1
|
Pan Z, Hu G, Zhu Z, Tan W, Han W, Zhou Z, Song W, Yu Y, Song L, Jin Z. Predicting Invasiveness of Lung Adenocarcinoma at Chest CT with Deep Learning Ternary Classification Models. Radiology 2024; 311:e232057. [PMID: 38591974 DOI: 10.1148/radiol.232057] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/10/2024]
Abstract
Background Preoperative discrimination of preinvasive, minimally invasive, and invasive adenocarcinoma at CT informs clinical management decisions but may be challenging for classifying pure ground-glass nodules (pGGNs). Deep learning (DL) may improve ternary classification. Purpose To determine whether a strategy that includes an adjudication approach can enhance the performance of DL ternary classification models in predicting the invasiveness of adenocarcinoma at chest CT and maintain performance in classifying pGGNs. Materials and Methods In this retrospective study, six ternary models for classifying preinvasive, minimally invasive, and invasive adenocarcinoma were developed using a multicenter data set of lung nodules. The DL-based models were progressively modified through framework optimization, joint learning, and an adjudication strategy (simulating a multireader approach to resolving discordant nodule classifications), integrating two binary classification models with a ternary classification model to resolve discordant classifications sequentially. The six ternary models were then tested on an external data set of pGGNs imaged between December 2019 and January 2021. Diagnostic performance including accuracy, specificity, and sensitivity was assessed. The χ2 test was used to compare model performance in different subgroups stratified by clinical confounders. Results A total of 4929 nodules from 4483 patients (mean age, 50.1 years ± 9.5 [SD]; 2806 female) were divided into training (n = 3384), validation (n = 579), and internal (n = 966) test sets. A total of 361 pGGNs from 281 patients (mean age, 55.2 years ± 11.1 [SD]; 186 female) formed the external test set. The proposed strategy improved DL model performance in external testing (P < .001). For classifying minimally invasive adenocarcinoma, the accuracy was 85% and 79%, sensitivity was 75% and 63%, and specificity was 89% and 85% for the model with adjudication (model 6) and the model without (model 3), respectively. Model 6 showed a relatively narrow range (maximum minus minimum) across diagnostic indexes (accuracy, 1.7%; sensitivity, 7.3%; specificity, 0.9%) compared with the other models (accuracy, 0.6%-10.8%; sensitivity, 14%-39.1%; specificity, 5.5%-17.9%). Conclusion Combining framework optimization, joint learning, and an adjudication approach improved DL classification of adenocarcinoma invasiveness at chest CT. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Sohn and Fields in this issue.
Collapse
Affiliation(s)
- Zhengsong Pan
- From the Department of Radiology (Z.P., Z. Zhu, W.S., L.S., Z.J.), Medical Research Center (G.H.), State Key Laboratory of Complex Severe and Rare Disease (G.H.), Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, No. 1 Shuaifuyuan, Dongcheng District, Beijing 100730, China; 4 + 4 Medical Doctor Program (Z.P., Z. Zhu), Department of Epidemiology and Health Statistics (W.H.), Institute of Basic Medicine Sciences (W.H.), Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China; Deepwise AI Laboratory, Beijing Deepwise & League of PhD Technology, Beijing, China (W.T., Z. Zhou, Y.Y.); and Department of Computer Science, The University of Hong Kong, Hong Kong, China (Y.Y.)
| | - Ge Hu
- From the Department of Radiology (Z.P., Z. Zhu, W.S., L.S., Z.J.), Medical Research Center (G.H.), State Key Laboratory of Complex Severe and Rare Disease (G.H.), Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, No. 1 Shuaifuyuan, Dongcheng District, Beijing 100730, China; 4 + 4 Medical Doctor Program (Z.P., Z. Zhu), Department of Epidemiology and Health Statistics (W.H.), Institute of Basic Medicine Sciences (W.H.), Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China; Deepwise AI Laboratory, Beijing Deepwise & League of PhD Technology, Beijing, China (W.T., Z. Zhou, Y.Y.); and Department of Computer Science, The University of Hong Kong, Hong Kong, China (Y.Y.)
