Multi-phase liver lesions classification using relevant visual words based on mutual information

Idit Diamant, Jacob Goldberger, Eyal Klang, Michal Amitai, Hayit Greenspan
2015 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI)  
We present a novel method for automated diagnosis of liver lesions in multi-phase CT images. Our approach is a variant of the Bag-of-Visual-Words (BoVW) method. It improves the BoVW model by selecting the most relevant words to be used for the input representation using a mutual information based criterion. Additionally, we generate relevance maps to visualize and localize the decision of the automatic classification algorithm. We validated our algorithm on 85 multi-phase CT images of 4
more » ... es: hemangiomas, Focal Nodular Hyperplasia (FNH), Hepatic Cellular Carcinoma (HCC) and cholangiocarcinoma. The new algorithm suggested in this paper improves the classical BoVW method sensitivity by 16% and specificity by 3%. The shift from single-phase liver data to a multi-phase representation is shown to substantially improve classification results. Overall, the system presented reaches state-of-the-art classification results of 80% sensitivity and 92% specificity on the 4 category lesion data, a challenging clinical diagnosis task.
doi:10.1109/isbi.2015.7163898 dblp:conf/isbi/DiamantGKAG15 fatcat:2nv4pt7d6bdapimbc4l3v4u6fa