| 人工智能CT定量分析预测并评估COVID-19肺炎临床分型的研究 |
| |
| 引用本文： | 刘力,陈宏,钟威,魏冬梅,宋永丽,李慧鑫,周昕,高晓隆.人工智能CT定量分析预测并评估COVID-19肺炎临床分型的研究[J].CT理论与应用研究,2021,30(6):743-751. |
| |
| 作者姓名： | 刘力 陈宏 钟威 魏冬梅 宋永丽 李慧鑫 周昕 高晓隆 |
| |
| 作者单位： | 1. 齐齐哈尔市第一医院 CRT 临床研发小组, 黑龙江 齐齐哈尔 161005; |
| |
| 基金项目： | 齐齐哈尔市科技局社会发展攻关指令项目（Th22细胞与系统性红斑狼疮肾脏损伤的关系及机制研究（SFGG-201924））。 |
| |
| 摘 要： | 目的:评价人工智能CT定量分析预测并评估COVID-19肺炎临床分型的相关性。方法:回顾性分析齐齐哈尔第一医院发热门诊收治2020年2月1日至2021年1月20日COVID-19确诊患者46例的临床及CT影像资料。比较人工智能（AI）定量分析中病灶累及全肺感染体积、磨玻璃密度体积（GGO体积）和实性密度体积（SO体积）与临床分型的相关性。结果:普通型26例、重型16例和危重型4例，临床表现以发热、咳嗽、乏力症状为主。重型和危重型更常见于年龄较大患者。3种临床分型肺部病变的CT表现均以GGO为主；普通型的全肺感染体积、GGO体积、SO体积比重型/危重型患者小，Spearman等级相关性分析显示全肺感染体积、GGO体积、SO体积均与临床分型具有显著相关（0.86、0.87和0.84）。结论:人工智能CT定量指标分析（感染体积、GGO体积、SO体积）与COVID-19肺炎临床分型具有较好的相关性。
|
| 关 键 词： | 新型冠状病毒肺炎 CT 人工智能 临床分型 |
| 收稿时间： | 2021-06-21 |
Study on Predicting and Evaluating Clinical Classification of COVID-19 Pneumonia by Artificial Intelligence CT Quantitative Analysis |
| |
| Institution: | 1. Clinical Research Team, The First Hospital of Qiqihar, Qiqihar 161005, China;2. Hangzhou Yitu Medical Technology Co, Ltd. Hangzhou 310024, China;3. School of Medicine and Technology, Qiqihar Medical University, Qiqihar 161000, China |
| |
| Abstract: | Objective: To evaluate the correlation of CT artificial intelligence quantitative analysis in prediction and evaluation of clinical classification of COVID-19 pneumonia. Methods: The clinical and CT imaging data of 46 patients with COVID-19 treated in the hospital from February 1st, 2019 to January 20th, 2021 was retrospectively analyzed. We compared the correlation between the total lung infection volume, grinding glass density volume (GGO volume), solid density volume (SO volume) and clinical classification when artificial intelligence (AI) quantitative analysis was applied. Results: Among the 26 cases of common type, 16 cases of severe type and 4 cases of critical type, the main clinical manifestations were fever, cough and fatigue. Severe and critical types were more common in elder patients. The CT manifestations of three clinical types of pulmonary lesions were mainly GGO; total lung infection volume, GGO volume, SO volume in common type were smaller than that in patients of severe/critical type. Spearman grade correlation analysis showed significant correlation between total lung infection volume, GGO volume, and SO volume with clinical classification (0.86, 0.87, 0.84). Conclusion: The artificial intelligence CT quantitative index analysis (infection volume, GGO volume, SO volume) holds much correlation with clinical classification of COVID-19 pneumonia. |
| |
| Keywords: | |
|
| 点击此处可从《CT理论与应用研究》浏览原始摘要信息 |
| 点击此处可从《CT理论与应用研究》下载免费的PDF全文 |
|
