林天武 吳佩琪
【摘要】 隨著計算機斷層掃描在肺癌篩查中的廣泛應用,孤立性肺結節的發現率較以往顯著上升,但其良惡性鑒別和侵襲性評估等仍是近年來胸部影像學研究的熱點及難點。影像組學可以從醫學影像圖像中高通量地提取并分析大量高級且定量的影像學特征,對疾病的良惡性定性診斷、分期、預后預測、療效評價等具有重要價值。本文介紹了孤立性肺結節的傳統CT特征和影像組學基本流程,并對影像組學在孤立性肺結節的良惡性鑒別、侵襲性評估等方面的研究進展進行綜述。
【關鍵詞】 計算機斷層掃描; 影像組學; 孤立性肺結節; 人工智能
Advances of Radiomics Research Based on Computed Tomography in Solitary Pulmonary Nodules/LIN Tianwu,WU Peiqi.//Medical Innovation of China,2019,16(21):-172
【Abstract】 With the wide application of computed tomography(CT)in lung cancer screening,the discovery rate of solitary pulmonary nodules is significantly higher than before,but its benign and malignant identification and invasiveness evaluation are still hot and difficult topic in chest imaging research in recent years.Radiomics can extract and analyze a large number of high-level and quantitative imaging features from medical image images,which is of great value for qualitative diagnosis,staging,prognosis prediction and therapeutic evaluation of diseases.This article introduces the traditional CT features of solitary pulmonary nodules and the basic flow of radiomics,then reviews the research progress of radiomics in the benign and malignant identification and invasiveness evaluation of solitary pulmonary nodules.
【Key words】 Computed tomography; Radiomics; Solitary pulmonary nodules; Artificial intelligence
First-authors address:Shenzhen Seventh Peoples Hospital,Shenzhen 518081,China
doi:10.3969/j.issn.1674-4985.2019.21.043
隨著計算機斷層掃描(computed tomography,CT),尤其是低劑量CT在肺癌篩查中的廣泛應用,孤立性肺結節(solitary pulmonary nodules,SPN)的發現率較以往顯著上升[1],通過基于CT的影像組學技術對孤立性肺結節進行診斷和評估已成為國內外研究的熱點。影像組學(radiomics)是指從醫學影像圖像中高通量地提取并分析大量高級且定量的影像學特征,對疾病的良惡性定性診斷、分期、預后預測、療效評價等具有重要價值[2]。本文基于CT的影像組學在孤立性肺結節中的研究進展進行綜述。
1 孤立性肺結節的定義及其影像檢查方法
根據Fleischner學會的定義[3],孤立性肺結節是指X線片或CT片上肺實質內單發、圓形或類圓形、邊界清晰或不清晰、直徑≤3 cm的不透明病灶,不伴有肺不張、衛星病灶、肺門或縱隔淋巴結腫大及胸腔積液。SPN的病理類型主要包括肺部腫瘤性病變(惡性腫瘤、良性腫瘤)、感染性病變、非感染性病變、先天性疾病等?!?br>