基于深度学习的前列腺T2加权MRI质量评估可解释人工智能工具
这项回顾性研究纳入三个队列共1046例患者,基于3D DenseNet121架构开发AI模型评估前列腺T2加权MRI质量。测试集多分类准确率73.9%(116/157),二分类准确率84.7%(133/157);AI与参考标准的一致性κ=0.704。AI可将全序列分类标签转化为3D体素级质量热图,最关键的不可诊断质量特征为直肠前列腺间隙遮蔽(94.4%,17/18)。
要点
- AI二分类识别质量不合格扫描的敏感度达100%(18/18),特异度90.5%(95/105)。
- AI与专家参考标准一致性κ=0.704,高于三位读片医师与AI之间的一致性(κ=0.292–0.445)。
- AI视角下最重要的不可诊断质量特征为直肠前列腺间隙遮蔽(94.4%,17/18)。
核心结论
- 3D AI模型能以中等准确率评估前列腺T2W MRI质量,并将全序列分类标签转化为3D体素级质量热图供解读,可能有助于以可解释的方式可重复地识别需要重新采集的MRI序列。
研究设计与样本
- 回顾性研究,纳入三个队列共1046例患者(ProstateX n=347、院内全入组 n=602、院内富集低质量MRI n=97),扫描时间为2011年1月至2022年5月;由一位专家读片者对T2W MRI进行质量评分;按70:15:15划分训练集、验证集和测试集,确保MRI扫描仪和协议在各分区均衡分布;T2W质量AI分类模型基于3D DenseNet121架构、使用MONAI框架构建;除多分类外还进行二分类(类别0/1 vs. 2);质量评分0分为不可诊断或不可用,1分为诊断质量可接受、有一定可用性但存在质量失真,2分为最佳诊断质量和可用性;生成部分遮挡敏感性图用于解剖相关性分析;由三位体部放射科医师在60例测试子组中用加权Cohen Kappa评估可重复性。
关键影像表现/征象
- AI视角下最关键的不可诊断质量影像特征为直肠前列腺间隙遮蔽,占94.4%(17/18)。
- AI可生成3D体素级质量热图,将全序列分类标签转化为可解释的解剖定位信息。
诊断标准与关键数值
- 测试集多分类准确率为73.9%(116/157),验证集最佳多分类准确率为77.1%(121/157)。
- 测试集二分类准确率为84.7%(133/157)。
- 二分类质量失真分类中类别0的亚类敏感度为100%(18/18)。
- T2W分类中无/极少质量失真的类别2亚类特异度为90.5%(95/105)。
- AI与参考标准的一致性κ=0.704(一致性较强)。
临床应用与阅片要点
- AI模型可将T2W序列的全序列质量分类标签转化为3D体素级质量热图,供阅片时定位质量失真区域。
- AI模型以100%(18/18)的敏感度识别类别0(不可诊断或不可用)扫描,可能有助于筛选需要重新采集的序列。
- 图像质量对排除临床显著癌症有显著的下游影响。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
RATIONALE AND OBJECTIVES: Prostate MRI quality is essential in guiding prostate biopsies. However, assessment of MRI quality is subjective with variation. Quality degradation sources exert varying impacts based on the sequence under consideration, such as T2W versus DWI. As a result, employing sequence-specific techniques for quality assessment could yield more advantageous outcomes. This study aims to develop an AI tool that offers a more consistent evaluation of T2W prostate MRI quality, efficiently identifying suboptimal scans while minimizing user bias.
MATERIALS AND METHODS: This retrospective study included 1046 patients from three cohorts (ProstateX [n = 347], All-comer in-house [n = 602], enriched bad-quality MRI in-house [n = 97]) scanned between January 2011 and May 2022. An expert reader assigned T2W MRIs a quality score. A train-validation-test split of 70:15:15 was applied, ensuring equal distribution of MRI scanners and protocols across all partitions. T2W quality AI classification model was based on 3D DenseNet121 architecture using MONAI framework. In addition to multiclassification, binary classification was utilized (Classes 0/1 vs. 2). A score of 0 was given to scans considered non-diagnostic or unusable, a score of 1 was given to those with acceptable diagnostic quality with some usability but with some quality distortions present, and a score of 2 was given to those considered optimal diagnostic quality and usability. Partial occlusion sensitivity maps were generated for anatomical correlation. Three body radiologists assessed reproducibility within a subgroup of 60 test cases using weighted Cohen Kappa.
RESULTS: The best validation multiclass accuracy of 77.1% (121/157) was achieved during training. In the test dataset, multiclassification accuracy was 73.9% (116/157), whereas binary accuracy was 84.7% (133/157). Sub-class sensitivity for binary quality distortion classification for class 0 was 100% (18/18), and sub-class specificity for T2W classification of absence/minimal quality distortions for class 2 was 90.5% (95/105). All three readers showed moderate to substantial agreement with ground truth (R1-R3 κ = 0.588, κ = 0.649, κ = 0.487, respectively), moderate to substantial agreement with each other (R1-R2 κ = 0.599, R1-R3 κ = 0.612, R2-R3 κ = 0.685), fair to moderate agreement with AI (R1-R3 κ = 0.445, κ = 0.410, κ = 0.292, respectively). AI showed substantial agreement with ground truth (κ = 0.704). 3D quality heatmap evaluation revealed that the most critical non-diagnostic quality imaging features from an AI perspective related to obscuration of the rectoprostatic space (94.4%, 17/18).
CONCLUSION: The 3D AI model can assess T2W prostate MRI quality with moderate accuracy and translate whole sequence-level classification labels into 3D voxel-level quality heatmaps for interpretation. Image quality has a significant downstream impact on ruling out clinically significant cancers. AI may be able to help with reproducible identification of MRI sequences requiring re-acquisition with explainability.
引用
- Belue MJ, Law YM, Marko J, et al. Deep Learning-Based Interpretable AI for Prostate T2W MRI Quality Evaluation. Acad Radiol. 2023. PMID: 37858505. doi:10.1016/j.acra.2023.09.030
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。