Pseudo-Label Guided Multi-Contrast Generalization for Non-Contrast Organ-Aware Segmentation
This addresses the challenge of organ segmentation in medical imaging for clinical applications like cancer screening, offering an unsupervised approach that improves accuracy without requiring labeled data.
The paper tackles the problem of segmenting organs in non-contrast CT scans without ground-truth labels by leveraging pairwise contrast-enhanced CT context, achieving a 3.98% higher Dice for internal multi-organ segmentation and 8.00% for external aorta segmentation compared to fully supervised state-of-the-art methods.
Non-contrast computed tomography (NCCT) is commonly acquired for lung cancer screening, assessment of general abdominal pain or suspected renal stones, trauma evaluation, and many other indications. However, the absence of contrast limits distinguishing organ in-between boundaries. In this paper, we propose a novel unsupervised approach that leverages pairwise contrast-enhanced CT (CECT) context to compute non-contrast segmentation without ground-truth label. Unlike generative adversarial approaches, we compute the pairwise morphological context with CECT to provide teacher guidance instead of generating fake anatomical context. Additionally, we further augment the intensity correlations in 'organ-specific' settings and increase the sensitivity to organ-aware boundary. We validate our approach on multi-organ segmentation with paired non-contrast & contrast-enhanced CT scans using five-fold cross-validation. Full external validations are performed on an independent non-contrast cohort for aorta segmentation. Compared with current abdominal organs segmentation state-of-the-art in fully supervised setting, our proposed pipeline achieves a significantly higher Dice by 3.98% (internal multi-organ annotated), and 8.00% (external aorta annotated) for abdominal organs segmentation. The code and pretrained models are publicly available at https://github.com/MASILab/ContrastMix.