CGI 2023 - Image Analysis and Visualization in Advanced Medical Imaging Technology

Workshop Session Introduction

Medical images such as magnetic resonance (MR), computed tomography (CT), positron emission tomography (PET) and dermoscopy are commonly used for the diagnosis of various diseases such as cancer and cardiovascular diseases. These medical images are used, for example, for disease staging, monitoring, quantification and localization of a tumor, deciding precisely where to place an implant, planning for chemotherapy, radiation, and immunotherapy, or determining the margins for surgical resection. With the improvement in imaging hardware, software, mechanics and tracers, advanced medical imaging technology is improving the way we treat diseases. For example, the total-body 3-dimensional (3D) photography that constructs a digital 3D avatar of the patient can be used to view and monitor skin lesions across the total body, over time. Compared to current widespread dermoscopy, total-body 3D photography brings new spatial and temporal capabilities, where skin lesions at different sites of the body and time can be detected simultaneously.

Interpretation of medical images is time-consuming, and there is considerable intra- and inter-clinician variability. With the massive amounts of collected imaging data, manual interpretation of them is time consuming and tedious process. There are also the issues with subjectivity, inaccurate, and poorly reproducible results, even among experienced clinicians. This is attributed to the challenges in interpreting medical images where there can be diverse visual characteristics such as variations in size, shape boundaries (e.g., ‘fuzzy’) and artifacts. In addition, the ability to visualize these medical images so as to optimally represent complex and native 3D structures, such as a tumor without occlusion by surrounding structures, brings significant advantages.

Despite the new imaging capabilities from the advanced imaging technologies, the development of image analysis and visualization algorithms has not kept pace, where the current focus of the algorithm development is still on single site and single time point. The goals of this workshop are to facilitate advancements and knowledge dissemination in algorithm development in image analysis and visualization for advanced medical imaging technologies. Only high-quality and original research contributions will be considered. The workshop aims to cover, but not be limited to, the following topics:

• Image Analysis and Reconstruction
• Imaging Visualization (Spatial and Temporal)
• Segmentation, Detection and Classification from Medical Images
• Image Analysis in Multi- and Cross-modality Medical Images
• Registration of Cross-Modality and Sequential Medical Images
• Image Feature Extraction and Content-Based Image Retrieval
• Large-scale Public Medical Imaging Analysis and Visualization Datasets