Convolutional Neural Networks for Automated Classification of Prostate Multiparametric Magnetic Resonance Imaging Based on Image Quality

Abstract

Background Prostate magnetic resonance imaging (MRI) is technically demanding, requiring high image quality to reach its full diagnostic potential. An automated method to identify diagnostically inadequate images could help optimize image quality. Purpose To develop a convolutional neural networks (CNNs) based analysis pipeline for the classification of prostate MRI image quality. Study Type Retrospective. Subjects Three hundred sixteen prostate mpMRI scans and 312 men (median age 67). Field Strength/Sequence A 3 T; fast spin echo T2WI, echo planar imaging DWI, ADC, gradient‐echo dynamic contrast enhanced (DCE). Assessment MRI scans were reviewed by three genitourinary radiologists (V.P., M.D.M., S.C.) with 21, 12, and 5 years of experience, respectively. Sequences were labeled as high quality (Q1) or low quality (Q0) and used as the reference standard for all analyses. Statistical Tests Sequences were split into training, validation, and testing sets (869, 250, and 120 sequences, respectively). Inter‐reader agreement was assessed with the Fleiss kappa. Following preprocessing and data augmentation, 28 CNNs were trained on MRI slices for each sequence. Model performance was assessed on both a per‐slice and a per‐sequence basis. A pairwise t ‐test was performed to compare performances of the classifiers. Results The number of sequences labeled as Q0 or Q1 was 38 vs. 278 for T2WI, 43 vs. 273 for DWI, 41 vs. 275 for ADC, and 38 vs. 253 for DCE. Inter‐reader agreement was almost perfect for T2WI and DCE and substantial for DWI and ADC. On the per‐slice analysis, accuracy was 89.95% ± 0.02% for T2WI, 79.83% ± 0.04% for DWI, 76.64% ± 0.04% for ADC, 96.62% ± 0.01% for DCE. On the per‐sequence analysis, accuracy was 100% ± 0.00% for T2WI, DWI, and DCE, and 92.31% ± 0.00% for ADC. The three best algorithms performed significantly better than the remaining ones on every sequence ( P ‐value < 0.05). Data Conclusion CNNs achieved high accuracy in classifying prostate MRI image quality on an individual‐slice basis and almost perfect accuracy when classifying the entire sequences. Evidence Level 4 Technical Efficacy Stage 1

Multi-class classification of prostate cancer MRIS based on UCLA score using deep transfer learning models

“…Image quality could be improved through the use of the automated approach for identifying diagnostically poor images, for example. A CNN-based analysis pipeline to classify the prostate MRI images quality was developed in [13]. This model exhibited great accuracy in prostate MRI classification of image quality on the individual-slice basis and nearly flawless accuracy in classifying whole sequences when applied to the entire dataset.…”

Quality checkpoints in the MRI-directed prostate cancer diagnostic pathway

“…Future iterations of PI-QUAL criteria are likely to include elements of lesion detection and quantification of the effect of PI-QUAL scores in clinical practice; the revision of PI-QUAL scores might create the basis of future QC processes to assess image quality 87,88 . AI might have a role to support the process of image quality assessment; results from a feasibility study showed that CNNs could be used to provide a binary classification of prostate MR images as high-quality or low-quality on an individual-slice basis with high accuracy (79.8-96.6%) and at a sequence level with almost perfect accuracy (92.3-100%) 89 . Automation of this process and calibration to PI-QUAL scoring would make central review of image quality a realistic goal and could be used at a centre level to identify poor image quality on a cases-by-case basis, to indicate whether repeating sequences is necessary.…”

Editorial on “Convolutional Neural Networks for Automated Classification of Prostate Multiparametric Magnetic Resonance Imaging Based on Image Quality”

“…Yet, the study of Cipollari et al 4 has some limitations. The model uses a binary classification to assess image quality, but a wider scale could be more valuable.…”

“…Several articles have recently discussed the quality standards that should be applied to mpMRI examinations 2,3 . In this issue of JMRI , Cipollari et al 4 bring attention to a new approach to the topic.…”