Infertility Center, Iryouhoujin Kouseikai Mihara Hospital. 6-8 Kamikatsura Miyanogo-cho, Nishikyo-ku, Kyoto 615-8227, Japan; Iryouhoujin Kouseikai Katsura-ekimae Mihara Clinic. 103 Katsura OS Plaza Building, 133 Katsura Minamitatsumi-cho, Nishikyo-ku, Kyoto 615-8074, Japan.
Department of Obstetrics and Gynecology, Otsu City Hospital. 2-9-9 Motomiya, Otsu 520-0804, Japan.
Eur J Obstet Gynecol Reprod Biol. 2024 Jun;297:249-253. doi: 10.1016/j.ejogrb.2024.04.026. Epub 2024 Apr 21.
OBJECTIVE(S): Chronic endometritis (CE) is a localized mucosal inflammatory disorder associated with female infertility of unknown etiology, endometriosis, tubal factors, repeated implantation failure, and recurrent pregnancy loss, along with atypical uterine bleeding and iron deficiency anemia. Diagnosis of CE has traditionally relied on endometrial biopsy and detection of CD138(+) endometrial stromal plasmacytes. To develop a less invasive diagnostic system for CE, we aimed to construct a deep learning-based convolutional neural network (CNN) model for the automatic detection of endometrial micropolyps (EMiP), a fluid hysteroscopy (F-HSC) finding recognized as tiny protrusive lesions that are closely related to this disease.
This is an in silico study using archival images of F-HSC performed at an infertility center in a private clinic. A total of 244 infertile women undergoing F-HSC on the days 6-12 of the menstrual cycle between April 2019 and December 2021 with histopathologically-confirmed CE with the aid of immunohistochemistry for CD138 were utilized.
The archival F-HSC images of 208 women (78 with EMiP and 130 without EMiP) who met the inclusion criteria were finally subjected to analysis. Following preprocessing of the images, half a set was input into a CNN architecture for training, whereas the remaining images were utilized as the test set to evaluate the performance of the model, which was compared with that of the experienced gynecologists. The sensitivity, specificity, accuracy, precision, and F1-score of the CNN model-aided diagnosis were 93.6 %, 92.3 %, 92.8 %, 88.0 %, and 0.907, respectively. The area under the receiver operating characteristic curves of the CNN model-aided diagnosis (0.930) was at a similar level (p > .05) to the value of conventional diagnosis by three experienced gynecologists (0.927, 0.948, and 0.906).
These findings indicate that our deep learning-based CNN is capable of recognizing EMiP in F-HSC images and holds promise for further development of the computer-aided diagnostic system for CE.
慢性子宫内膜炎（CE）是一种局部黏膜炎症性疾病，与女性不明原因不孕、子宫内膜异位症、输卵管因素、反复着床失败和反复妊娠丢失有关，同时伴有非典型子宫出血和缺铁性贫血。CE 的诊断传统上依赖于子宫内膜活检和检测 CD138(+)子宫内膜基质浆细胞。为了开发一种用于 CE 的微创诊断系统，我们旨在构建一种基于深度学习的卷积神经网络（CNN）模型，用于自动检测子宫内膜微息肉（EMiP），这是一种在宫腔镜检查（F-HSC）中发现的微小突起性病变，被认为与这种疾病密切相关。
这是一项在私人诊所不孕中心进行的基于 F-HSC 图像的计算机研究。共纳入 244 名在 2019 年 4 月至 2021 年 12 月月经周期第 6-12 天行 F-HSC 的不孕妇女，所有患者均经免疫组化 CD138 辅助病理检查确诊为 CE。
最终对符合纳入标准的 208 名妇女（78 名有 EMiP，130 名无 EMiP）的 F-HSC 存档图像进行了分析。在对图像进行预处理后，将一半数据集输入到 CNN 架构中进行训练，而其余图像则用作测试集，以评估模型的性能，并与经验丰富的妇科医生进行比较。CNN 模型辅助诊断的灵敏度、特异性、准确性、精密度和 F1 分数分别为 93.6%、92.3%、92.8%、88.0%和 0.907。CNN 模型辅助诊断的受试者工作特征曲线下面积（0.930）与三位经验丰富的妇科医生的常规诊断值（0.927、0.948 和 0.906）相当（p>.05）。
这些发现表明，我们的基于深度学习的 CNN 能够识别 F-HSC 图像中的 EMiP，并有望进一步开发 CE 的计算机辅助诊断系统。
