ClinReadNet: A clinical reading-inspired network for low-dose abdominal CT image quality assessment

2026-06-08

AI Summary

This study addresses the challenge of assessing low-dose abdominal CT image quality under no-reference conditions in a manner consistent with radiologists’ clinical reading habits. To this end, the authors propose ClinReadNet, a novel framework that emulates the radiologist’s strategy of jointly considering local details and global context. The method innovatively integrates clinical workflow insights through three key components: a Sobel Ordinal Quality Network (SOQN), a shifted-window multi-scale temperature-scaled multi-head self-attention mechanism ((S)W-MTMSA), and a Hierarchical Ranking Probability Score (HRPS) loss function, which together model both image quality distribution and edge fidelity. Evaluated on the LDCTIQAG2023 dataset, the proposed approach achieves state-of-the-art performance with PLCC, SROCC, and KROCC scores of 0.9507, 0.9554, and 0.8629, respectively, yielding a total score of 2.7690.

Abstract

In abdominal CT imaging, developing a low-dose, no-reference image quality assessment (No-reference IQA) model that mimics doctors' reading habits for evaluating CT image quality has significant practical value. This paper proposes a novel deep learning-based framework, ClinReadNet, whose design aligns with the clinical reading logic of radiologists: first, it introduces the Sobel ordinal quality network (SOQN) module, which can simultaneously focus on edge details highly relevant to image quality and the quality distribution pattern of the entire image, accurately matching the clinical image-reading judgment habit of "considering both local details and overall context"; second, the framework integrates the (shifted) window multi-scale temperature multi-head self-attention ((S)W-MTMSA) module, which further replicates the radiologists' image-reading process of shifting from overall scanning to local focusing, and accurately locks in regions of interest through multi-sharpness attention; third, it designs the hierarchical ranked probability score (HRPS) loss function, which combines the dual logics of coarse classification and fine classification, while paying attention to the distance information between grading labels, effectively improving the performance of image quality assessment. Experiments conducted on the LDCTIQAG2023 dataset show that the proposed method achieves the current state-of-the-art (SOTA) performance: the values of Pearson's linear correlation coefficient (PLCC), Spearman's rank-order correlation coefficient (SROCC), and Kendall's rank-order correlation coefficient (KROCC) reach 0.9507, 0.9554, and 0.8629 respectively, with the sum of their absolute values (Score) being 2.7690, outperforming existing methods.

Problem

• low-dose CT
• no-reference image quality assessment
• clinical reading habit
• abdominal CT
• image quality evaluation

Innovation

• ClinReadNet
• no-reference IQA
• clinical reading-inspired
• multi-scale self-attention
• hierarchical ranked probability score