Automated Segmentation of Levator Ani Muscle from 3D Endovaginal Ultrasound Images.
Automated Segmentation of Levator Ani Muscle from 3D Endovaginal Ultrasound Images.
复制标题
从 3D 阴道内超声图像自动分割提肛肌。
DOI：
10.3390/bioengineering10080894
复制
发表时间：
2023-07-28
影响因子：
4.6
通讯作者：
Wei, Qi
中科院分区：
文献类型：
--
作者：
Rabbat, Nada;Qureshi, Amad;Hsu, Ko-Tsung;Asif, Zara;Chitnis, Parag;Shobeiri, Seyed Abbas;Wei, Qi
提肛肌 (LAM) 撕脱是阴道分娩的常见并发症，与多种盆底疾病有关。诊断和治疗这些病症需要对盆底进行成像并检查所获得的图像，这是一个耗时的过程，受操作者的可变性影响。在我们的研究中，我们建议使用深度学习 (DL) 自动分割 3D 阴道内超声图像 (EVUS) 中的 LAM，以提高诊断准确性和效率。从健康受试者和盆底疾病患者的 3D EVUS 数据中提取的 1000 多张图像用于自动 LAM 分割。实施了 U-Net 模型，并使用 Intersection over Union (IoU) 和 Dice 指标进行模型性能评估。该模型的平均 Dice 得分为 0.86，表现出比现有作品更好的性能。平均 IoU 为 0.76，表明 LAM 的自动分割和手动分割之间存在高度重叠。其他三个模型（包括 Attention UNet、FD-UNet 和 Dense-UNet）也应用于相同的图像，显示出类似的结果。我们的研究证明了使用 DL 分割和 U-Net 架构来自动化 LAM 分割的可行性和准确性，以减少 3D EVUS 图像手动分割所需的时间和资源。所提出的方法可能成为基于人工智能的诊断工具的重要组成部分，特别是在医疗资源获取有限的低社会经济地区。通过改善盆底疾病的管理，我们的方法可能有助于改善这些服务不足地区的患者治疗效果。
Levator ani muscle (LAM) avulsion is a common complication of vaginal childbirth and is linked to several pelvic floor disorders. Diagnosing and treating these conditions require imaging of the pelvic floor and examination of the obtained images, which is a time-consuming process subjected to operator variability. In our study, we proposed using deep learning (DL) to automate the segmentation of the LAM from 3D endovaginal ultrasound images (EVUS) to improve diagnostic accuracy and efficiency. Over one thousand images extracted from the 3D EVUS data of healthy subjects and patients with pelvic floor disorders were utilized for the automated LAM segmentation. A U-Net model was implemented, with Intersection over Union (IoU) and Dice metrics being used for model performance evaluation. The model achieved a mean Dice score of 0.86, demonstrating a better performance than existing works. The mean IoU was 0.76, indicative of a high degree of overlap between the automated and manual segmentation of the LAM. Three other models including Attention UNet, FD-UNet and Dense-UNet were also applied on the same images which showed comparable results. Our study demonstrated the feasibility and accuracy of using DL segmentation with U-Net architecture to automate LAM segmentation to reduce the time and resources required for manual segmentation of 3D EVUS images. The proposed method could become an important component in AI-based diagnostic tools, particularly in low socioeconomic regions where access to healthcare resources is limited. By improving the management of pelvic floor disorders, our approach may contribute to better patient outcomes in these underserved areas.
登录
查看更多内容
影响因子：
120.7
作者：
Nygaard, Ingrid;Barber, Matthew D.;Burgio, Kathryn L.;Kenton, Kimberly;Meikle, Susan;Schaffer, Joseph;Spino, Cathie;Whitehead, William E.;Wu, Jennifer;Brody, Debra J.
通讯作者：
Brody, Debra J.
DOI：
10.1002/uog.18927
发表时间：
2018-07
期刊：
Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology
影响因子：
--
作者：
van den Noort F;Grob ATM;Slump CH;van der Vaart CH;van Stralen M
通讯作者：
van Stralen M
影响因子：
7.1
作者：
van den Noort, F.;Manzini, C.;van der Vaart, C. H.;van Limbeek, M. A. J.;Slump, C. H.;Grob, A. T. M.
通讯作者：
Grob, A. T. M.
影响因子：
10.9
作者：
Chaitanya, Krishna;Karani, Neerav;Konukoglu, Ender
通讯作者：
Konukoglu, Ender
影响因子：
7.1
作者：
Wong, N. K. L.;Cheung, R. Y. K.;Chan, S. S. C.
通讯作者：
Chan, S. S. C.