Department of Radiological Sciences, Oncology and Pathology, Sapienza University/Policlinico Umberto I, Rome, Italy.
Department of Computer, Control and Management Engineering, Sapienza University of Rome, Italy.
J Magn Reson Imaging. 2022 Feb;55(2):480-490. doi: 10.1002/jmri.27879. Epub 2021 Aug 9.
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.
To develop a convolutional neural networks (CNNs) based analysis pipeline for the classification of prostate MRI image quality.
Retrospective.
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).
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.
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.
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).
CNNs achieved high accuracy in classifying prostate MRI image quality on an individual-slice basis and almost perfect accuracy when classifying the entire sequences.
4 TECHNICAL EFFICACY: Stage 1.
前列腺磁共振成像（MRI）技术要求高，需要高质量的图像才能充分发挥其诊断潜力。一种自动识别诊断不足图像的方法可以帮助优化图像质量。
开发一种基于卷积神经网络（CNN）的前列腺 MRI 图像质量分类分析管道。
回顾性。
316 例前列腺 mpMRI 扫描和 312 名男性（中位年龄 67 岁）。
磁场强度/序列：3T；快速自旋回波 T2WI、回波平面成像 DWI、ADC、梯度回波动态对比增强（DCE）。
三位泌尿生殖系统放射科医生（V.P.、M.D.M.、S.C.）分别具有 21、12 和 5 年的经验，对 MRI 扫描进行了回顾。序列被标记为高质量（Q1）或低质量（Q0），并作为所有分析的参考标准。
将序列分为训练集、验证集和测试集（分别为 869、250 和 120 个序列）。采用 Fleiss kappa 评估读者间的一致性。在预处理和数据增强后，为每个序列的 MRI 切片训练了 28 个 CNN。在切片和序列基础上评估模型性能。采用配对 t 检验比较分类器的性能。
T2WI 序列中标记为 Q0 或 Q1 的序列数量为 38 个，标记为 Q1 的序列数量为 278 个；DWI 序列中标记为 Q0 或 Q1 的序列数量为 43 个，标记为 Q1 的序列数量为 273 个；ADC 序列中标记为 Q0 或 Q1 的序列数量为 41 个，标记为 Q1 的序列数量为 275 个；DCE 序列中标记为 Q0 或 Q1 的序列数量为 38 个，标记为 Q1 的序列数量为 253 个。T2WI 和 DCE 的读者间一致性几乎完美，DWI 和 ADC 的读者间一致性良好。在切片分析中，T2WI 的准确率为 89.95%±0.02%，DWI 的准确率为 79.83%±0.04%，ADC 的准确率为 76.64%±0.04%，DCE 的准确率为 96.62%±0.01%。在序列分析中，T2WI、DWI 和 DCE 的准确率为 100%±0.00%，ADC 的准确率为 92.31%±0.00%。三种最佳算法在每个序列上的性能均显著优于其他算法（P 值均<0.05）。
CNN 在基于单个切片的前列腺 MRI 图像质量分类方面具有很高的准确性，在对整个序列进行分类时具有近乎完美的准确性。
4 级 技术功效：1 级
