Deep learning-driven multi-view multi-task image quality assessment method for chest CT image.

Background: Chest computed tomography (CT) image quality impacts radiologists' diagnoses. Pre-diagnostic image quality assessment is essential but labor-intensive and may have human limitations (fatigue, perceptual biases, and cognitive biases). This study aims to develop and validate a deep learning (DL)-driven multi-view multi-task image quality assessment (M[Formula: see text]IQA) method for assessing the quality of chest CT images in patients, to determine if they are suitable for assessing the patient's physical condition.

Methods: This retrospective study utilizes and analyzes chest CT images from 327 patients. Among them, 1613 images from 286 patients are used for model training and validation, while the remaining 41 patients are reserved as an additional test set for conducting ablation studies, comparative studies, and observer studies. The M[Formula: see text]IQA method is driven by DL technology and employs a multi-view fusion strategy, which incorporates three scanning planes (coronal, axial, and sagittal). It assesses image quality for multiple tasks, including inspiration evaluation, position evaluation, radiation protection evaluation, and artifact evaluation. Four algorithms (pixel threshold, neural statistics, region measurement, and distance measurement) have been proposed, each tailored for specific evaluation tasks, with the aim of optimizing the evaluation performance of the M[Formula: see text]IQA method.

Results: In the additional test set, the M[Formula: see text]IQA method achieved 87% precision, 93% sensitivity, 69% specificity, and a 0.90 F1-score. Extensive ablation and comparative studies have demonstrated the effectiveness of the proposed algorithms and the generalization performance of the proposed method across various assessment tasks.

Conclusion: This study develops and validates a DL-driven M[Formula: see text]IQA method, complemented by four proposed algorithms. It holds great promise in automating the assessment of chest CT image quality. The performance of this method, as well as the effectiveness of the four algorithms, is demonstrated on an additional test set.