Co-Heterogeneous and Adaptive Segmentation from Multi-Source and Multi-Phase CT Imaging Data: A Study on Pathological Liver and Lesion Segmentation

TL;DR

This paper introduces CHASe, a novel segmentation method that adapts from limited labeled data to diverse unlabeled multi-phase CT scans, significantly improving liver and lesion segmentation accuracy across various clinical scenarios.

Contribution

The study presents a versatile framework combining semi-supervision, adversarial domain adaptation, and pseudo-labeling, along with a new co-heterogeneous training approach for improved multi-phase CT segmentation.

Findings

CHASe outperforms state-of-the-art methods in liver lesion segmentation.

Achieves up to 9.4% improvement in Dice scores across phases.

Effectively adapts from limited labeled data to diverse clinical scenarios.

Abstract

In medical imaging, organ/pathology segmentation models trained on current publicly available and fully-annotated datasets usually do not well-represent the heterogeneous modalities, phases, pathologies, and clinical scenarios encountered in real environments. On the other hand, there are tremendous amounts of unlabelled patient imaging scans stored by many modern clinical centers. In this work, we present a novel segmentation strategy, co-heterogenous and adaptive segmentation (CHASe), which only requires a small labeled cohort of single phase imaging data to adapt to any unlabeled cohort of heterogenous multi-phase data with possibly new clinical scenarios and pathologies. To do this, we propose a versatile framework that fuses appearance based semi-supervision, mask based adversarial domain adaptation, and pseudo-labeling. We also introduce co-heterogeneous training, which is a novel integration of co-training and hetero modality learning. We have evaluated CHASe using a clinically comprehensive and challenging dataset of multi-phase computed tomography (CT) imaging studies (1147 patients and 4577 3D volumes). Compared to previous state-of-the-art baselines, CHASe can further improve pathological liver mask Dice-Sorensen coefficients by ranges of $4.2\% \sim 9.4\%$, depending on the phase combinations: e.g., from $84.6\%$ to $94.0\%$ on non-contrast CTs.