| | - Zhenchen Zhu
- From the Department of Radiology (Z.P., Z. Zhu, W.S., L.S., Z.J.), Medical Research Center (G.H.), State Key Laboratory of Complex Severe and Rare Disease (G.H.), Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, No. 1 Shuaifuyuan, Dongcheng District, Beijing 100730, China; 4 + 4 Medical Doctor Program (Z.P., Z. Zhu), Department of Epidemiology and Health Statistics (W.H.), Institute of Basic Medicine Sciences (W.H.), Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China; Deepwise AI Laboratory, Beijing Deepwise & League of PhD Technology, Beijing, China (W.T., Z. Zhou, Y.Y.); and Department of Computer Science, The University of Hong Kong, Hong Kong, China (Y.Y.)
| | - Weixiong Tan
- From the Department of Radiology (Z.P., Z. Zhu, W.S., L.S., Z.J.), Medical Research Center (G.H.), State Key Laboratory of Complex Severe and Rare Disease (G.H.), Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, No. 1 Shuaifuyuan, Dongcheng District, Beijing 100730, China; 4 + 4 Medical Doctor Program (Z.P., Z. Zhu), Department of Epidemiology and Health Statistics (W.H.), Institute of Basic Medicine Sciences (W.H.), Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China; Deepwise AI Laboratory, Beijing Deepwise & League of PhD Technology, Beijing, China (W.T., Z. Zhou, Y.Y.); and Department of Computer Science, The University of Hong Kong, Hong Kong, China (Y.Y.)
| | - Wei Han
- From the Department of Radiology (Z.P., Z. Zhu, W.S., L.S., Z.J.), Medical Research Center (G.H.), State Key Laboratory of Complex Severe and Rare Disease (G.H.), Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, No. 1 Shuaifuyuan, Dongcheng District, Beijing 100730, China; 4 + 4 Medical Doctor Program (Z.P., Z. Zhu), Department of Epidemiology and Health Statistics (W.H.), Institute of Basic Medicine Sciences (W.H.), Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China; Deepwise AI Laboratory, Beijing Deepwise & League of PhD Technology, Beijing, China (W.T., Z. Zhou, Y.Y.); and Department of Computer Science, The University of Hong Kong, Hong Kong, China (Y.Y.)
| | - Zhen Zhou
- From the Department of Radiology (Z.P., Z. Zhu, W.S., L.S., Z.J.), Medical Research Center (G.H.), State Key Laboratory of Complex Severe and Rare Disease (G.H.), Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, No. 1 Shuaifuyuan, Dongcheng District, Beijing 100730, China; 4 + 4 Medical Doctor Program (Z.P., Z. Zhu), Department of Epidemiology and Health Statistics (W.H.), Institute of Basic Medicine Sciences (W.H.), Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China; Deepwise AI Laboratory, Beijing Deepwise & League of PhD Technology, Beijing, China (W.T., Z. Zhou, Y.Y.); and Department of Computer Science, The University of Hong Kong, Hong Kong, China (Y.Y.)
| | - Wei Song
- From the Department of Radiology (Z.P., Z. Zhu, W.S., L.S., Z.J.), Medical Research Center (G.H.), State Key Laboratory of Complex Severe and Rare Disease (G.H.), Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, No. 1 Shuaifuyuan, Dongcheng District, Beijing 100730, China; 4 + 4 Medical Doctor Program (Z.P., Z. Zhu), Department of Epidemiology and Health Statistics (W.H.), Institute of Basic Medicine Sciences (W.H.), Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China; Deepwise AI Laboratory, Beijing Deepwise & League of PhD Technology, Beijing, China (W.T., Z. Zhou, Y.Y.); and Department of Computer Science, The University of Hong Kong, Hong Kong, China (Y.Y.)
