Radiologist-in-the-Loop Self-Training for Generalizable CT Metal Artifact Reduction
This work addresses the domain gap issue in metal artifact reduction for CT imaging, which is crucial for accurate diagnosis in clinical settings, representing a novel approach but with incremental improvements over existing semi-supervised methods.
The paper tackled the problem of metal artifacts degrading CT image quality by proposing a radiologist-in-the-loop self-training framework (RISE-MAR) that integrates radiologist feedback to improve pseudo ground-truths, resulting in superior generalization performance on real clinical CT images compared to state-of-the-art methods.
Metal artifacts in computed tomography (CT) images can significantly degrade image quality and impede accurate diagnosis. Supervised metal artifact reduction (MAR) methods, trained using simulated datasets, often struggle to perform well on real clinical CT images due to a substantial domain gap. Although state-of-the-art semi-supervised methods use pseudo ground-truths generated by a prior network to mitigate this issue, their reliance on a fixed prior limits both the quality and quantity of these pseudo ground-truths, introducing confirmation bias and reducing clinical applicability. To address these limitations, we propose a novel Radiologist-In-the-loop SElf-training framework for MAR, termed RISE-MAR, which can integrate radiologists' feedback into the semi-supervised learning process, progressively improving the quality and quantity of pseudo ground-truths for enhanced generalization on real clinical CT images. For quality assurance, we introduce a clinical quality assessor model that emulates radiologist evaluations, effectively selecting high-quality pseudo ground-truths for semi-supervised training. For quantity assurance, our self-training framework iteratively generates additional high-quality pseudo ground-truths, expanding the clinical dataset and further improving model generalization. Extensive experimental results on multiple clinical datasets demonstrate the superior generalization performance of our RISE-MAR over state-of-the-art methods, advancing the development of MAR models for practical application. Code is available at https://github.com/Masaaki-75/rise-mar.