Cheeloo College of Medicine, Shandong University, Jinan City, China.
Department of Pathology, School of Basic Medical Science, Cheeloo College of Medicine, Shandong University, Jinan City, China.
Cancer Med. 2023 Sep;12(17):17952-17966. doi: 10.1002/cam4.6437. Epub 2023 Aug 10.
Lymph node metastasis (LNM) significantly impacts the prognosis of individuals diagnosed with cervical cancer, as it is closely linked to disease recurrence and mortality, thereby impacting therapeutic schedule choices for patients. However, accurately predicting LNM prior to treatment remains challenging. Consequently, this study seeks to utilize digital pathological features extracted from histopathological slides of primary cervical cancer patients to preoperatively predict the presence of LNM.
A deep learning (DL) model was trained using the Vision transformer (ViT) and recurrent neural network (RNN) frameworks to predict LNM. This prediction was based on the analysis of 554 histopathological whole-slide images (WSIs) obtained from Qilu Hospital of Shandong University. To validate the model's performance, an external test was conducted using 336 WSIs from four other hospitals. Additionally, the efficiency of the DL model was evaluated using 190 cervical biopsies WSIs in a prospective set.
In the internal test set, our DL model achieved an area under the curve (AUC) of 0.919, with sensitivity and specificity values of 0.923 and 0.905, respectively, and an accuracy (ACC) of 0.909. The performance of the DL model remained strong in the external test set. In the prospective cohort, the AUC was 0.91, and the ACC was 0.895. Additionally, the DL model exhibited higher accuracy compared to imaging examination in the evaluation of LNM. By utilizing the transformer visualization method, we generated a heatmap that illustrates the local pathological features in primary lesions relevant to LNM.
DL-based image analysis has demonstrated efficiency in predicting LNM in early operable cervical cancer through the utilization of biopsies WSI. This approach has the potential to enhance therapeutic decision-making for patients diagnosed with cervical cancer.
淋巴结转移（LNM）显著影响宫颈癌患者的预后，因为它与疾病复发和死亡率密切相关，从而影响患者的治疗方案选择。然而，在治疗前准确预测 LNM 仍然具有挑战性。因此，本研究旨在利用从原发性宫颈癌患者的组织病理学幻灯片中提取的数字病理学特征来术前预测 LNM 的存在。
使用 Vision transformer（ViT）和递归神经网络（RNN）框架训练深度学习（DL）模型来预测 LNM。该预测基于对来自山东大学齐鲁医院的 554 张组织病理学全幻灯片图像（WSI）的分析。为了验证模型的性能，使用来自其他四个医院的 336 张 WSI 进行了外部测试。此外，还在一个前瞻性队列中使用 190 张宫颈活检 WSI 评估了 DL 模型的效率。
在内部测试集中，我们的 DL 模型的曲线下面积（AUC）为 0.919，灵敏度和特异性值分别为 0.923 和 0.905，准确性（ACC）为 0.909。DL 模型在外部测试集中的性能仍然很强。在前瞻性队列中，AUC 为 0.91，ACC 为 0.895。此外，与影像学检查相比，DL 模型在评估 LNM 方面具有更高的准确性。通过利用变压器可视化方法，我们生成了一个热图，说明了原发性病变中与 LNM 相关的局部病理特征。
通过使用活检 WSI，基于 DL 的图像分析已证明在预测早期可手术宫颈癌的 LNM 方面具有效率。这种方法有可能增强对宫颈癌患者的治疗决策。