| | - Yizhou Yu
- From the Department of Radiology (Z.P., Z. Zhu, W.S., L.S., Z.J.), Medical Research Center (G.H.), State Key Laboratory of Complex Severe and Rare Disease (G.H.), Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, No. 1 Shuaifuyuan, Dongcheng District, Beijing 100730, China; 4 + 4 Medical Doctor Program (Z.P., Z. Zhu), Department of Epidemiology and Health Statistics (W.H.), Institute of Basic Medicine Sciences (W.H.), Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China; Deepwise AI Laboratory, Beijing Deepwise & League of PhD Technology, Beijing, China (W.T., Z. Zhou, Y.Y.); and Department of Computer Science, The University of Hong Kong, Hong Kong, China (Y.Y.)
| | - Lan Song
- From the Department of Radiology (Z.P., Z. Zhu, W.S., L.S., Z.J.), Medical Research Center (G.H.), State Key Laboratory of Complex Severe and Rare Disease (G.H.), Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, No. 1 Shuaifuyuan, Dongcheng District, Beijing 100730, China; 4 + 4 Medical Doctor Program (Z.P., Z. Zhu), Department of Epidemiology and Health Statistics (W.H.), Institute of Basic Medicine Sciences (W.H.), Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China; Deepwise AI Laboratory, Beijing Deepwise & League of PhD Technology, Beijing, China (W.T., Z. Zhou, Y.Y.); and Department of Computer Science, The University of Hong Kong, Hong Kong, China (Y.Y.)
| | - Zhengyu Jin
- From the Department of Radiology (Z.P., Z. Zhu, W.S., L.S., Z.J.), Medical Research Center (G.H.), State Key Laboratory of Complex Severe and Rare Disease (G.H.), Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, No. 1 Shuaifuyuan, Dongcheng District, Beijing 100730, China; 4 + 4 Medical Doctor Program (Z.P., Z. Zhu), Department of Epidemiology and Health Statistics (W.H.), Institute of Basic Medicine Sciences (W.H.), Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China; Deepwise AI Laboratory, Beijing Deepwise & League of PhD Technology, Beijing, China (W.T., Z. Zhou, Y.Y.); and Department of Computer Science, The University of Hong Kong, Hong Kong, China (Y.Y.)
| |
Collapse
|
2
|
Fu G, Yu H, Liu J, Xia T, Xiang L, Li P, Huang D, Lin L, Zhuang Y, Yang Y. Arc concave sign on thin-section computed tomography:A novel predictor for invasive pulmonary adenocarcinoma in pure ground-glass nodules. Eur J Radiol 2021; 139:109683. [PMID: 33836337 DOI: 10.1016/j.ejrad.2021.109683] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/30/2020] [Revised: 03/01/2021] [Accepted: 03/23/2021] [Indexed: 12/24/2022]
Abstract
OBJECTIVE We aimed to investigate the risk factors of invasive pulmonary adenocarcinoma, especially to report and validate the use of our newly identified arc concave sign in predicting invasiveness of pure ground-glass nodules (pGGNs). METHODS From January 2015 to August 2018, we retrospectively enrolled 302 patients with 306 pGGNs ≤ 20 mm pathologically confirmed (141 preinvasive lesions and 165 invasive lesions). Arc concave sign was defined as smooth and sunken part of the edge of the lesion on thin-section computed tomography (TSCT). The degree of arc concave sign was expressed by the arc chord distance to chord length ratio (AC-R); deep arc concave sign was defined as AC-R larger than the optimal cut-off value. Logistic regression analysis was used to identify the independent risk factors of invasiveness. RESULTS Arc concave sign was observed in 65 of 306 pGGNs (21.2 %), and deep arc concave sign (AC-R > 0.25) were more common in invasive lesions (P = 0.008). Under microscope, interlobular septal displacements were found at tumour surface. Multivariate analysis indicated that irregular shape (OR, 3.558; CI: 1.374-9.214), presence of deep arc concave sign (OR, 3.336; CI: 1.013-10.986), the largest diameter > 10.1 mm (OR, 4.607; CI: 2.584-8.212) and maximum density > -502 HU (OR, 6.301; CI: 3.562-11.148) were significant independent risk factors of invasive lesions. CONCLUSIONS Arc concave sign on TSCT is caused by interlobular septal displacement. The degree of arc concave sign can reflect the invasiveness of pGGNs. Invasive lesions can be effectively distinguished from preinvasive lesions by the presence of deep arc concave sign, irregular shape, the largest diameter > 10.1 mm and maximum density > -502 HU in pGGNs ≤ 20 mm.
