|
|||||
|
|
| 人工智能在肺结节良恶性鉴别诊断中的价值分析 | |
| 引用本文： | 南岩东,李玉娟,刘苗苗,金发光,张涛. 人工智能在肺结节良恶性鉴别诊断中的价值分析[J]. 中华肺部疾病杂志(电子版), 2020, 13(6): 760-763. DOI: 10.3877/cma.j.issn.1674-6902.2020.06.009 |
| 作者姓名： | 南岩东 李玉娟 刘苗苗 金发光 张涛 |
| 作者单位： | 1. 710038 西安,空军（第四）军医大学唐都医院呼吸与危重症医学科 |
| 基金项目： | 陕西省重点研发计划(2019SF-009) |
| 摘 要： | 目的评价人工智能(artificial intelligence, AI)风险评估对肺结节良恶性鉴别诊断的价值。 方法收集2018年8月至2019年12月唐都医院行胸部CT检查,发现肺结节患者310例,将患者CT影像数据DICOM文件拷贝输入到"FACT人工智能"软件系统对结节进行分析,获得结节的部位、数量、特征(磨玻璃、亚实性、实性)、大小、密度、以及恶性风险概率AI值和Lung-rads分级;其中39例肺结节经过多学科讨论,建议采用外科手术、经皮肺穿刺或者支气管镜下活检等,271例患者进行随访。 结果31例肺结节病理诊断良性14例,分别为结核8例,隐球菌2例,炎性结节4例;恶性25例,分别肺鳞癌2例,腺癌23例。进一步分析,恶性病变的AI风险概率明显高于良性病变(P<0.05);结节AI风险概率与肺结节特点(磨玻璃、亚实性、实性)显著相关(P<0.05),而与数量及边缘毛刺征无显著相关性(P>0.05);肺结节特点(磨玻璃、亚实性、实性)在良恶性之间存在显著性差异(P<0.05),而密度和体积之间在在良恶性之间无显著性差异(P>0.05)。肺结节Lung-rads分级与AI风险概率之间具有显著的相关性(P<0.05)。 结论依据人工智能自动分析良恶性概率AI值对肺结节良恶性鉴别诊断具有一定的价值,值得临床借鉴。 |
| 关 键 词： | 人工智能 肺结节 支气管肺癌 早期诊断 |
| 收稿时间： | 2020-05-07 |
Analysis of the value of artificial intelligence in differential diagnosis of benign and malignant pulmonary nodules |
|
| Yandong Nan,Yujuan Li,Miaomiao Liu,Faguang Jin,Tao Zhang. Analysis of the value of artificial intelligence in differential diagnosis of benign and malignant pulmonary nodules[J]. Chinese Journal of lung Disease（Electronic Edition）, 2020, 13(6): 760-763. DOI: 10.3877/cma.j.issn.1674-6902.2020.06.009 | |
| Authors: | Yandong Nan Yujuan Li Miaomiao Liu Faguang Jin Tao Zhang |
| Affiliation: | 1. Department of Respiratory and Critical Care Medicine, Tangdu Hospital, Air Force Military Medical University, 710038, China |
| Abstract: | ObjectiveTo evaluate the value of risk assessment of artificial intelligence (AI) in the differential diagnosis of benign and malignant pulmonary nodules. MethodsAll of 310 patients with pulmonary nodules by the Chest CT examination in Tangdu Hospital from August 2018 to December 2019 were collected in this study. A copy of the patient′s CT image with DICOM format was input into the "FACT artificial intelligence" software system to and the pulmonary nodules was analyzed. The pulmonary nodules characteristics, including the location, quantity, featutes (ground glass, subsolid and solid), size, density and AI values and Lung-rads grade were obtained. After multidisciplinary discussion, 39 cases of pulmonary nodules were suggested to be diagnosed by surgery, percutaneous lung puncture or bronchoscopic biopsy and 271 patients were followed up. ResultsAmong 31 cases of pulmonary nodules, 14 cases were benign, including tuberculosis (8 cases), cryptococci (2 cases), inflammatory nodule (4 cases), and 25 cases were malignant, including squamous cell carcinoma (2 cases) and adenocarcinoma (23 cases). Further analysis showed that the AI risk probability of malignant lesions was significantly higher than that of benign lesions (P>0.05), and the AI risk probability of nodules was significantly correlated with the characteristics of pulmonary nodules (ground glass, subsolid and solid) (P>0.05), but not with the numbers and the marginal burr sign (P>0.05). There were significant differences in the characteristics of pulmonary nodules (ground glass, subsolid, and solid) between benign and malignant (P<0.05), but there was no significant difference in density or volume between benign and malignant (P>0.05). In addition, Lung-rads grade significantly correlated with AI risk probability of pulmonary nodules (P<0.05). ConclusionThe automatic analysis of benign and malignant probability of pulmonary based on AI has a certain value in the differential diagnosis of pulmonary nodules and could be used in clinic. |
| Keywords: | Artificial intelligence Lung nodules Lung cancer Early diagnosis |
| 点击此处可从《中华肺部疾病杂志(电子版)》浏览原始摘要信息 | |
| 点击此处可从《中华肺部疾病杂志(电子版)》下载全文 | |