Implementation of artificial intelligence in the histological assessment of pulmonary subsolid nodules

doi:10.21037/tlcr-21-971

	Implementation of artificial intelligence in the histological assessment of pulmonary subsolid nodules
	Deng, Jiajun 1; Zhao, Mengmeng 1; Li, Qiuyuan 1; Zhang, Yikai2 ; Ma, Minjie 3; Li, Chuanyi 4; Wang, Jun 5; She, Yunlang 1; Jiang, Yan 1; Zhang, Yunzeng 6; Wang, Tingting 7; Wu, Chunyan 8; Hou, Likun 8; Zhong, Sheng 9; Jin, Shengxi 10; Qian, Dahong 5; Xie, Dong 1; Zhu, Yuming 1; Tandon, Yasmeen K.11; Snoeckx, Annemiek 12,13,14; Jin, Feng 15; Yu, Bentong 16; Zhao, Guofang 17,18; Chen, Chang 1,3,19
	2021-12-01
发表期刊	TRANSLATIONAL LUNG CANCER RESEARCH (IF:4.0[JCR-2023],4.3[5-Year])
ISSN	2218-6751
EISSN	2226-4477
发表状态	已发表
DOI	10.21037/tlcr-21-971
摘要	Background: Clinical management of subsolid nodules (SSNs) is defined by the suspicion of tumor invasiveness. We sought to develop an artificial intelligent (AI) algorithm for invasiveness assessment of lung adenocarcinoma manifesting as radiological SSNs. We investigated the performance of this algorithm in classification of SSNs related to invasiveness. Methods: A retrospective chest computed tomography (CT) dataset of 1,589 SSNs was constructed to develop (85%) and internally test (15%) the proposed AI diagnostic tool, SSNet. Diagnostic performance was evaluated in the hold-out test set and was further tested in an external cohort of 102 SSNs. Three thoracic surgeons and three radiologists were required to evaluate the invasiveness of SSNs on both test datasets to investigate the clinical utility of the proposed SSNet. Results: In the differentiation of invasive adenocarcinoma (IA), SSNet achieved a similar area under the curve [AUC; 0.914, 95% confidence interval (CI): 0.813-0.987] with that of the 6 doctors (0.900, 95% CI: 0.867-0.922). When interpreting with the assistance of SSNet, the sensitivity of junior doctors, specificity of senior doctor, and their accuracy were significantly improved. In the external test, SSNet (AUC: 0.949, 95% CI: 0.884-1.000) achieved a better AUC than doctors (AUC: 0.883, 95% CI: 0.826-0.939) whose AUC increased (AUC: 0.908: 95% CI: 0.847-0.982) with SSNet assistance. In the histological subtype classifications, SSNet achieved better performance than practicing doctors. The AUCs of doctors were significantly improved with the assistance of SSNet in both 4-category and 3-category classifications to 0.836 (95% CI: 0.811-0.862) and 0.852 (95% CI: 0.825-0.882), respectively. Conclusions: The AI diagnostic system achieved non-inferior performance to doctors, and will potentially improve diagnostic performance and efficiency in SSN evaluation.
关键词	Artificial intelligence (AI) pulmonary subsolid nodules (SSNs) lung adenocarcinoma computed tomography (CT)
URL	查看原文
收录类别	SCI ; SCIE
语种	英语
资助项目	National Natural Science Foundation of China[8210071009] ; Shanghai Science and Technology Commission[21YF1438200] ; Shanghai Municipal Health Commission[2019SY072] ; Science-Technology Foundation for Young Scientists of Gansu Province["18JR3RA305","21JR1RA107"] ; Natural Science Foundation of Gansu Province["21JR1RA118","21JR1RA092"]
WOS研究方向	Oncology ; Respiratory System
WOS类目	Oncology ; Respiratory System
WOS记录号	WOS:000738997700001
出版者	AME PUBL CO
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/148749
专题	信息科学与技术学院_本科生生物医学工程学院
通讯作者	Jin, Feng; Yu, Bentong; Zhao, Guofang; Chen, Chang
作者单位	1.Tongji Univ, Dept Thorac Surg, Shanghai Pulm Hosp, Sch Med, 507 Zhengmin Rd, Shanghai 200433, Peoples R China 2.ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai, Peoples R China 3.Lanzhou Univ, Hosp 1, Dept Thorac Surg, Lanzhou, Peoples R China 4.Nantong 6 Peoples Hosp, Dept Thorac Surg, Nantong, Peoples R China 5.Shanghai Jiao Tong Univ, Sch Biomed Engn, Shanghai, Peoples R China 6.Shandong Publ Hlth Clin Ctr, Dept Thorac Surg, Jinan, Peoples R China 7.Tongji Univ, Shanghai Pulm Hosp, Dept Radiol, Sch Med, Shanghai, Peoples R China 8.Tongji Univ, Shanghai Pulm Hosp, Dept Pathol, Sch Med, Shanghai, Peoples R China 9.Tailai Biosci Inc, Shenzhen, Peoples R China 10.Dianei Technol, Shanghai, Peoples R China 11.Mayo Clin, Dept Radiol, Rochester, MN USA 12.Antwerp Univ Hosp, Dept Radiol, Edegem, Belgium 13.Univ Antwerp, Edegem, Belgium 14.Univ Antwerp, Fac Med & Hlth Sci, Antwerp, Belgium 15.Shandong Univ, Shandong Prov Chest Hosp, Cheeloo Coll Med, Prov Key Lab Resp Infect Dis Shandong, 46 Lishan Rd, Jinan 250013, Peoples R China 16.Nanchang Univ, Affiliated Hosp 1, Dept Thorac Surg, 17 Yongwaizheng St, Nanchang 330006, Jiangxi, Peoples R China 17.Univ Chinese Acad Sci, Hwa Mei Hosp, Dept Cardiothorac Surg, 41 Xibei St, Ningbo 315000, Peoples R China 18.Univ Chinese Acad Sci, Ningbo Inst Life & Hlth Ind, Ningbo, Peoples R China 19.Int Sci & Technol Cooperat Base Dev & Applicat Ke, Lanzhou, Peoples R China
推荐引用方式 GB/T 7714	Deng, Jiajun,Zhao, Mengmeng,Li, Qiuyuan,et al. Implementation of artificial intelligence in the histological assessment of pulmonary subsolid nodules[J]. TRANSLATIONAL LUNG CANCER RESEARCH,2021.
APA	Deng, Jiajun.,Zhao, Mengmeng.,Li, Qiuyuan.,Zhang, Yikai.,Ma, Minjie.,...&Chen, Chang.(2021).Implementation of artificial intelligence in the histological assessment of pulmonary subsolid nodules.TRANSLATIONAL LUNG CANCER RESEARCH.
MLA	Deng, Jiajun,et al."Implementation of artificial intelligence in the histological assessment of pulmonary subsolid nodules".TRANSLATIONAL LUNG CANCER RESEARCH (2021).