Liver lesion segmentation informed by joint liver segmentation

TL;DR

This paper introduces a simple, end-to-end joint liver and lesion segmentation model for CT scans that achieves competitive results with minimal post-processing and no external data, nearly matching top methods.

Contribution

The paper presents a novel single-stage, fully convolutional network for joint liver and lesion segmentation that simplifies the process and maintains high accuracy.

Findings

Achieves competitive segmentation scores on MICCAI challenge

Nearly matches top lesion segmentation performance

Attains second highest precision for lesion detection

Abstract

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.