深度学习可以根据内镜图像预测食道水出血
Yu Hong1, Qianqian Yu2, Feng Mo3
1Department of Gastroenterology, The First Affiliated Hospital of Soochow University, Suzhou, China.
深度学习模型从内镜图像中准确地预测食道静脉出血风险. 人工智能辅助显著提高了内镜医生的诊断准确度,有助于肝硬化管理.
科学领域:
- 肝病学 肝病学是一种肝病学.
- 医疗成像医学成像
- 人工智能的人工智能
背景情况:
- 食道静脉 (EV) 出血是肝硬化的严重并发症.
- 目前的预测方法依赖于经验丰富的内镜师,但往往不可靠和低效.
研究的目的:
- 评估使用深度学习 (DL) 模型预测使用内镜图像预测12个月EV出血风险的可行性.
- 为了比较DL模型与人类内镜医生的诊断性能.
主要方法:
- 训练了6个DL模型进行内镜图像的二元分类.
- 模型在外部数据集上得到验证,并与两个内镜师的分类进行了比较.
主要成果:
- 在测试数据集中,EfficientNet获得了最高的精度 (0.893),超过了内镜 (0.800和0.763).
- 人工智能协助提高了内镜师的精度17.3%和19.0%.
- 模型架构影响了统计协议.
结论:
- 深度学习模型显示了从内镜图像预测12个月EV出血风险的可行性.
- 人工智能辅助诊断为改善肝硬化管理提供了一个有希望的工具.
更多相关视频
06:55Diagnosis of Neoplasia in Barrett’s Esophagus using Vital-dye Enhanced Fluorescence Imaging
Published on: May 11, 2014
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
相关概念视频
Esophageal Varices-II: Clinical Features and Management
In the initial assessment, a thorough review of the patient's medical history is vital to identify risk factors such as liver disease, alcohol...
Esophageal Varices-I: Introduction
Endoscopic Procedures I: Esophagogastroduodenoscopy
During an EGD, the endoscope can be used to:
Endoscopic Procedures III: Video Capsule Endoscopy
Ultrasound II: Endoscopic Ultrasound and FibroScan
Endoscopic Ultrasound (EUS):
Esophageal Strictures-II: Clinical Features and Management
Healthcare providers should gather a comprehensive medical history and conduct a physical examination for diagnosis. If esophageal stricture is...
