Thimansson Erik, Baubeta Erik, Engman Jonatan, Bjartell Anders, Zackrisson Sophia
Lund University, Department of Translational Medicine, Diagnostic Radiology, Malmö, Sweden.
Helsingborg Hospital, Department of Radiology, Helsingborg, Sweden.
J Med Imaging (Bellingham). 2024 Jan;11(1):015002. doi: 10.1117/1.JMI.11.1.015002. Epub 2024 Feb 22.
Accurate whole-gland prostate segmentation is crucial for successful ultrasound-MRI fusion biopsy, focal cancer treatment, and radiation therapy techniques. Commercially available artificial intelligence (AI) models, using deep learning algorithms (DLAs) for prostate gland segmentation, are rapidly increasing in numbers. Typically, their performance in a true clinical context is scarcely examined or published. We used a heterogenous clinical MRI dataset in this study aiming to contribute to validation of AI-models.
We included 123 patients in this retrospective multicenter (7 hospitals), multiscanner (8 scanners, 2 vendors, 1.5T and 3T) study comparing prostate contour assessment by 2 commercially available Food and Drug Association (FDA)-cleared and CE-marked algorithms (DLA1 and DLA2) using an expert radiologist's manual contours as a reference standard (RSexp) in this clinical heterogeneous MRI dataset. No in-house training of the DLAs was performed before testing. Several methods for comparing segmentation overlap were used, the Dice similarity coefficient (DSC) being the most important.
The DSC mean and standard deviation for DLA1 versus the radiologist reference standard (RSexp) was and for DLA2 versus RSexp it was . A paired -test to compare the DSC for DLA1 and DLA2 showed no statistically significant difference ().
Two commercially available DL algorithms (FDA-cleared and CE-marked) can perform accurate whole-gland prostate segmentation on a par with expert radiologist manual planimetry on a real-world clinical dataset. Implementing AI models in the clinical routine may free up time that can be better invested in complex work tasks, adding more patient value.
准确的全腺体前列腺分割对于成功进行超声 - MRI融合活检、局部癌症治疗和放射治疗技术至关重要。使用深度学习算法（DLA）进行前列腺分割的商用人工智能（AI）模型数量正在迅速增加。通常，它们在真实临床环境中的性能很少得到检验或发表。在本研究中，我们使用了一个异质性临床MRI数据集，旨在为AI模型的验证做出贡献。
在这项回顾性多中心（7家医院）、多扫描仪（8台扫描仪，2个供应商，1.5T和3T）研究中，我们纳入了123名患者，在这个临床异质性MRI数据集中，将2种获得美国食品药品监督管理局（FDA）批准并带有CE标志的商用算法（DLA1和DLA2）对前列腺轮廓的评估与专家放射科医生的手动轮廓作为参考标准（RSexp）进行比较。在测试之前，未对DLA进行内部训练。使用了几种比较分割重叠的方法，其中最重要的是Dice相似系数（DSC）。
DLA1与放射科医生参考标准（RSexp）的DSC均值和标准差为 ，DLA2与RSexp的DSC均值和标准差为 。一项比较DLA1和DLA2的DSC的配对 -检验显示无统计学显著差异（ ）。
两种商用DL算法（获得FDA批准并带有CE标志）在真实世界的临床数据集上能够进行与专家放射科医生手动平面测量相当的准确全腺体前列腺分割。在临床常规中实施AI模型可能会节省时间，这些时间可以更好地投入到复杂的工作任务中，为患者增加更多价值。
