Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.2
3.0
Journals
JCM
Special Issues
Artificial Intelligence and Deep Learning in Medical Imaging
jcm-logo
Submit to Special Issue Submit Abstract to Special Issue Review for JCM Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Artificial Intelligence and Deep Learning in Medical Imaging

A special issue of Journal of Clinical Medicine (ISSN 2077-0383). This special issue belongs to the section "Nuclear Medicine & Radiology".

Deadline for manuscript submissions: 30 October 2025 | Viewed by 243

Special Issue Editors

Dr. Eros Montin

E-Mail Website
Guest Editor
1. Department of Radiology, Bernard and Irene Schwartz Center for Biomedical Imaging, New York, NY USA
2. Department of Radiology, Center for Advanced Imaging Innovation and Research (CAI2R), New York, NY, USA
Interests: magnetic resonance imaging; radiomics; artificial intelligence (AI); deep learning; clinical and translational medicine
Dr. Giuseppe Carluccio

E-Mail Website
Guest Editor
Department of Electrical Engineering and Information Technology, University Federico II of Napoli, Napoli, Italy
Interests: basic research; deep learning; SAR; safety analysis; MRI

Special Issue Information

Dear Colleagues,

Artificial Intelligence (AI) and Deep Learning (DL) are redefining medical imaging by providing unprecedented opportunities to improve diagnosis, prognosis, treatment planning, and patient safety. From advanced image segmentation and radiomics to explainable AI and privacy-preserving models, these technologies are addressing long-standing challenges in clinical imaging. However, critical issues such as reproducibility, algorithmic bias, and the safe implementation of AI in clinical workflows remain to be solved.

This Special Issue aims to focus on the latest advancements in AI and DL for medical imaging, emphasizing not only precision and efficiency but also safety and ethical deployment. Submissions are welcome to explore topics such as multi-modal data integration, robust feature extraction, federated learning, clinical validation, and methods ensuring regulatory compliance. Studies that investigate strategies for mitigating risks and improving interpretability to enhance patient safety are especially welcome to be submitted.

We invite authors to submit their original research articles and reviews on the abovementioned themes. This Special Issue aims to mobilize interdisciplinary collaboration and drive innovation in safe and effective AI applications for medical imaging.

Dr. Eros Montin
Dr. Giuseppe Carluccio
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. Journal of Clinical Medicine 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

  • magnetic resonance imaging
  • radiomics
  • artificial intelligence (AI)
  • deep learning
  • clinical and translational medicine
  • MRI safety
  • radiogenomics
  • multiomics

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 (1 paper)

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

Research

22 pages, 5432 KiB  
Article
Radiomics for Precision Diagnosis of FAI: How Close Are We to Clinical Translation? A Multi-Center Validation of a Single-Center Trained Model
by Eros Montin, Srikar Namireddy, Hariharan Subbiah Ponniah, Kartik Logishetty, Iman Khodarahmi, Sion Glyn-Jones and Riccardo Lattanzi
J. Clin. Med. 2025, 14(12), 4042; https://doi.org/10.3390/jcm14124042 (registering DOI) - 7 Jun 2025
Abstract
Background: Femoroacetabular impingement (FAI) is a complex hip disorder characterized by abnormal contact between the femoral head and acetabulum, often leading to joint damage, chronic pain, and early-onset osteoarthritis. Despite MRI being the imaging modality of choice, diagnosis remains challenging due to subjective [...] Read more.
Background: Femoroacetabular impingement (FAI) is a complex hip disorder characterized by abnormal contact between the femoral head and acetabulum, often leading to joint damage, chronic pain, and early-onset osteoarthritis. Despite MRI being the imaging modality of choice, diagnosis remains challenging due to subjective interpretation, lack of standardized imaging criteria, and difficulty differentiating symptomatic from asymptomatic cases. This study aimed to develop and externally validate radiomics-based machine learning (ML) models capable of classifying healthy, asymptomatic, and symptomatic FAI cases with high diagnostic accuracy and generalizability. Methods: A total of 82 hip MRI datasets (31 symptomatic, 31 asymptomatic, 20 healthy) from a single center were used for training and cross-validation. Radiomic features were extracted from four segmented anatomical regions (femur, acetabulum, gluteus medius, gluteus maximus). A four-step feature selection pipeline was implemented, followed by training 16 ML classifiers. External validation was conducted on a separate multi-center cohort of 185 symptomatic FAI cases acquired with heterogeneous MRI protocols. Results: The best-performing models achieved a cross-validation accuracy of up to 90.9% in distinguishing among healthy, asymptomatic, and symptomatic hips. External validation on the independent multi-center cohort demonstrated 100% accuracy in identifying symptomatic FAI cases. Since this metric reflects performance on symptomatic cases only, it should be interpreted as a detection rate (true positive rate) rather than overall multi-class accuracy. Gini index-based feature selection consistently outperformed F-statistic-based methods across all the models. Conclusions: This is the first study to systematically integrate radiomics and multiple ML models for FAI classification for these three phenotypes, trained on a single-center dataset and externally validated on multi-institutional MRI data. The demonstrated robustness and generalizability of radiomic features support their use in clinical workflows and future large-scale studies targeting standardized, data-driven FAI diagnosis. Full article
(This article belongs to the Special Issue Artificial Intelligence and Deep Learning in Medical Imaging)
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-1
Back to TopTop