OBJECTIVES Reliable in situ diagnosis of diminutive (≤5 mm) colorectal polyps could allow for "resect and discard" and "diagnose and leave" strategies, resulting in $1 billion cost savings per year in the United States alone. Current methodologies have failed to consistently meet the Preservation and Incorporation of Valuable endoscopic Innovations (PIVIs) initiative thresholds. Convolutional neural networks (CNNs) have the potential to predict polyp pathology and achieve PIVI thresholds in real time. METHODS We developed a CNN-based optical pathology (OP) model using Tensorflow and pretrained on ImageNet, capable of operating at 77 frames per second. A total of 6,223 images of unique colorectal polyps of known pathology, location, size, and light source (white light or narrow band imaging [NBI]) underwent 5-fold cross-training (80%) and validation (20%). Separate fresh validation was performed on 634 polyp images. Surveillance intervals were calculated, comparing OP with true pathology. RESULTS In the original validation set, the negative predictive value for adenomas was 97% among diminutive rectum/rectosigmoid polyps. Results were independent of use of NBI or white light. Surveillance interval concordance comparing OP and true pathology was 93%. In the fresh validation set, the negative predictive value was 97% among diminutive polyps in the rectum and rectosigmoid and surveillance concordance was 94%. DISCUSSION This study demonstrates the feasibility of in situ diagnosis of colorectal polyps using CNN. Our model exceeds PIVI thresholds for both "resect and discard" and "diagnose and leave" strategies independent of NBI use. Point-of-care adenoma detection rate and surveillance recommendations are potential added benefits.

中文翻译：

---

使用卷积神经网络预测息肉病理学达到“切除和丢弃”阈值

目标 对微小 (≤5 mm) 结直肠息肉进行可靠的原位诊断可以实现“切除并丢弃”和“诊断并离开”策略，仅在美国每年就可节省 10 亿美元的成本。当前的方法未能始终满足有价值的内窥镜创新 (PIVI) 倡议阈值的保存和纳入。卷积神经网络 (CNN) 具有预测息肉病理学和实时实现 PIVI 阈值的潜力。方法 我们使用 Tensorflow 开发了一个基于 CNN 的光学病理学 (OP) 模型，并在 ImageNet 上进行了预训练，能够以每秒 77 帧的速度运行。共有 6,223 张独特的结直肠息肉图像，其病理、位置、大小、和光源（白光或窄带成像 [NBI]）经过 5 倍交叉训练（80%）和验证（20%）。对 634 个息肉图像进行了单独的新鲜验证。计算监测间隔，将 OP 与真实病理学进行比较。结果 在原始验证集中，在小型直肠/直肠乙状结肠息肉中，腺瘤的阴性预测值为 97%。结果与使用 NBI 或白光无关。比较 OP 和真实病理学的监测间隔一致性为 93%。在新验证集中，直肠和直肠乙状结肠小息肉的阴性预测值为 97%，监测一致性为 94%。讨论 本研究证明了使用 CNN 原位诊断结直肠息肉的可行性。我们的模型超过了“切除和丢弃”的 PIVI 阈值 以及独立于 NBI 使用的“诊断和离开”策略。床旁腺瘤检出率和监测建议是潜在的附加好处。