基于PET/CT成像和深度学习模型的超代谢性肺病变检测和诊断
Jiajia Hu1, Ran Cheng1, Meilin Quan2,3
1Department of Nuclear Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, No.197 Ruijin Second Road, Huangpu District, Shanghai, China.
深度学习模型使用PET/CT扫描准确地检测和分类高代谢性肺病变. 人工智能显示出改善肺病诊断和临床决策的前景.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 在瘤学瘤学.
背景情况:
- 超代谢性肺病变需要准确的检测和分类才能进行有效的治疗.
- 区分良性病变,肺癌,淋巴瘤和转移是临床上至关重要的.
- 目前的诊断方法可能耗时,可能有局限性.
研究的目的:
- 开发和评估深度学习 (DL) 模型,用于检测和分类高代谢性肺病变.
- 将病变分为四个不同的类别:良性,肺癌,肺淋巴瘤和转移.
- 将DL模型的性能与传统的放射学方法进行比较.
主要方法:
- 使用手动注释的PET/CT图像开发病变定位模型.
- 实施一个多维联合分类网络,整合图像补丁和2D投影.
- 使用精度和曲线下的面积 (AUC) 等指标进行性能评估,并与放射学模型进行比较.
主要成果:
- 该研究包括多个中心和数据集的647个回顾性病例.
- 本地化模型的检测率在75.48%至81.19%之间.
- DL分类模型表现出比放射学更优异的性能,AUC为88.4% (内部) 和80.7% (外部测试集I).
结论:
- 深度学习模型有效地检测,细分和分类PET/CT上的高代谢性肺病变.
- 这些人工智能模型还可以识别可疑的邻近病变,帮助临床评估.
- 这些发现强调了人工智能在肺部疾病诊断中增强临床决策的潜力.
更多相关视频
10:04Analysis of 18FDG PET/CT Imaging as a Tool for Studying Mycobacterium tuberculosis Infection and Treatment in Non-human Primates
Published on: September 5, 2017
06:51Utilizing 18F-FDG PET/CT Imaging and Quantitative Histology to Measure Dynamic Changes in the Glucose Metabolism in Mouse Models of Lung Cancer
Published on: July 21, 2018
相关概念视频
01:29Positron Emission Tomography
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...
01:13Radiological Investigation III: Pulmonary Angiogram and PET Scan
Pulmonary Angiogram
A Pulmonary Angiogram is an invasive procedure involving injecting a contrast medium through a catheter threaded into the pulmonary artery or the right side of the heart to visualize the pulmonary vasculature. Computed Tomography (CT) scans have mainly replaced this...
01:25Imaging Studies II: Positron Emission Tomography and Scintigraphy
Fundamental Principles of PET