文献速递膀胱癌与上尿路尿路上皮癌

深度学习增强膀胱肿瘤检测

Augmented Bladder Tumor Detection Using Deep Learning.
PubMed 文献 · Eur Urol · 2019-09-17

本研究开发了基于卷积神经网络的CystoNet平台,用于膀胱镜自动检测膀胱肿瘤。在54例前瞻性验证队列中,每帧敏感性和特异性分别为90.9%和98.6%,每肿瘤敏感性为90.9%,检出41个乳头状癌中的39个和3个平坦型癌中的3个。CystoNet有望提高膀胱镜诊断率和TURBT疗效。

要点

  • 标准白光膀胱镜遗漏高达20%的膀胱肿瘤。
  • CystoNet每帧敏感性90.9%、特异性98.6%。
  • 每肿瘤敏感性90.9%,检出39/41乳头状癌和3/3平坦型癌。

核心结论

  • CystoNet深度学习算法在膀胱镜图像中检测膀胱癌具有高敏感性和特异性,可能改善诊断率和TURBT疗效。

研究设计与样本

  • 开发数据集包含95例患者用于训练、5例用于测试,前瞻性验证队列包含54例患者。

主要发现

  • 验证队列每帧敏感性90.9%(95%CI 90.3-91.6%),特异性98.6%(95%CI 98.5-98.8%)。
  • 每肿瘤敏感性90.9%(95%CI 90.3-91.6%)。
  • 检出39/41例乳头状癌和3/3例平坦型癌。

临床怎么用

  • CystoNet可作为膀胱镜辅助工具,帮助定位肿瘤并指导术中切除。

局限性

  • 原文未报告验证队列的详细人群特征、多中心外部验证结果及实时性能数据。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

Adequate tumor detection is critical in complete transurethral resection of bladder tumor (TURBT) to reduce cancer recurrence, but up to 20% of bladder tumors are missed by standard white light cystoscopy. Deep learning augmented cystoscopy may improve tumor localization, intraoperative navigation, and surgical resection of bladder cancer. We aimed to develop a deep learning algorithm for augmented cystoscopic detection of bladder cancer. Patients undergoing cystoscopy/TURBT were recruited and white light videos were recorded. Video frames containing histologically confirmed papillary urothelial carcinoma were selected and manually annotated. We constructed CystoNet, an image analysis platform based on convolutional neural networks, for automated bladder tumor detection using a development dataset of 95 patients for algorithm training and five patients for testing. Diagnostic performance of CystoNet was validated prospectively in an additional 54 patients. In the validation dataset, per-frame sensitivity and specificity were 90.9% (95% confidence interval [CI], 90.3-91.6%) and 98.6% (95% CI, 98.5-98.8%), respectively. Per-tumor sensitivity was 90.9% (95% CI, 90.3-91.6%). CystoNet detected 39 of 41 papillary and three of three flat bladder cancers. With high sensitivity and specificity, CystoNet may improve the diagnostic yield of cystoscopy and efficacy of TURBT. PATIENT SUMMARY: Conventional cystoscopy has recognized shortcomings in bladder cancer detection, with implications for recurrence. Cystoscopy augmented with artificial intelligence may improve cancer detection and resection.

来源:Eur Urol,查看原文。版权归原作者所有。

引用

  1. Shkolyar E, Jia X, Chang TC, et al. Augmented Bladder Tumor Detection Using Deep Learning. Eur Urol. 2019. PMID: 31537407. doi:10.1016/j.eururo.2019.08.032

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。