University of Michigan-Shanghai Jiao Tong University Joint Institute, Shanghai Jiao Tong University, Shanghai, 200240, China.
Department of Mechanical Engineering, University of Michigan, Ann Arbor, MI, 48109, USA.
Int Urogynecol J. 2021 Nov;32(11):3069-3075. doi: 10.1007/s00192-020-04626-5. Epub 2021 Jan 21.
Magnetic resonance imaging (MRI) plays an important role in assessing pelvic organ prolapse (POP), and automated pelvic floor landmark localization potentially accelerates MRI-based measurements of POP. Herein, we aimed to develop and evaluate a deep learning-based technique for automated localization of POP-related landmarks.
Ninety-six mid-sagittal stress MR images (at rest and at maximal Valsalva) were used for deep-learning model training and generalization testing. We randomly split our dataset into a training set of 73 images and a testing set of 23 images. One soft-tissue landmark (the cervical os [P1]) and three bony landmarks (the mid-pubic line [MPL] endpoints [P2&P3] and the sacrococcygeal inferior-pubic point [SCIPP] line endpoints [P3&P4]) were annotated by experts. We used an encoder-decoder structure to develop the deep learning model for automated localization of the four landmarks. Localization performance was assessed using the root square error (RSE), whereas the reference lines were assessed based on the length and orientation differences.
We localized landmarks (P1 to P4) with mean RSEs of 1.9 mm, 1.3 mm, 0.9 mm, and 3.6 mm. The mean length errors of the MPL and SCIPP line were 0.1 and -2.1 mm, and the mean orientation errors of the MPL and SCIPP line were -0.7° and -0.3°. Our method predicted each image in 0.015 s.
We demonstrated the feasibility of a deep learning-based approach for accurate and fast fully automated localization of bony and soft-tissue landmarks. This sped up the MR interpretation process for fast POP screening and treatment planning.
磁共振成像（MRI）在评估盆腔器官脱垂（POP）中起着重要作用，而自动盆底标志定位有可能加速基于 MRI 的 POP 测量。在此，我们旨在开发和评估一种基于深度学习的技术，用于自动定位与 POP 相关的标志。
使用 96 个中矢状面应激 MRI 图像（在休息和最大瓦萨尔时）进行深度学习模型的训练和泛化测试。我们将数据集随机分为训练集（73 个图像）和测试集（23 个图像）。由专家对一个软组织标志（宫颈口 [P1]）和三个骨性标志（耻骨中线 [MPL]终点 [P2&P3]和尾骨-耻骨下点 [SCIPP]线终点 [P3&P4]）进行标注。我们使用编码器-解码器结构开发用于自动定位四个标志的深度学习模型。使用根均方误差（RSE）评估定位性能，而参考线则基于长度和方向差异进行评估。
我们定位标志（P1 至 P4）的平均 RSE 分别为 1.9mm、1.3mm、0.9mm 和 3.6mm。MPL 和 SCIPP 线的平均长度误差分别为 0.1mm 和-2.1mm，MPL 和 SCIPP 线的平均方向误差分别为-0.7°和-0.3°。我们的方法每张图像预测用时 0.015s。
我们证明了基于深度学习的方法对于准确和快速全自动定位骨性和软组织标志的可行性。这加速了 POP 的快速筛查和治疗计划的 MRI 解读过程。
