MS-IQA: A Multi-Scale Feature Fusion Network for PET/CT Image Quality Assessment

2025-06-25

AI Summary

To address the challenge of jointly modeling low-level distortions and high-level anatomical semantics in PET/CT image quality assessment (IQA), this paper proposes a multi-scale feature fusion network integrating ResNet and Swin Transformer. A novel dynamic weighted channel attention module is introduced to enable adaptive fusion of local fine-grained details and global semantic features. Furthermore, we construct PET-CT-IQA-DS—the first dedicated PET/CT IQA benchmark dataset—filling a critical gap in the field. Extensive experiments demonstrate that our method achieves state-of-the-art performance on both PET-CT-IQA-DS and the public LDCTIQAC2023 dataset, significantly outperforming existing approaches across quantitative metrics (PSNR, SSIM, LPIPS) and clinically relevant diagnostic evaluation criteria. These results validate the effectiveness of our framework in supporting clinical diagnosis-oriented IQA.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Web Mining and Content Analysis: Web data integration and cleaning

Abstract

Positron Emission Tomography / Computed Tomography (PET/CT) plays a critical role in medical imaging, combining functional and anatomical information to aid in accurate diagnosis. However, image quality degradation due to noise, compression and other factors could potentially lead to diagnostic uncertainty and increase the risk of misdiagnosis. When evaluating the quality of a PET/CT image, both low-level features like distortions and high-level features like organ anatomical structures affect the diagnostic value of the image. However, existing medical image quality assessment (IQA) methods are unable to account for both feature types simultaneously. In this work, we propose MS-IQA, a novel multi-scale feature fusion network for PET/CT IQA, which utilizes multi-scale features from various intermediate layers of ResNet and Swin Transformer, enhancing its ability of perceiving both local and global information. In addition, a multi-scale feature fusion module is also introduced to effectively combine high-level and low-level information through a dynamically weighted channel attention mechanism. Finally, to fill the blank of PET/CT IQA dataset, we construct PET-CT-IQA-DS, a dataset containing 2,700 varying-quality PET/CT images with quality scores assigned by radiologists. Experiments on our dataset and the publicly available LDCTIQAC2023 dataset demonstrate that our proposed model has achieved superior performance against existing state-of-the-art methods in various IQA metrics. This work provides an accurate and efficient IQA method for PET/CT. Our code and dataset are available at https://github.com/MS-IQA/MS-IQA/.

Problem

• Assessing PET/CT image quality degraded by noise and compression
• Fusing multi-scale features for local and global quality evaluation
• Addressing lack of PET/CT IQA datasets with labeled scores

Innovation

• Multi-scale feature fusion network for PET/CT IQA
• Dynamically weighted channel attention mechanism
• ResNet and Swin Transformer multi-scale features