Phase Collaborative Network for Two-Phase Medical Image Segmentation

TL;DR

This paper introduces a novel end-to-end framework called Phase Collaborative Network (PCN) for organ segmentation in two-phase CT scans, effectively leveraging complementary information from different phases despite domain gaps and label inconsistencies.

Contribution

The paper proposes PCN, a joint generative-discriminative model that captures phase-to-phase and data-to-label relations, improving two-phase medical image segmentation performance.

Findings

PCN outperforms single-phase baselines significantly.

PCN effectively models inter-phase collaboration.

PCN generalizes well to public single-phase datasets.

Abstract

In real-world practice, medical images acquired in different phases possess complementary information, {\em e.g.}, radiologists often refer to both arterial and venous scans in order to make the diagnosis. However, in medical image analysis, fusing prediction from two phases is often difficult, because (i) there is a domain gap between two phases, and (ii) the semantic labels are not pixel-wise corresponded even for images scanned from the same patient. This paper studies organ segmentation in two-phase CT scans. We propose Phase Collaborative Network (PCN), an end-to-end framework that contains both generative and discriminative modules. PCN can be mathematically explained to formulate phase-to-phase and data-to-label relations jointly. Experiments are performed on a two-phase CT dataset, on which PCN outperforms the baselines working with one-phase data by a large margin, and we empirically verify that the gain comes from inter-phase collaboration. Besides, PCN transfers well to two public single-phase datasets, demonstrating its potential applications.