Special Session on ICME 2023

Multimedia-based Health Computing

Scope, aims and topics

In healthcare, an immense amount of data is being generated by distributed sensors and cameras, as well as multi-modal digital health platforms that sup- port multimedia, such as audio, video, image, 3D geometry, and text. The availability of data from medical devices and digital record systems has greatly increased the potential for automated diagnosis. The past several years have witnessed an explosion of interest, and a dizzyingly fast development, in com- puter aided medical investigations using MRI, CT, X-rays, images, point clouds etc. Researchers, having reached a deeper understanding of the methods and on one hand are proposing elegant ways to better integrate machine learning with neural networks in complex problems (such as image reconstruction), and on the other hand are advancing the learning algorithms themselves. Note that medical imaging data may include 2D images, image volumes, and 3D geometric data (e.g., point cloud) etc. 

Nowadays, machine learning and deep learning has spread over almost all fields. Yet, pattern recognition, computer vision and language processing etc remain the heart of these advances when it comes to the multimedia data in in digital health, offering the big data and enabling advanced multimedia computing solutions to be developed. 

This special session focuses on various computing techniques (including mo- bile solutions and hardware solutions) for multimedia data in health. The topics of interest include (but are not limited to) the following areas: 

• Developing better deep learning based debugging methods and tools

• Intelligent medical and health systems

• Novel theories and methods of deep learning for medical imaging

• Pandemic (e.g., COVID-19) management with deep learning

• Health and medical behavior analytics with deep learning

• Dealing with the vulnerability to adversarial examples

• Medical visual question and answering

• Un-/semi-/weakly/fully supervised medical data (text, images etc)

• Graph learning on medical data (text, images etc)

• Generating diagnostic reports from medical images

• Fewer Labels in clinical informatics

• Summarization of clinical information

• Knowledge transfer and domain adaptation under various health environments

• Multimodal medical image analysis

• Medical image registration

• Organ and lesion segmentation/detection

• Image classification with MRI/CT/PET etc

• Medical image enhancement/denoising

• Learning robust medical image representation with noisy annotation

• Predicting clinical outcomes from multimodal medical data

• Anomaly detection in medical images

• Active Learning and Life-long Learning

• User/patient psychometric modeling from video, image, audio, and text

Important Dates

Regular Paper Submissions (including Special Sessions)：15-Dec-22 

Regular Paper Acceptance Notification：12-Mar-23

This will be the same as ICME 2023 “Important Dates” for conference papers.

Please submit using the guidelines in ICME 2023.

Organizers 

Xuequan Lu, Deakin University

Imran Razzak, University of New South Wales

Mingqiang Wei, Nanjing University of Aeronautics and Astronautics

Zongyuan Ge, Monash University

Liang Wan, Tianjin University