Quantitative Imaging Biomarkers in Medicine (Quibim S.L.), Aragon Avenue, 30, 13th floor, Office I-J, 46021, Valencia, Spain.
Intelligent Data Analysis Laboratory (IDAL), ETSE, Universidad de Valencia, Valencia, Spain.
Eur Radiol. 2023 Jul;33(7):5087-5096. doi: 10.1007/s00330-023-09410-9. Epub 2023 Jan 24.
Automatic MR imaging segmentation of the prostate provides relevant clinical benefits for prostate cancer evaluation such as calculation of automated PSA density and other critical imaging biomarkers. Further, automated T2-weighted image segmentation of central-transition zone (CZ-TZ), peripheral zone (PZ), and seminal vesicle (SV) can help to evaluate clinically significant cancer following the PI-RADS v2.1 guidelines. Therefore, the main objective of this work was to develop a robust and reproducible CNN-based automatic prostate multi-regional segmentation model using an intercontinental cohort of prostate MRI.
A heterogeneous database of 243 T2-weighted prostate studies from 7 countries and 10 machines of 3 different vendors, with the CZ-TZ, PZ, and SV regions manually delineated by two experienced radiologists (ground truth), was used to train (n = 123) and test (n = 120) a U-Net-based model with deep supervision using a cyclical learning rate. The performance of the model was evaluated by means of dice similarity coefficient (DSC), among others. Segmentation results with a DSC above 0.7 were considered accurate.
The proposed method obtained a DSC of 0.88 ± 0.01, 0.85 ± 0.02, 0.72 ± 0.02, and 0.72 ± 0.02 for the prostate gland, CZ-TZ, PZ, and SV respectively in the 120 studies of the test set when comparing the predicted segmentations with the ground truth. No statistically significant differences were found in the results obtained between manufacturers or continents.
Prostate multi-regional T2-weighted MR images automatic segmentation can be accurately achieved by U-Net like CNN, generalizable in a highly variable clinical environment with different equipment, acquisition configurations, and population.
• Deep learning techniques allows the accurate segmentation of the prostate in three different regions on MR T2w images. • Multi-centric database proved the generalization of the CNN model on different institutions across different continents. • CNN models can be used to aid on the diagnosis and follow-up of patients with prostate cancer.
前列腺的自动磁共振成像（MRI）分割为前列腺癌评估提供了相关的临床益处，例如自动前列腺特异性抗原密度（PSA density）和其他关键影像学生物标志物的计算。此外，基于 PI-RADS v2.1 指南，对中央转换区（CZ-TZ）、外周带（PZ）和精囊（SV）的自动 T2 加权图像分割可以帮助评估临床上有意义的癌症。因此，这项工作的主要目的是开发一种基于卷积神经网络（CNN）的、针对前列腺多区域分割的稳健且可重复的模型，该模型使用来自 7 个国家和 10 个不同制造商的 3 种不同设备的 243 例前列腺 MRI 异质数据库。
使用由两名有经验的放射科医生（金标准）手动勾画的 243 例 T2 加权前列腺研究的异质数据库，对基于 U-Net 的模型进行训练（n = 123）和测试（n = 120），该模型使用循环学习率进行深度监督。通过计算 Dice 相似系数（DSC）等指标来评估模型的性能。DSC 大于 0.7 的分割结果被认为是准确的。
当将预测的分割与金标准进行比较时，该方法在 120 例测试研究中，分别获得了前列腺、CZ-TZ、PZ 和 SV 的 DSC 为 0.88 ± 0.01、0.85 ± 0.02、0.72 ± 0.02 和 0.72 ± 0.02。在制造商或大洲之间，没有发现结果存在统计学上的显著差异。
U-Net 等 CNN 可以准确地对前列腺的 T2 加权 MR 图像进行多区域自动分割，并且可以在具有不同设备、采集配置和人群的高度变化的临床环境中具有通用性。
• 深度学习技术可以准确地对前列腺的三个不同区域进行 T2w 磁共振成像分割。• 多中心数据库证明了 CNN 模型在不同大洲的不同机构中的通用性。• CNN 模型可用于辅助前列腺癌患者的诊断和随访。
