INESCTEC, 4200-465, Porto, Portugal.
FEUP, University of Porto, 4200-465, Porto, Portugal.
Sci Rep. 2023 Mar 9;13(1):3970. doi: 10.1038/s41598-023-30497-z.
Cervical cancer is the fourth most common female cancer worldwide and the fourth leading cause of cancer-related death in women. Nonetheless, it is also among the most successfully preventable and treatable types of cancer, provided it is early identified and properly managed. As such, the detection of pre-cancerous lesions is crucial. These lesions are detected in the squamous epithelium of the uterine cervix and are graded as low- or high-grade intraepithelial squamous lesions, known as LSIL and HSIL, respectively. Due to their complex nature, this classification can become very subjective. Therefore, the development of machine learning models, particularly directly on whole-slide images (WSI), can assist pathologists in this task. In this work, we propose a weakly-supervised methodology for grading cervical dysplasia, using different levels of training supervision, in an effort to gather a bigger dataset without the need of having all samples fully annotated. The framework comprises an epithelium segmentation step followed by a dysplasia classifier (non-neoplastic, LSIL, HSIL), making the slide assessment completely automatic, without the need for manual identification of epithelial areas. The proposed classification approach achieved a balanced accuracy of 71.07% and sensitivity of 72.18%, at the slide-level testing on 600 independent samples, which are publicly available upon reasonable request.
宫颈癌是全球第四常见的女性癌症，也是女性癌症相关死亡的第四大主要原因。然而，如果能够及早发现并妥善管理，它也是最成功预防和治疗的癌症类型之一。因此，癌前病变的检测至关重要。这些病变在子宫颈的鳞状上皮中被发现，并被分级为低级别或高级别上皮内鳞状病变，分别称为 LSIL 和 HSIL。由于其复杂性，这种分类可能变得非常主观。因此，机器学习模型的开发，特别是直接在全切片图像（WSI）上的开发，可以帮助病理学家完成这项任务。在这项工作中，我们提出了一种使用不同程度的训练监督来分级宫颈发育不良的弱监督方法，努力在不需要对所有样本进行全面注释的情况下收集更大的数据集。该框架包括上皮分割步骤和发育不良分类器（非肿瘤性、LSIL、HSIL），使幻灯片评估完全自动化，无需手动识别上皮区域。在对 600 个独立样本进行的幻灯片级测试中，所提出的分类方法的平衡准确率为 71.07%，灵敏度为 72.18%，这些样本可根据合理要求公开获取。
