Deep learning for prediction of colorectal cancer outcome: a discovery and validation study
Deep learning for prediction of colorectal cancer outcome: a discovery and validation study
复制标题
DOI：
10.1016/s0140-6736(19)32998-8
复制
发表时间：
2020-02-01
期刊：
影响因子：
168.9
通讯作者：
Danielsen, Havard E.
中科院分区：
文献类型：
--
作者：
Skrede, Ole-Johan;De Raedt, Sepp;Danielsen, Havard E.
背景：需要改进的预后标志物来对早期结直肠癌患者进行分层，以完善辅助治疗的选择。本研究的目的是通过使用深度学习直接分析扫描的常规苏木精和伊红染色切片来开发原发性结直肠癌切除术后患者结局的生物标志物。方法来自四个队列的疾病结局明显良好或不良的患者的超过12 000 000个图像块用于训练总共10个卷积神经网络，专为分类超大型异构图像而构建。使用具有非明显结果的患者确定整合十个网络的预后生物标志物。该标记物在920名患者中进行了测试，使用在英国制备的载玻片，然后根据预定义的方案在1122名使用挪威制备的载玻片接受卡培他滨单药治疗的患者中进行了独立验证。所有队列仅包括可切除肿瘤的患者，以及可用于分析的福尔马林固定、石蜡包埋的肿瘤组织块。主要结果是癌症特异性survival.Findings 828例患者从四个队列有一个不同的结果，并作为一个训练队列，以获得明确的地面真相。1645例患者的结局不明显，并用于调整。该生物标志物提供的不良预后与良好预后的风险比为3.84（95%CI 2.72-5.43; p
Background Improved markers of prognosis are needed to stratify patients with early-stage colorectal cancer to refine selection of adjuvant therapy. The aim of the present study was to develop a biomarker of patient outcome after primary colorectal cancer resection by directly analysing scanned conventional haematoxylin and eosin stained sections using deep learning.Methods More than 12 000 000 image tiles from patients with a distinctly good or poor disease outcome from four cohorts were used to train a total of ten convolutional neural networks, purpose-built for classifying supersized heterogeneous images. A prognostic biomarker integrating the ten networks was determined using patients with a non-distinct outcome. The marker was tested on 920 patients with slides prepared in the UK, and then independently validated according to a predefined protocol in 1122 patients treated with single-agent capecitabine using slides prepared in Norway. All cohorts included only patients with resectable tumours, and a formalin-fixed, paraffin-embedded tumour tissue block available for analysis. The primary outcome was cancer-specific survival.Findings 828 patients from four cohorts had a distinct outcome and were used as a training cohort to obtain clear ground truth. 1645 patients had a non-distinct outcome and were used for tuning. The biomarker provided a hazard ratio for poor versus good prognosis of 3.84 (95% CI 2.72-5.43; p