The diagnostic ability to classify neoplasias occurring in inflammatory bowel disease by artificial intelligence and endoscopists -pilot study.
The diagnostic ability to classify neoplasias occurring in inflammatory bowel disease by artificial intelligence and endoscopists -pilot study.
复制标题
通过人工智能和内窥镜医师对炎症性肠病中发生的肿瘤进行分类的诊断能力 - 试点研究。
DOI：
10.1111/jgh.15904
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Kawahara Y.
中科院分区：
文献类型：
--
作者：
Yamamoto S;Kinugasa H;Hamada K;Tomiya M;Tanimoto T;Ohto A;Toda A;Takei D;Matsubara M;Suzuki S;Inoue K;Tanaka T;Hiraoka S;Okada H;Kawahara Y.
背景和目的虽然对于可见的低度不典型增生，允许进行仔细监测的内镜切除术而不是全直肠结肠切除术，但尚不清楚内镜医师如何准确地区分这些病变，因为由于背景慢性炎症，对炎症性肠病（IBDN）中发生的肿瘤进行分类非常具有挑战性。我们评估了用于对 IBDN 进行分类的人工智能 (AI) 系统的试点模型，并将其与内窥镜医师的能力进行了比较。方法本研究使用了深度卷积神经网络 EfficientNet-B3。在 2003 年至 2021 年间在两家医院接受 IBDN 治疗的患者中，我们从 99 个 IBDN 病变中选择了 862 张非放大内窥镜图像，并利用了 6 375 352 张图像，这些图像通过数据增强而增加，用于 AI 的开发。我们使用两个分类来评估人工智能的诊断能力：“腺癌/高度不典型增生”和“低度不典型增生/散发性腺瘤/正常粘膜”组。我们使用 186 个测试集图像比较了人工智能和内窥镜医生（三名非专家和四名专家）之间的诊断准确性。结果专家/非专家/人工智能对测试集图像中两种分类的诊断能力的敏感性为 60.5%（95% 置信区间 [CI]：54.5–66.3）/70.5%（95% CI： 63.8–76.6)/72.5% (95% CI: 60.4–82.5)，特异性为 88.0% (95% CI: 84.7–90.8)/78.8% (95% CI: 74.3–83.1)/82.9% (95% CI: 74.8–89.2)，准确度为 77.8%分别为（95% CI：74.7~80.8）/75.8%（95% CI：72~79.3）/79.0%（95% CI：72.5~84.6）。结论 IBDN 两种分类的诊断准确率均高于专家的诊断准确率。我们的人工智能系统非常有价值，足以为下一代临床实践做出贡献。
Background and AimAlthough endoscopic resection with careful surveillance instead of total proctocolectomy become to be permitted for visible low‐grade dysplasia, it is unclear how accurately endoscopists can differentiate these lesions, as classifying neoplasias occurring in inflammatory bowel disease (IBDN) is exceedingly challenging due to background chronic inflammation. We evaluated a pilot model of an artificial intelligence (AI) system for classifying IBDN and compared it with the endoscopist's ability.MethodsThis study used a deep convolutional neural network, the EfficientNet‐B3. Among patients who underwent treatment for IBDN at two hospitals between 2003 and 2021, we selected 862 non‐magnified endoscopic images from 99 IBDN lesions and utilized 6 375 352 images that were increased by data augmentation for the development of AI. We evaluated the diagnostic ability of AI using two classifications: the “adenocarcinoma/high‐grade dysplasia” and “low‐grade dysplasia/sporadic adenoma/normal mucosa” groups. We compared the diagnostic accuracy between AI and endoscopists (three non‐experts and four experts) using 186 test set images.ResultsThe diagnostic ability of the experts/non‐experts/AI for the two classifications in the test set images had a sensitivity of 60.5% (95% confidence interval [CI]: 54.5–66.3)/70.5% (95% CI: 63.8–76.6)/72.5% (95% CI: 60.4–82.5), specificity of 88.0% (95% CI: 84.7–90.8)/78.8% (95% CI: 74.3–83.1)/82.9% (95% CI: 74.8–89.2), and accuracy of 77.8% (95% CI: 74.7–80.8)/75.8% (95% CI: 72–79.3)/79.0% (95% CI: 72.5–84.6), respectively.ConclusionsThe diagnostic accuracy of the two classifications of IBDN was higher than that of the experts. Our AI system is valuable enough to contribute to the next generation of clinical practice.