Are Pixel-Wise Metrics Reliable for Sparse-View Computed Tomography Reconstruction?

TL;DR

This paper introduces anatomy-aware evaluation metrics and a structural preservation framework called CARE to improve the assessment and quality of sparse-view CT reconstructions, focusing on anatomical completeness.

Contribution

The paper proposes novel anatomy-aware metrics and a model-agnostic framework, CARE, to enhance structural preservation in CT reconstructions beyond pixel-wise fidelity.

Findings

CARE improves structural completeness by up to 40%.

Anatomy-aware metrics better capture anatomical preservation.

Framework is compatible with various reconstruction methods.

Abstract

Widely adopted evaluation metrics for sparse-view CT reconstruction--such as Structural Similarity Index Measure and Peak Signal-to-Noise Ratio--prioritize pixel-wise fidelity but often fail to capture the completeness of critical anatomical structures, particularly small or thin regions that are easily missed. To address this limitation, we propose a suite of novel anatomy-aware evaluation metrics designed to assess structural completeness across anatomical structures, including large organs, small organs, intestines, and vessels. Building on these metrics, we introduce CARE, a Completeness-Aware Reconstruction Enhancement framework that incorporates structural penalties during training to encourage anatomical preservation of significant structures. CARE is model-agnostic and can be seamlessly integrated into analytical, implicit, and generative methods. When applied to these methods, CARE substantially improves structural completeness in CT reconstructions, achieving up to +32% improvement for large organs, +22% for small organs, +40% for intestines, and +36% for vessels.