PURPOSE There are few markers to identify those likely to recur or progress after treatment with intravesical bacillus Calmette-Guérin (BCG). We developed and validated artificial intelligence-based histologic assays that extract interpretable features from transurethral resection of bladder tumor digitized pathology images to predict risk of recurrence, progression, development of BCG-unresponsive disease, and cystectomy. MATERIALS AND METHODS Pre-BCG resection-derived whole-slide images and clinical data were obtained for high-risk NMIBC cases treated with BCG from 12 centers and were analyzed through a segmentation and feature extraction pipeline. Features associated with clinical outcomes were defined and tested on independent development and validation cohorts. Cases were classified into high or low risk for recurrence, progression, BCG-unresponsive disease, and cystectomy. RESULTS Nine hundred forty-four cases (development: 303, validation: 641, median follow-up: 36 months) representative of the intended use population were included (high-grade Ta: 34.1%, high-grade T1: 54.8%; carcinoma in situ only: 11.1%, any carcinoma in situ: 31.4%). In the validation cohort, "high recurrence risk" cases had inferior high-grade recurrence-free survival vs "low recurrence risk" cases (HR, 2.08, P < .0001). "High progression risk" patients had poorer progression-free survival (HR, 3.87, P < .001) and higher risk of cystectomy (HR, 3.35, P < .001) than "low progression risk" patients. Cases harboring the BCG-unresponsive disease signature had a shorter time to development of BCG-unresponsive disease than cases without the signature (HR, 2.31, P < .0001). AI assays provided predictive information beyond clinicopathologic factors. CONCLUSIONS We developed and validated AI-based histologic assays that identify high-risk NMIBC cases at higher risk of recurrence, progression, BCG-unresponsive disease, and cystectomy, potentially aiding clinical decision making.

中文翻译：

---

使用人工智能驱动的病理学检测预测高危 NMIBC 对膀胱内 BCG 的反应：在国际 12 中心队列中开发和验证。


目的 几乎没有标志物可以识别那些在膀胱内卡介苗 （BCG） 治疗后可能复发或进展的标志物。我们开发并验证了基于人工智能的组织学检测方法，可从经尿道膀胱肿瘤切除术数字化病理图像中提取可解释的特征，以预测复发、进展、BCG 无反应性疾病发展和膀胱切除术的风险。材料和方法 从 12 个中心获得接受 BCG 治疗的高危 NMIBC 病例的 BCG 切除前衍生的全玻片图像和临床数据，并通过分割和特征提取管道进行分析。在独立的开发和验证队列中定义和测试与临床结果相关的特征。病例分为复发、进展、BCG 无反应性疾病和膀胱切除术的高风险或低风险。结果 纳入了代表预期用途人群的 944 例病例 （发展： 303， 验证： 641， 中位随访： 36 个月） （高级别 Ta： 34.1%，高级别 T1： 54.8%;仅原位癌： 11.1%，任何原位癌： 31.4%）。在验证队列中，“高复发风险”病例与“低复发风险”病例的无复发生存率较差 （HR， 2.08， P < .0001）。与“低进展风险”患者相比，“高进展风险”患者的无进展生存期 （HR， 3.87， P < .001） 较差，膀胱切除术风险较高 （HR， 3.35， P < .001）。携带 BCG 无反应疾病特征的病例比没有特征的病例发展为 BCG 无反应疾病的时间短 （HR，2.31，P < .0001）。AI 检测提供了临床病理因素之外的预测信息。 结论 我们开发并验证了基于 AI 的组织学分析，可识别复发、进展、BCG 无反应性疾病和膀胱切除术风险较高的高危 NMIBC 病例，可能有助于临床决策。