Modeling the Intra-class Variability for Liver Lesion Detection using a Multi-class Patch-based CNN
This work addresses the problem of liver lesion detection for radiologists, offering an incremental improvement over existing methods.
The paper tackles the challenge of automatic liver lesion detection in CT images by modeling intra-class variability within the non-lesion class using a multi-class patch-based CNN, achieving highly improved detection results that outperform the state-of-the-art fully convolutional network on a dataset of 132 livers and 498 lesions.
Automatic detection of liver lesions in CT images poses a great challenge for researchers. In this work we present a deep learning approach that models explicitly the variability within the non-lesion class, based on prior knowledge of the data, to support an automated lesion detection system. A multi-class convolutional neural network (CNN) is proposed to categorize input image patches into sub-categories of boundary and interior patches, the decisions of which are fused to reach a binary lesion vs non-lesion decision. For validation of our system, we use CT images of 132 livers and 498 lesions. Our approach shows highly improved detection results that outperform the state-of-the-art fully convolutional network. Automated computerized tools, as shown in this work, have the potential in the future to support the radiologists towards improved detection.