Yong Loo Lin School of Medicine, National University Singapore, Singapore, Singapore.
Department of Anatomical Pathology, Singapore General Hospital, 20 College Road, Singapore, 169856, Singapore.
Sci Rep. 2022 Feb 9;12(1):2222. doi: 10.1038/s41598-022-06264-x.
Colorectal cancer is one of the most common cancers worldwide, accounting for an annual estimated 1.8 million incident cases. With the increasing number of colonoscopies being performed, colorectal biopsies make up a large proportion of any histopathology laboratory workload. We trained and validated a unique artificial intelligence (AI) deep learning model as an assistive tool to screen for colonic malignancies in colorectal specimens, in order to improve cancer detection and classification; enabling busy pathologists to focus on higher order decision-making tasks. The study cohort consists of Whole Slide Images (WSI) obtained from 294 colorectal specimens. Qritive's unique composite algorithm comprises both a deep learning model based on a Faster Region Based Convolutional Neural Network (Faster-RCNN) architecture for instance segmentation with a ResNet-101 feature extraction backbone that provides glandular segmentation, and a classical machine learning classifier. The initial training used pathologists' annotations on a cohort of 66,191 image tiles extracted from 39 WSIs. A subsequent application of a classical machine learning-based slide classifier sorted the WSIs into 'low risk' (benign, inflammation) and 'high risk' (dysplasia, malignancy) categories. We further trained the composite AI-model's performance on a larger cohort of 105 resections WSIs and then validated our findings on a cohort of 150 biopsies WSIs against the classifications of two independently blinded pathologists. We evaluated the area under the receiver-operator characteristic curve (AUC) and other performance metrics. The AI model achieved an AUC of 0.917 in the validation cohort, with excellent sensitivity (97.4%) in detection of high risk features of dysplasia and malignancy. We demonstrate an unique composite AI-model incorporating both a glandular segmentation deep learning model and a classical machine learning classifier, with excellent sensitivity in picking up high risk colorectal features. As such, AI plays a role as a potential screening tool in assisting busy pathologists by outlining the dysplastic and malignant glands.
结直肠癌是全球最常见的癌症之一，每年估计有 180 万例新发病例。随着结肠镜检查数量的增加，结直肠活检在任何组织病理学实验室工作量中占很大比例。我们训练和验证了一个独特的人工智能（AI）深度学习模型作为辅助工具，以筛查结直肠标本中的结肠恶性肿瘤，从而提高癌症检测和分类的能力；使忙碌的病理学家能够专注于更高层次的决策任务。该研究队列包括 294 份结直肠标本的全切片图像（WSI）。Qritive 的独特组合算法包括一个基于 Faster Region Based Convolutional Neural Network（Faster-RCNN）架构的深度学习模型，用于实例分割，具有 ResNet-101 特征提取骨干，提供腺体分割，以及一个经典的机器学习分类器。最初的训练使用了来自 39 张 WSI 的 66191 张图像块的病理学家注释。随后，应用基于经典机器学习的幻灯片分类器将 WSI 分为“低风险”（良性、炎症）和“高风险”（发育不良、恶性）类别。我们进一步在更大的 105 例切除 WSI 队列上训练了组合 AI 模型的性能，然后在 150 例活检 WSI 队列上验证了我们的发现，对照两名独立盲法病理学家的分类。我们评估了接收者操作特征曲线下的面积（AUC）和其他性能指标。该 AI 模型在验证队列中获得了 0.917 的 AUC，在检测发育不良和恶性特征的高风险方面具有出色的敏感性（97.4%）。我们展示了一个独特的组合 AI 模型，该模型结合了一个腺体分割深度学习模型和一个经典的机器学习分类器，在识别结直肠高危特征方面具有出色的敏感性。因此，人工智能在帮助忙碌的病理学家勾勒出发育不良和恶性腺体方面，可以作为一种潜在的筛选工具发挥作用。
