AG-CRC: Anatomy-Guided Colorectal Cancer Segmentation in CT with Imperfect Anatomical Knowledge

TL;DR

This paper introduces AG-CRC, a novel anatomy-guided framework that leverages imperfect organ masks from CT scans to improve colorectal cancer segmentation, achieving significant performance gains over existing methods.

Contribution

The study proposes a new anatomy-guided segmentation framework utilizing auto-generated organ masks, a robust sampling strategy, self-supervised learning, and masked loss to enhance CRC segmentation accuracy.

Findings

Achieved 5-9% improvement in Dice score over state-of-the-art models.

Demonstrated the effectiveness of anatomy-guided training and self-supervised schemes.

Validated on two CRC datasets with extensive ablation studies.

Abstract

When delineating lesions from medical images, a human expert can always keep in mind the anatomical structure behind the voxels. However, although high-quality (though not perfect) anatomical information can be retrieved from computed tomography (CT) scans with modern deep learning algorithms, it is still an open problem how these automatically generated organ masks can assist in addressing challenging lesion segmentation tasks, such as the segmentation of colorectal cancer (CRC). In this paper, we develop a novel Anatomy-Guided segmentation framework to exploit the auto-generated organ masks to aid CRC segmentation from CT, namely AG-CRC. First, we obtain multi-organ segmentation (MOS) masks with existing MOS models (e.g., TotalSegmentor) and further derive a more robust organ of interest (OOI) mask that may cover most of the colon-rectum and CRC voxels. Then, we propose an anatomy-guided training patch sampling strategy by optimizing a heuristic gain function that considers both the proximity of important regions (e.g., the tumor or organs of interest) and sample diversity. Third, we design a novel self-supervised learning scheme inspired by the topology of tubular organs like the colon to boost the model performance further. Finally, we employ a masked loss scheme to guide the model to focus solely on the essential learning region. We extensively evaluate the proposed method on two CRC segmentation datasets, where substantial performance improvement (5% to 9% in Dice) is achieved over current state-of-the-art medical image segmentation models, and the ablation studies further evidence the efficacy of every proposed component.