Multimodal and Explainable AI for Biomedical Imaging and Computer-Aided Diagnosis

A Special Issue of Bioengineering (ISSN 2306-5354) belonging to the section "Biosignal Processing".

Deadline for manuscript submissions: 31 December 2026 | Viewed by 496

Editors


E-Mail Website
Guest Editor
LabISEN, ISEN Yncréa Ouest, Caen, France
Interests: medical imaging AI; multimodal learning; explainable AI; computer-aided diagnosis; biomedical image analysis; foundation models in healthcare; vision transformers; AI for clinical decision support

E-Mail Website
Guest Editor
CNRS, Centrale Marseille, Institut Fresnel UMR 7249, Aix-Marseille University, 13007 Marseille, France
Interests: biomedical signal and image processing; computer-aided diagnosis; pattern recognition; machine learning for medical applications
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Biomedical Engineering, University of Southern California, Los Angeles, CA, USA
Interests: optical imaging; machine learning; biomedicine; bioengineering; biophotonics; translational research; interdisciplinary
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The rapid emergence of foundation models, transformers, and multimodal AI systems is redefining computer-aided diagnosis and biomedical imaging. While traditional machine learning and deep learning approaches have already transformed medical image analysis, the new generation of AI systems—large language models (LLMs), vision–language models (VLMs), self-supervised learning frameworks, and multimodal transformers—is enabling more generalizable, data-efficient, and clinically adaptable diagnostic tools.

These advances open new possibilities for integrating heterogeneous medical data sources, including imaging, clinical records, signals, and text, while also raising crucial challenges related to explainability, robustness, and trust in clinical environments. This Special Issue aims to gather cutting-edge research bridging methodological AI innovations and real-world healthcare applications. We particularly welcome contributions on foundation models in medical imaging, multimodal learning, self-supervised and weakly supervised approaches, explainable and trustworthy AI, federated learning, and privacy-preserving diagnostic systems.

By highlighting emerging paradigms beyond conventional machine learning, this issue seeks to shape the next generation of AI-enabled computer-aided diagnostic technologies.

Dr. Nesma Settouti
Prof. Dr. Mouloud Adel
Dr. Daniel L. Farkas
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-anonymized 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

  • foundation models
  • transformers
  • multimodal AI
  • medical imaging
  • computer-aided diagnosis
  • biomedical image analysis
  • vision transformers
  • large language models
  • vision-language models
  • self-supervised learning
  • weakly supervised learning
  • explainable AI
  • trustworthy AI
  • federated learning
  • clinical decision support

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
Select all
Export citation of selected articles as:

Research

29 pages, 948 KB  
Article
Leakage-Free Multimodal Depression Screening: Controlled Evaluation of Text, Facial Behavior, and Prosodic Fusion
by Souaad Hamza-Cherif and Nesma Settouti
Bioengineering 2026, 13(9), 1009; https://doi.org/10.3390/bioengineering13091009 - 30 Aug 2026
Abstract
Multimodal behavioral sensing may support depression screening, but evaluation on small clinical-interview datasets is particularly vulnerable to data leakage and model-selection bias. We present a leakage-audited trimodal framework evaluated on DAIC-WOZ (n=180, PHQ-8 10), combining SBERT text [...] Read more.
Multimodal behavioral sensing may support depression screening, but evaluation on small clinical-interview datasets is particularly vulnerable to data leakage and model-selection bias. We present a leakage-audited trimodal framework evaluated on DAIC-WOZ (n=180, PHQ-8 10), combining SBERT text embeddings, OpenFace facial-behavior descriptors, and COVAREP prosodic features. Participant-level partitioning is performed before augmentation, while decision thresholds and neural-model checkpoints are selected exclusively from internal validation data. A controlled five-seed experiment showed that a deliberately leaky full-pool MixUp construction, in which a retained development sample could include a held-out participant as its second parent, was associated with a 27–33 percentage-point increase in Macro-F1 across four fusion configurations. Under the participant-level leakage-free 5-fold protocol, trimodal late fusion achieved a Macro-F1 of 0.532±0.041, compared with 0.446±0.021 for Text+Imaging late fusion. Paired participant-level correctness outcomes also favored trimodal fusion (McNemar χ2=6.618, p=0.010), consistent with improved paired classification when the audio modality was included under the leakage-free protocol. On 86 participant-disjoint E-DAIC sessions, using a consistent PHQ-8-based outcome definition (PHQ-8 10), trimodal late fusion achieved Macro-F1 = 0.621 and AUC = 0.676; this experiment is interpreted as within-family generalization rather than independent cross-corpus validation. Overall, the results show that leakage control can substantially alter both absolute performance and comparative conclusions, and that multimodal gains should be established through participant-level evaluation, modality-specific analysis, and reproducible model-selection procedures. Full article
Show Figures

Graphical abstract

Back to TopTop