超声成像因其无创、成本低、实时成像等特点，成为子宫内膜疾病早期诊断的首选方法。然而，超声图像的准确评估很大程度上依赖于放射科医生的经验。因此，稳定、客观的计算机辅助诊断模型对于辅助放射科医生诊断子宫内膜病变至关重要。 经阴道超声图像采集自浙江省衢州市多家医院。该数据集包含来自 734 名患者的 1875 张图像，包括子宫内膜息肉、增生和癌症病例。在这里，我们提出了一种基于自监督子宫内膜疾病分类模型（BSEM），该模型学习联合统一任务（原始任务和自监督任务）并应用自蒸馏技术和集成策略来帮助医生诊断子宫内膜疾病。 BSEM 使用五重交叉验证进行评估。实验结果表明，BSEM模型在各项指标上均取得了令人满意的表现，准确率、曲线下面积、查准率、召回率和F1分数分别为75.1%、87.3%、76.5%、73.4%和74.1%。此外，与基线模型 ResNet、DenseNet、VGGNet、ConvNeXt、VIT 和 CMT 相比，BSEM 模型的准确率、曲线下面积、精确率、召回率和 F1 分数分别提高了 3.3-7.9%、3.2-7.3%、3.9分别为-8.5%、3.1-8.5%和3.3-9.0%。BSEM模型是超声显示子宫内膜疾病早期发现的辅助诊断工具，帮助放射科医生准确、高效地筛查子宫内膜癌前病变。 © 2023。作者。

Ultrasound imaging is the preferred method for the early diagnosis of endometrial diseases because of its non-invasive nature, low cost, and real-time imaging features. However, the accurate evaluation of ultrasound images relies heavily on the experience of radiologist. Therefore, a stable and objective computer-aided diagnostic model is crucial to assist radiologists in diagnosing endometrial lesions.Transvaginal ultrasound images were collected from multiple hospitals in Quzhou city, Zhejiang province. The dataset comprised 1875 images from 734 patients, including cases of endometrial polyps, hyperplasia, and cancer. Here, we proposed a based self-supervised endometrial disease classification model (BSEM) that learns a joint unified task (raw and self-supervised tasks) and applies self-distillation techniques and ensemble strategies to aid doctors in diagnosing endometrial diseases.The performance of BSEM was evaluated using fivefold cross-validation. The experimental results indicated that the BSEM model achieved satisfactory performance across indicators, with scores of 75.1%, 87.3%, 76.5%, 73.4%, and 74.1% for accuracy, area under the curve, precision, recall, and F1 score, respectively. Furthermore, compared to the baseline models ResNet, DenseNet, VGGNet, ConvNeXt, VIT, and CMT, the BSEM model enhanced accuracy, area under the curve, precision, recall, and F1 score in 3.3-7.9%, 3.2-7.3%, 3.9-8.5%, 3.1-8.5%, and 3.3-9.0%, respectively.The BSEM model is an auxiliary diagnostic tool for the early detection of endometrial diseases revealed by ultrasound and helps radiologists to be accurate and efficient while screening for precancerous endometrial lesions.© 2023. The Author(s).