations show consistent improvements over contemporary models, while ablations confirm the additive benefits of spatial–channel attention, expert specialization, and dynamic routing. The design also yields reduced computational cost and improved explanation quality via attention-driven reasoning. Conclusion: By unifying attention, expert specialization, and dynamic routing, GID-Xpert delivers accurate, computationally efficient, and more interpretable GI disease classification. These findings support GID-Xpert as a credible diagnostic aid and a strong foundation for future extensions toward broader GI pathologies and clinical integration. Full article
(This article belongs to the Special Issue Medical Image Analysis and Machine Learning)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-4
Back to TopTop