Jiang Yuqi, Chan Cecilia K W, Chan Ronald C K, Wang Xin, Wong Nathalie, To Ka Fai, Ng Simon S M, Lau James Y W, Poon Carmen C Y
Department of SurgeryThe Chinese University of Hong Kong Hong Kong SAR.
Division of Vascular and General Surgery, Department of Surgery, Prince of Wales HospitalThe Chinese University of Hong Kong Hong Kong SAR.
IEEE Open J Eng Med Biol. 2022 Jul 19;3:115-123. doi: 10.1109/OJEMB.2022.3192103. eCollection 2022.
Colorectal cancer (CRC) patients respond differently to treatments and are sub-classified by different approaches. We evaluated a deep learning model, which adopted endoscopic knowledge learnt from AI-doscopist, to characterise CRC patients by histopathological features. Data of 461 patients were collected from TCGA-COAD database. The proposed framework was able to 1) differentiate tumour from normal tissues with an Area Under Receiver Operating Characteristic curve (AUROC) of 0.97; 2) identify certain gene mutations (MYH9, TP53) with an AUROC > 0.75; 3) classify CMS2 and CMS4 better than the other subtypes; and 4) demonstrate the generalizability of predicting KRAS mutants in an external cohort. Artificial intelligent can be used for on-site patient classification. Although KRAS mutants were commonly associated with therapeutic resistance and poor prognosis, subjects with predicted KRAS mutants in this study have a higher survival rate in 30 months after diagnoses.
结直肠癌（CRC）患者对治疗的反应各不相同，并通过不同方法进行亚分类。我们评估了一种深度学习模型，该模型采用从人工智能内镜医生那里学到的内镜知识，通过组织病理学特征对CRC患者进行特征描述。从TCGA-COAD数据库收集了461例患者的数据。所提出的框架能够：1）以0.97的受试者工作特征曲线下面积（AUROC）区分肿瘤组织与正常组织；2）识别某些基因突变（MYH9、TP53），AUROC>0.75；3）比其他亚型更好地分类CMS2和CMS4；4）在外部队列中证明预测KRAS突变体的可推广性。人工智能可用于对患者进行现场分类。虽然KRAS突变体通常与治疗耐药性和不良预后相关，但在本研究中预测为KRAS突变体的受试者在诊断后30个月的生存率较高。
