Nowadays, disease diagnosis mainly depends on the clinical experience of doctors,combined with various examination reports and diagnostic data of patients for comprehensive judgment. However, different doctors have different clinical thinking, and thus there are often some deviations in the diagnostic results. With the development of modern medicine, the use of information technology, such as machine learning and artificial intelligence, for auxiliary diagnosis is gradually becoming an important part of the research in the field of medicine and informatics. Although it can improve the accuracy of the results of different detection methods to a certain extent, most of the existing studies only consider the single modality of case data for disease feature analysis, extraction and fusion. However, the clinical diagnosis of disease is a complex process, it is difficult for doctors to give accurate judgments according to the one modality result. Therefore, it is necessary to comprehensively analyze the patient's signs, symptoms, medical test results and other multimodal information together by new artificial intelligence based multimodal medical diagnosis (MMD) methods.
This Workshop seeks the high-quality papers from academics and industry-related researchers of machine learning and artificial intelligence, to present the most recently advanced methods and applications for realizing promising multimodal medical diagnosis.
Proposed submissions should be original, unpublished, and novel for in-depth research. Topics include but not limited to:
• Artificial Intelligence Theory and Methods for MMD
• Multimodal Analysis for Medical Data
• Domain Adaption and Transfer Learning for MMD
• Machine Learning and Reinforcement Learning for MMD
• Knowledge Graphs for MMD
• Natural Language Processing for MMD
• Cross-modal Index for MMD
• Small Sample Learning for MMD
• Uncertainty Data Analysis for MMD
• Data Reliability Analysis for MMD
• Other Medical Methods, Datasets and Applications
Nov. 2, 2025: Due date for full workshop papers submission
Nov. 10, 2025: Notification of paper acceptance to authors
Nov. 21, 2025: Camera-ready of accepted papers
Dec. 15-18, 2025: Workshops
Liang Zhao (liangzhao@dlut.edu.cn), School of Software Technology, Dalian University of Technology, Dalian, China
Zhuo Liu (lzhuo0310@126.com), The First Affiliated Hospital of Dalian Medical University, Dalian, China
Zhao Jingyuan (zhaojingyuan3344@sina.cn), The First Affiliated Hospital of Dalian Medical University, Dalian, China
Hong Yuan (yuanhonglab@163.com), The Affiliated Central Hospital of Dalian University of Technology, Dalian, China
Boxiang Dong (dongb@montclair.edu), Montclair State University, New Jersey, USA
Liang Zou (liangzou@cumt.edu.cn), China University of Mining and Technology, Xuzhou, China
Yi Yang (yiyang@buaa.edu.cn), Beihang University, Beijing, China
Workshop Chairs: Liang Zhao and Zhuo Liu Time: 15th Dec.; Location: Hong Kong II(Wanda Reign Wuhan, 2F)
Time: 8:30-8:50
Title: From Pixels to Pathways: AI-based Approaches for Multimodal Lung Cancer Classification
Presenter/Author: Sofia Gonçalves, Joana Vale Sousa, Margarida Gonçalves, Maria Amaro, Hélder P. Oliveira, and Tania Pereira
Time: 8:50-9:10
Title: Risk Prediction for Ischemic Stroke Associate Pneumonia Based on Ensemble Learning
Presenter/Author: Lin Yao, Huanqi Tu, Guowei Wu, and Yi Liu
Time: 9:10-9:30
Title: Predicting Phenotype-Gene Relationship Using Heterogeneous Graph Attention Network
Presenter/Author: Qianhui Zhang and Qingchen Zhang
Time: 9:30-9:50
Title: MatFuseU-Net: Enhancing Lesion Segmentation with Matrix Factorization-Based U-Net Architecture
Presenter/Author: Zishuo Zhang, Xiujuan Xu, Yu Liu, and Xiaowei Zhao
Time: 9:50-10:10
Title: A Multi-modal Framework for Major Depressive Disorder Prediction Integrating Variant-Based Genomics, Wearables, and Clinical Data
Presenter/Author: Taeyeong Lee, SoonHo Ha, KyungMin Kang, Juwan Kim, Min Jhon, and Hwamin Lee
Time: 10:10-10:30 Coffee Break
Time: 10:30-10:50
Title: CMGNN: Cross-Modal Emotion Recognition via EEG-Face Alignment and Expert-Guided Fusion
Presenter/Author: Ruijie He, Xin Wen, Yanrong Hao, Mengni Zhou, and Rui Cao
Time: 10:50-11:10
Title: DQU-CLIP: Enhanced Multimodal for COVID-19 ICU Patients Survival Prediction using CXR and Clinical Data
Presenter/Author: Intakhab Alam Qadri, Zhang Jin, Victor C.M. Leung, Syeda Shamaila Zareen, and Jianqiang Li
Time: 11:10:11:30
Title: Recurrent Visual Feature Extraction and Stereo Attentions for CT Report Generation
Presenter/Author: Yuanhe Tian, Lei Mao, and Yan Song
Time: 11:30-11:50
Title: PAVNet: A Personality-Aware Audio-Visual Fusion Network for Depression Detection
Presenter/Author: Shu Liu, Yilin Huang, and Xiuhong Yuan
Closing Remarks
*For the papers that not in-person presented, please upload the video to the conference system. We will help present it.
©2025 AIBMMD