K-Space-Aware Cross-Modality Score for Synthesized Neuroimage Quality Assessment

TL;DR

This paper introduces K-CROSS, a novel metric for assessing cross-modality neuroimage synthesis quality by integrating lesion localization, k-space features, and structural information, outperforming existing measures.

Contribution

The paper presents K-CROSS, a new comprehensive metric that incorporates frequency, structural, and lesion information for improved neuroimage quality assessment.

Findings

K-CROSS outperforms existing metrics in correlating with radiologist judgments.

The method effectively captures lesion, frequency, and structural features.

Extensive experiments on NIRPS dataset validate its superior performance.

Abstract

The problem of how to assess cross-modality medical image synthesis has been largely unexplored. The most used measures like PSNR and SSIM focus on analyzing the structural features but neglect the crucial lesion location and fundamental k-space speciality of medical images. To overcome this problem, we propose a new metric K-CROSS to spur progress on this challenging problem. Specifically, K-CROSS uses a pre-trained multi-modality segmentation network to predict the lesion location, together with a tumor encoder for representing features, such as texture details and brightness intensities. To further reflect the frequency-specific information from the magnetic resonance imaging principles, both k-space features and vision features are obtained and employed in our comprehensive encoders with a frequency reconstruction penalty. The structure-shared encoders are designed and constrained with a similarity loss to capture the intrinsic common structural information for both modalities. As a consequence, the features learned from lesion regions, k-space, and anatomical structures are all captured, which serve as our quality evaluators. We evaluate the performance by constructing a large-scale cross-modality neuroimaging perceptual similarity (NIRPS) dataset with 6,000 radiologist judgments. Extensive experiments demonstrate that the proposed method outperforms other metrics, especially in comparison with the radiologists on NIRPS.