Department of Medical Imaging, First Hospital of Qinhuangdao, 066000, Qinhuangdao City, Hebei Province, China.
Department of Radiology, Beijing Friendship Hospital, Capital Medical University, 100050, Beijing, China.
Abdom Radiol (NY). 2024 Apr;49(4):1275-1287. doi: 10.1007/s00261-024-04241-8. Epub 2024 Mar 4.
The aim of the study was to externally validate two AI models for the classification of prostate mpMRI sequences and segmentation of the prostate gland on T2WI.
MpMRI data from 719 patients were retrospectively collected from two hospitals, utilizing nine MR scanners from four different vendors, over the period from February 2018 to May 2022. Med3D deep learning pretrained architecture was used to perform image classification,UNet-3D was used to segment the prostate gland. The images were classified into one of nine image types by the mode. The segmentation model was validated using T2WI images. The accuracy of the segmentation was evaluated by measuring the DSC, VS,AHD.Finally,efficacy of the models was compared for different MR field strengths and sequences.
20,551 image groups were obtained from 719 MR studies. The classification model accuracy is 99%, with a kappa of 0.932. The precision, recall, and F1 values for the nine image types had statistically significant differences, respectively (all P < 0.001). The accuracy for scanners 1.436 T, 1.5 T, and 3.0 T was 87%, 86%, and 98%, respectively (P < 0.001). For segmentation model, the median DSC was 0.942 to 0.955, the median VS was 0.974 to 0.982, and the median AHD was 5.55 to 6.49 mm,respectively.These values also had statistically significant differences for the three different magnetic field strengths (all P < 0.001).
The AI models for mpMRI image classification and prostate segmentation demonstrated good performance during external validation, which could enhance efficiency in prostate volume measurement and cancer detection with mpMRI.
These models can greatly improve the work efficiency in cancer detection, measurement of prostate volume and guided biopsies.
本研究旨在对两种用于前列腺磁共振成像（mpMRI）序列分类和 T2WI 前列腺分割的人工智能（AI）模型进行外部验证。
回顾性收集了 2018 年 2 月至 2022 年 5 月期间来自两家医院的 719 名患者的 mpMRI 数据，使用了来自四个不同供应商的九台磁共振扫描仪。采用 Med3D 深度学习预训练架构进行图像分类，采用 UNet-3D 进行前列腺分割。通过模态将图像分类为九种图像类型之一。使用 T2WI 图像验证分割模型。通过测量 DSC、VS、AHD 来评估分割的准确性。最后，比较了不同磁共振场强和序列下模型的效能。
从 719 项 MRI 研究中获得了 20551 个图像组。分类模型的准确率为 99%，kappa 值为 0.932。对于九种图像类型，其精度、召回率和 F1 值均有统计学差异（均 P<0.001）。场强为 1.436 T、1.5 T 和 3.0 T 的扫描仪的准确率分别为 87%、86%和 98%（P<0.001）。对于分割模型，中位数 DSC 为 0.942 至 0.955，中位数 VS 为 0.974 至 0.982，中位数 AHD 为 5.55 至 6.49 mm，三个不同磁场强度之间的这些值也有统计学差异（均 P<0.001）。
在外部验证中，用于 mpMRI 图像分类和前列腺分割的 AI 模型表现出良好的性能，这可以提高 mpMRI 前列腺体积测量和癌症检测的效率。
这些模型可以极大地提高癌症检测、前列腺体积测量和引导活检的工作效率。
