MICCAI Industrial Talk: Effective Liver Disease Screening, Diagnosis and Staging using CT скачать в хорошем качестве

MICCAI Industrial Talk: Effective Liver Disease Screening, Diagnosis and Staging using CT

MICCAI Industrial Talk Series @ March 10, 2025, by Dr. Ke Yan from Alibaba DAMO Academy Speaker: Ke Yan, PhD, Staff Algorithm Expert, Alibaba DAMO Academy Abstract: The liver, being the largest solid organ in the human body, plays a pivotal role in numerous physiological processes. It is also a frequent site for tumors and chronic diseases. Early detection and precise diagnosis of liver conditions are essential for enhancing patient outcomes, with computed tomography (CT) serving as a widely utilized imaging tool. In this presentation, we will discuss our work on screening, diagnosing, and staging liver tumors and chronic diseases using CT, particularly non-contrast CT, which is both cost-effective and highly accessible. Firstly, we have developed a liver tumor screening algorithm capable of identifying various types of tumors from non-contrast CT scans. This algorithm has been implemented in several hospitals and has successfully detected malignant tumors that might initially be overlooked by radiologists. Secondly, we have constructed a comprehensive liver tumor diagnosis framework that can segment and classify 11 different types of malignant and benign tumors in contrast-enhanced CT images. Liver steatosis and fibrosis, two common chronic liver diseases, have high incidence rates. We have devised algorithms to assess the severity of these conditions using non-contrast CT, achieving superior performance compared to other clinical tools such as FibroScan. For patients with liver cirrhosis, our methods can predict the extent of esophageal varices, a significant and potentially life-threatening complication. Additionally, we can accurately delineate liver vessels and Couinaud segments, providing valuable information for disease diagnosis and prognosis. Our goal is to support clinicians in making more informed decisions, thereby improving diagnostic accuracy and efficiency, and ultimately, saving more lives. Bio: Ke Yan is a Staff Algorithm Expert in the Alibaba DAMO Academy. He obtained his PhD degree from the Department of Electronic Engineering, Tsinghua University. Then, he worked as a postdoctoral fellow in the Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, National Institute of Health, US. His research mainly focuses on medical image analysis, especially on disease screening and diagnosis in CT images using deep learning. He published the DeepLesion dataset, a large-scale and universal CT lesion dataset. He also won the RSNA Trainee Research Prize in 2018 and Tsinghua University Excellent Doctoral Dissertation Award in 2016. He has published papers and abstracts on IEEE Transactions on Medical Imaging, Radiology: Artificial Intelligence, NPJ Digital Medicine, CVPR, MICCAI, RSNA, etc., and got 4200 citations. He also holds 6 granted patents in the US and 12 in China.