Abstract #3748

Explainable and Quantitative LI-RADS Automated Grading System for Hepatocellular Carcinoma based on Dynamic Contrast-Enhanced MRI

Xueqin Xia¹, Li Yang^2,3, Ruofan Sheng^2,3, Rencheng Zheng⁴, Weibo Chen⁵, Chengyan Wang¹, Mengsu Zeng^2,3,6, and He Wang^1,4

¹Human Phenome Institute, Fudan University, Shanghai, China, ²Department of Radiology, Zhongshan Hospital, Fudan University, Shanghai, China, ³Shanghai Institute of Medical Imaging, Shanghai, China, ⁴Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, China, ⁵Philips Healthcare, Shanghai, China, ⁶Cancer Center, Zhongshan Hospital, Fudan University, Shanghai, China

Synopsis

The judgment of the three major features of LI-RADS by radiologists is subjective and time-consuming. We proposed an explainable and quantitative algorithm based on DCE MRI to recognize the three major features and then get LI-RADS grades together with tumor diameter. The AUC is 0.96, 0.92, 0.70 in the validation set and 0.98, 0.90, 0.76 in the testing set for arterial phase hyper-enhancement (APHE), washout, and capsule. The overall accuracy of LI-RADS grades is 0.68 and 0.71 for the validation and testing set. The developed automatic LI-RADS grading system can provide explainable results for HCC diagnosis with high efficiency.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.