Collapse
Affiliation(s)
- Gangze Fu
- Depatment of Radiology, The First Affiliated Hospital of Wenzhou Medical University, NO.2 Fuxue Rd, Wenzhou, 325000, China
| | - Huibo Yu
- Department of Radiology, Xiangshan Affiliated Hospital of Wenzhou Medical University, Xiangshan, 315700, China
| | - Jinjin Liu
- Depatment of Radiology, The First Affiliated Hospital of Wenzhou Medical University, NO.2 Fuxue Rd, Wenzhou, 325000, China
| | - Tianyi Xia
- Depatment of Radiology, The First Affiliated Hospital of Wenzhou Medical University, NO.2 Fuxue Rd, Wenzhou, 325000, China
| | - Lanting Xiang
- Depatment of Pathology, The First Affiliated Hospital of Wenzhou Medical University, NO.2 Fuxue Rd, Wenzhou, 325000, China
| | - Peng Li
- Depatment of Pathology, The First Affiliated Hospital of Wenzhou Medical University, NO.2 Fuxue Rd, Wenzhou, 325000, China
| | - Dingpin Huang
- Depatment of Radiology, The First Affiliated Hospital of Wenzhou Medical University, NO.2 Fuxue Rd, Wenzhou, 325000, China
| | - Liaoyi Lin
- Depatment of Radiology, The First Affiliated Hospital of Wenzhou Medical University, NO.2 Fuxue Rd, Wenzhou, 325000, China
| | - Yuandi Zhuang
- Depatment of Radiology, The First Affiliated Hospital of Wenzhou Medical University, NO.2 Fuxue Rd, Wenzhou, 325000, China
| | - Yunjun Yang
- Depatment of Radiology, The First Affiliated Hospital of Wenzhou Medical University, NO.2 Fuxue Rd, Wenzhou, 325000, China.
| |
Collapse
|
3
|
Heidinger BH, Anderson KR, Nemec U, Costa DB, Gangadharan SP, VanderLaan PA, Bankier AA. Morphologic characteristics of pulmonary adenocarcinomas manifesting as pure ground-glass nodules on CT. J Thorac Dis 2017; 9:E1148-E1150. [PMID: 29313855 DOI: 10.21037/jtd.2017.11.25] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/26/2022]
Affiliation(s)
- Benedikt H Heidinger
- Department of Radiology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, USA.,Department of Biomedical Imaging and Image-guided Therapy, Vienna General Hospital, Medical University of Vienna, Vienna, Austria
| | - Kevin R Anderson
- Department of Pathology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, USA
| | - Ursula Nemec
- Department of Radiology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, USA.,Department of Biomedical Imaging and Image-guided Therapy, Vienna General Hospital, Medical University of Vienna, Vienna, Austria
| | - Daniel B Costa
- Department of Internal Medicine, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, USA
| | - Sidhu P Gangadharan
- Department of Surgery, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, USA
| | - Paul A VanderLaan
- Department of Pathology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, USA
| | - Alexander A Bankier
- Department of Radiology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, USA
| |
Collapse
|