Liver lesion segmentation informed by joint liver segmentation

• Published in: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) pp. 1332 - 1335
• Main Authors: Vorontsov, Eugene, Tang, An, Pal, Chris, Kadoury, Samuel
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-04-2018
• Subjects: Computed tomography; Convolution; fully convolutional network; Image segmentation; lesion; Lesions; Liver; Measurement; segmentation
• ISSN: 1945-8452
• DOI: 10.1109/ISBI.2018.8363817

We propose a model for the joint segmentation of the liver and liver lesions in computed tomography (CT) volumes. We build the model from two fully convolutional networks, connected in tandem and trained together end-to-end. We evaluate our approach on the 2017 MICCAI Liver Tumour Segmentation Challenge, attaining competitive liver and liver lesion detection and segmentation scores across a wide range of metrics. Unlike other top performing methods, our model output post-processing is trivial, we do not use data external to the challenge, and we propose a simple single-stage model that is trained end-to-end. However, our method nearly matches the top lesion segmentation performance and achieves the second highest precision for lesion detection while maintaining high recall.