Deep learning for quality assessment of axial T2-weighted prostate MRI: a tool to reduce unnecessary rescanning

Abstract

Background: T2-weighted images are a critical component of prostate magnetic resonance imaging (MRI), and it would be useful to automatically assess image quality (IQ) on a patient-specific basis without radiologist oversight. Methods: This retrospective study comprised 1,412 axial T2-weighted prostate scans. Four experienced uroradiologists graded IQ using a 0-to-3 scale (0 = uninterpretable; 1 = marginally interpretable; 2 = adequately diagnostic; 3 = more than adequately diagnostic), binarized into nondiagnostic (IQ0 or IQ1), requiring rescanning, and diagnostic (IQ2 or IQ3), not requiring rescanning. The deep learning (DL) model was trained on 1,006 scans; 203 other scans were used for validation of multiple convolutional neural networks; the remaining 203 exams were used as a test set. 3D-DenseNet_169 was chosen among 11 models based on multiple evaluation criteria. The rescan predictions were compared to the number of rescans performed on a subset of 174 exams. Results: The model accurately predicts radiologist IQ scores (Cohen κ = 0.658), similar to the human inter-rater reliability (κ = 0.688–0.791). The model also predicts rescanning necessity similarly to radiologists: model κ = 0.537; reviewer κ = 0.577–0.703. The rescan model prediction area under the curve was 0.867. Conclusion: The DL model showed a strong ability to differentiate diagnostic from nondiagnostic axial T2-weighted prostate images, accurately mimicking expert radiologists’ IQ scores. Using the model, the clinical unnecessary rescan rate could be reduced from over 50% to less than 30%. Relevance statement: DL assessment of T2-weighted prostate MRI scans can accurately assess IQ, determining the need to repeat inadequate scans as well as avoiding repeat scans of those with adequate diagnostic quality, resulting in reduced unnecessary rescanning. Key Points: Artificial intelligence assessment of prostate MRI T2-weighted image quality can improve exam time management. The model showed over 75% accuracy in assessing prostate MRI T2-weighted image quality. Expert radiologists have a substantial agreement in evaluating prostate MRI T2-weighted image quality.