Whole slide image-based prediction of lymph node metastasis in T1 colorectal cancer using unsupervised artificial intelligence
Whole slide image-based prediction of lymph node metastasis in T1 colorectal cancer using unsupervised artificial intelligence
复制标题
使用无监督人工智能基于全幻灯片图像预测 T1 结直肠癌淋巴结转移
DOI：
10.1111/den.14547
复制
发表时间：
2023
影响因子：
5.3
通讯作者：
et. al
中科院分区：
文献类型：
--
作者：
Yuki Takashina ;Shin-Ei Kudo;Yuta Kouyama ;Katsuro Ichimasa ;Hideyuki Miyachi ;Masashi Misawa;et. al
T1期结直肠癌（CRC）淋巴结转移（LNM）的预测对于确定内镜切除术后是否需要手术至关重要，因为LNM发生率为10%。我们的目的是开发一种新的人工智能（AI）系统，使用全载玻片图像（WSIs）来预测LNM.MethodsWe进行了回顾性单中心研究。为了训练和测试AI模型，我们纳入了2001年4月至2021年10月期间LNM状态确认的T1和T2 CRC。这些病变分为两个队列：训练（T1和T2）和测试（T1）。WSI被裁剪成小块，并通过无监督K均值聚类。从每个WSI计算属于每个聚类的斑块的百分比。使用随机森林算法提取和学习每个聚类的百分比、性别和肿瘤位置。我们计算了受试者工作特征曲线（AUC）下的面积，以确定LNM和AI模型和guidelines.ResultsThe训练队列包含217个T1和268个T2 CRC，而100个T1病例（LNM阳性15%）是测试队列。使用指南标准，试验队列AI系统的AUC为0.74（95%置信区间[CI] 0.58-0.86）和0.52（95% CI 0.50-0.55）（P= 0.0028）。与指南相比，该AI模型可以减少21%的过度手术。结论我们使用WSI开发了T1 CRC中LNM的病理学家独立预测模型，用于确定内镜切除术后是否需要手术。试验注册UMIN临床试验注册（UMIN 000046992，https://center6.umin.ac.jp/cgi-open-bin/ctr/ctr_view.cgi? recptno=R000053590）。
ObjectivesLymph node metastasis (LNM) prediction for T1 colorectal cancer (CRC) is critical for determining the need for surgery after endoscopic resection because LNM occurs in 10%. We aimed to develop a novel artificial intelligence (AI) system using whole slide images (WSIs) to predict LNM.MethodsWe conducted a retrospective single center study. To train and test the AI model, we included LNM status‐confirmed T1 and T2 CRC between April 2001 and October 2021. These lesions were divided into two cohorts: training (T1 and T2) and testing (T1). WSIs were cropped into small patches and clustered by unsupervised K‐means. The percentage of patches belonging to each cluster was calculated from each WSI. Each cluster's percentage, sex, and tumor location were extracted and learned using the random forest algorithm. We calculated the areas under the receiver operating characteristic curves (AUCs) to identify the LNM and the rate of over‐surgery of the AI model and the guidelines.ResultsThe training cohort contained 217 T1 and 268 T2 CRCs, while 100 T1 cases (LNM‐positivity 15%) were the test cohort. The AUC of the AI system for the test cohort was 0.74 (95% confidence interval [CI] 0.58–0.86), and 0.52 (95% CI 0.50–0.55) using the guidelines criteria (P= 0.0028). This AI model could reduce the 21% of over‐surgery compared to the guidelines.ConclusionWe developed a pathologist‐independent predictive model for LNM in T1 CRC using WSI for determination of the need for surgery after endoscopic resection.Trial registrationUMIN Clinical Trials Registry (UMIN000046992, https://center6.umin.ac.jp/cgi-open-bin/ctr/ctr_view.cgi?recptno=R000053590).