The pathological risk score: A new deep learning-based signature for predicting survival in cervical cancer.
The pathological risk score: A new deep learning-based signature for predicting survival in cervical cancer.
复制标题
DOI：
10.1002/cam4.4953
复制
发表时间：
2023-01
期刊：
影响因子：
4
通讯作者：
Tian, Jie
中科院分区：
文献类型：
--
作者：
Chen, Chi;Cao, Yuye;Li, Weili;Liu, Zhenyu;Liu, Ping;Tian, Xin;Sun, Caixia;Wang, Wuliang;Gao, Han;Kang, Shan;Wang, Shaoguang;Jiang, Jingying;Chen, Chunlin;Tian, Jie
开发并验证基于深度学习的病理风险评分（RS），以预测患者预后，探讨全幻灯片图像（WSI）内信息与宫颈癌预后之间的潜在关联。本研究共纳入251例FIGO (International Federation of Gynecology and Obstetrics) IA1-IIA2期宫颈癌患者，术前未进行任何治疗。收集每位患者的临床特征和WSI。为了构建与预后相关的RS，使用带有自编码器的卷积神经网络提取高维病理特征。使用X - tile选择的评分阈值，应用Kaplan-Meier生存分析来验证RS在训练和测试数据集以及不同临床亚组中对总生存期（OS）和无病生存期（DFS）的预测性能。对于检测队列的OS和DFS预测，RS显示Harrell’s concordance index > 0.700，而同一队列的曲线下面积（AUC）达到0.800。此外，Kaplan-Meier生存分析表明，RS是一个潜在的预后因素，即使在不同的数据集或亚组中也是如此。进一步区分临床病理危险分层后的生存差异。在本研究中，我们建立了宫颈癌预后预测和患者OS和DFS分层的有效标志。这是一项基于深度学习的研究，对整个幻灯片图像的高维特征进行编码，以建立独立的预后风险评分，该评分可以进一步区分临床病理风险分层后的生存差异。
To develop and validate a deep learning‐based pathological risk score (RS) with an aim of predicting patients' prognosis to investigate the potential association between the information within the whole slide image (WSI) and cervical cancer prognosis. A total of 251 patients with the International Federation of Gynecology and Obstetrics (FIGO) Stage IA1–IIA2 cervical cancer who underwent surgery without any preoperative treatment were enrolled in this study. Both the clinical characteristics and WSI of each patient were collected. To construct a prognosis‐associate RS, high‐dimensional pathological features were extracted using a convolutional neural network with an autoencoder. With the score threshold selected by X‐tile, Kaplan–Meier survival analysis was applied to verify the prediction performance of RS in overall survival (OS) and disease‐free survival (DFS) in both the training and testing datasets, as well as different clinical subgroups. For the OS and DFS prediction in the testing cohort, RS showed a Harrell's concordance index of higher than 0.700, while the areas under the curve (AUC) achieved up to 0.800 in the same cohort. Furthermore, Kaplan–Meier survival analysis demonstrated that RS was a potential prognostic factor, even in different datasets or subgroups. It could further distinguish the survival differences after clinicopathological risk stratification. In the present study, we developed an effective signature in cervical cancer for prognosis prediction and patients' stratification in OS and DFS. This is a deep learning‐based study that encoded the high dimensional features from whole slide image to establish an independent prognostic risk score, which can further distinguish survival differences after clinicopathological risk stratification.
登录
查看更多内容
影响因子：
4.7
作者：
KINNEY, WK;ALVAREZ, RD;SHINGLETON, HM
通讯作者：
SHINGLETON, HM
影响因子：
--
作者：
Kothari, Sonal;Phan, John H;Wang, May D
通讯作者：
Wang, May D
影响因子：
16.6
作者：
Liu, Ziheng;Yang, Ying;Wen, Wenyu
通讯作者：
Wen, Wenyu
DOI：
10.1073/pnas.1717139115
发表时间：
2018-03-27
影响因子：
11.1
作者：
Mobadersany P;Yousefi S;Amgad M;Gutman DA;Barnholtz-Sloan JS;Velázquez Vega JE;Brat DJ;Cooper LAD
通讯作者：
Cooper LAD
影响因子：
4.7
作者：
DELGADO, G;BUNDY, B;MAJOR, F
通讯作者：
MAJOR, F