Accurate Classification of Diminutive Colorectal Polyps Using Computer-Aided Analysis
Accurate Classification of Diminutive Colorectal Polyps Using Computer-Aided Analysis
复制标题
DOI：
10.1053/j.gastro.2017.10.010
复制
发表时间：
2018-02-01
期刊：
影响因子：
29.4
通讯作者：
Tseng, Vincent S.
中科院分区：
文献类型：
--
作者：
Chen, Peng-Jen;Lin, Meng-Chiung;Tseng, Vincent S.
背景与目的：窄带成像是一种图像增强形式的内窥镜，用于观察粘膜上皮的微观结构和毛细血管，从而可以实时预测结直肠息肉的组织学特征。然而，需要窄带成像的专业知识来区分增生性息肉和肿瘤性息肉，具有高水平的准确性。我们开发并测试了一种使用深度神经网络（DNN-CAD）的计算机辅助诊断系统，以分析小型结直肠息肉的窄带图像。方法：我们收集了1476张肿瘤性息肉和681张增生性息肉的图像，这些图像来自台湾一家三级医院的图像存档和通信系统数据库。还收集了息肉的组织学发现并用作参考标准。这些图像和数据被用来训练DNN。然后使用从2017年3月至2017年8月接受结肠镜检查的患者中获得的图像测试集（96个增生性息肉和188个肿瘤性息肉，小于5 mm）来测试DNN-CAD与内窥镜医师（2名专家和4名新手）的诊断能力，内窥镜医师被要求将测试集的图像分类为肿瘤性或增生性。将其分类与组织学分析结果进行比较。主要结果指标为诊断准确性、敏感性、特异性、阳性预测值（PPV）、阴性预测值（NPV）和诊断时间。比较DNN-CAD、新手内镜医师和专家内镜医师的准确性、敏感性、特异性、PPV、NPV和诊断时间。本研究旨在通过双侧McNemar检验检测10%的准确度差异。研究结果：在测试集中，DNN-CAD识别肿瘤性或增生性息肉的灵敏度为96.3%，特异性为78.1%，PPV为89.6%，NPV为91.5%。不到一半的新手内镜医师将息肉分类为NPV为90%（他们的NPV范围为73.9%至84.0%）。DNN-CAD在0.45 ± 0.07秒内将息肉分类为肿瘤性或增生性-比专家（1.54 ± 1.30秒）和非专家（1.77 ± 1.37秒）所需的时间短（均P <0.001）。DNN-CAD对息肉进行了分类，观察者之间具有完美的一致性（kappa评分为1）。内镜医师之间的分类观察者内和观察者间一致性水平较低。结论：我们开发了一个名为DNN-CAD的系统来识别小于5 mm的肿瘤性或增生性结直肠息肉。该系统对息肉进行分类，PPV为89.6%，NPV为91.5%，并且比内窥镜检查时间更短。这种深度学习模型不仅有可能用于内窥镜图像识别，还可能用于其他形式的医学图像分析，包括超声检查、计算机断层扫描和磁共振图像。
BACKGROUND & AIMS: Narrow-band imaging is an image-enhanced form of endoscopy used to observed microstructures and capillaries of the mucosal epithelium which allows for real-time prediction of histologic features of colorectal polyps. However, narrow-band imaging expertise is required to differentiate hyperplastic from neoplastic polyps with high levels of accuracy. We developed and tested a system of computer-aided diagnosis with a deep neural network (DNN-CAD) to analyze narrow-band images of diminutive colorectal polyps. METHODS: We collected 1476 images of neoplastic polyps and 681 images of hyperplastic polyps, obtained from the picture archiving and communications system database in a tertiary hospital in Taiwan. Histologic findings from the polyps were also collected and used as the reference standard. The images and data were used to train the DNN. A test set of images (96 hyperplastic and 188 neoplastic polyps, smaller than 5 mm), obtained from patients who underwent colonoscopies from March 2017 through August 2017, was then used to test the diagnostic ability of the DNN-CAD vs endoscopists (2 expert and 4 novice), who were asked to classify the images of the test set as neoplastic or hyperplastic. Their classifications were compared with findings from histologic analysis. The primary outcome measures were diagnostic accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and diagnostic time. The accuracy, sensitivity, specificity, PPV, NPV, and diagnostic time were compared among DNN-CAD, the novice endoscopists, and the expert endoscopists. The study was designed to detect a difference of 10% in accuracy by a 2-sided McNemar test. RESULTS: In the test set, the DNN-CAD identified neoplastic or hyperplastic polyps with 96.3% sensitivity, 78.1% specificity, a PPV of 89.6%, and a NPV of 91.5%. Fewer than half of the novice endoscopists classified polyps with a NPV of 90% (their NPVs ranged from 73.9% to 84.0%). DNN-CAD classified polyps as neoplastic or hyperplastic in 0.45 +/- 0.07 seconds-shorter than the time required by experts (1.54 +/- 1.30 seconds) and nonexperts (1.77 +/- 1.37 seconds) (both P < .001). DNN-CAD classified polyps with perfect intra-observer agreement (kappa score of 1). There was a low level of intra-observer and inter-observer agreement in classification among endoscopists. CONCLUSIONS: We developed a system called DNN-CAD to identify neoplastic or hyperplastic colorectal polyps less than 5 mm. The system classified polyps with a PPV of 89.6%, and a NPV of 91.5%, and in a shorter time than endoscopists. This deep-learning model has potential for not only endoscopic image recognition but for other forms of medical image analysis, including sonography, computed tomography, and magnetic resonance images.