Chuxi Huang1, Wenhui Lv2, Changsheng Zhou1, Li Mao3, Qinmei Xu1, Xinyu Li2, Li Qi1, Fei Xia1, Xiuli Li3, Qirui Zhang2, Longjiang Zhang1,2, Guangming Lu4,5. 1. Department of Medical Imaging, Jinling Hospital, Nanjing University School of Medicine, No.305, Zhongshan East Road, Nanjing, 210002, China. 2. Department of Medical Imaging, Jinling Hospital, Southern Medical University, No.305, Zhongshan East Road, Nanjing, 210002, China. 3. Deepwise AI Lab, Deepwise Inc, No.8, Haidian Avenue, Beijing, 100080, China. 4. Department of Medical Imaging, Jinling Hospital, Nanjing University School of Medicine, No.305, Zhongshan East Road, Nanjing, 210002, China. cjr.luguangming@vip.163.com. 5. Department of Medical Imaging, Jinling Hospital, Southern Medical University, No.305, Zhongshan East Road, Nanjing, 210002, China. cjr.luguangming@vip.163.com.
Abstract
OBJECTIVES: To develop and validate a deep learning model to discriminate transient from persistent subsolid nodules (SSNs) on baseline CT. METHODS: A cohort of 1414 SSNs, consisting of 319 transient SSNs in 168 individuals and 1095 persistent SSNs in 816 individuals, were identified on chest CT. The cohort was assigned by examination date into a development set of 996 SSNs, a tuning set of 212 SSNs, and a validation set of 206 SSNs. Our model was built by transfer learning, which was transferred from a well-performed deep learning model for pulmonary nodule classification. The performance of the model was compared with that of two experienced radiologists. Each nodule was categorized by Lung CT Screening Reporting and Data System (Lung-RADS) to further evaluate the performance and the potential clinical benefit of the model. Two methods were employed to visualize the learned features. RESULTS: Our model achieved an AUC of 0.926 on the validation set with an accuracy of 0.859, a sensitivity of 0.863, and a specificity of 0.858, and outperformed the radiologists. The model performed the best among Lung-RADS 2 nodules and maintained well performance among Lung-RADS 4 nodules. Feature visualization demonstrated the model's effectiveness in extracting features from images. CONCLUSIONS: The transfer learning model presented good performance on the discrimination between transient and persistent SSNs. A reliable diagnosis on nodule persistence can be achieved at baseline CT; thus, an early diagnosis as well as better patient care is available. KEY POINTS: • Deep learning can be used for the discrimination between transient and persistent subsolid nodules. • A transfer learning model can achieve good performance when it is transferred from a model with a similar task. • With the assistance of deep learning model, a reliable diagnosis on nodule persistence can be achieved at baseline CT, which can bring a better patient care strategy.
OBJECTIVES: To develop and validate a deep learning model to discriminate transient from persistent subsolid nodules (SSNs) on baseline CT. METHODS: A cohort of 1414 SSNs, consisting of 319 transient SSNs in 168 individuals and 1095 persistent SSNs in 816 individuals, were identified on chest CT. The cohort was assigned by examination date into a development set of 996 SSNs, a tuning set of 212 SSNs, and a validation set of 206 SSNs. Our model was built by transfer learning, which was transferred from a well-performed deep learning model for pulmonary nodule classification. The performance of the model was compared with that of two experienced radiologists. Each nodule was categorized by Lung CT Screening Reporting and Data System (Lung-RADS) to further evaluate the performance and the potential clinical benefit of the model. Two methods were employed to visualize the learned features. RESULTS: Our model achieved an AUC of 0.926 on the validation set with an accuracy of 0.859, a sensitivity of 0.863, and a specificity of 0.858, and outperformed the radiologists. The model performed the best among Lung-RADS 2 nodules and maintained well performance among Lung-RADS 4 nodules. Feature visualization demonstrated the model's effectiveness in extracting features from images. CONCLUSIONS: The transfer learning model presented good performance on the discrimination between transient and persistent SSNs. A reliable diagnosis on nodule persistence can be achieved at baseline CT; thus, an early diagnosis as well as better patient care is available. KEY POINTS: • Deep learning can be used for the discrimination between transient and persistent subsolid nodules. • A transfer learning model can achieve good performance when it is transferred from a model with a similar task. • With the assistance of deep learning model, a reliable diagnosis on nodule persistence can be achieved at baseline CT, which can bring a better patient care strategy.
Entities:
Keywords:
Deep learning; Diagnosis, computer-assisted; Lung; Tomography, X-ray computed
Authors: Sang Min Lee; Chang Min Park; Jin Mo Goo; Chang Hyun Lee; Hyun Ju Lee; Kwang Gi Kim; Mi-Jin Kang; In Sun Lee Journal: Radiology Date: 2010-02-19 Impact factor: 11.105
Authors: Heber MacMahon; David P Naidich; Jin Mo Goo; Kyung Soo Lee; Ann N C Leung; John R Mayo; Atul C Mehta; Yoshiharu Ohno; Charles A Powell; Mathias Prokop; Geoffrey D Rubin; Cornelia M Schaefer-Prokop; William D Travis; Paul E Van Schil; Alexander A Bankier Journal: Radiology Date: 2017-02-23 Impact factor: 11.105
Authors: Chang Min Park; Jin Mo Goo; Hyun Ju Lee; Chang Hyun Lee; Eun Ju Chun; Jung-Gi Im Journal: Radiographics Date: 2007 Mar-Apr Impact factor: 5.333
Authors: L Felix; G Serra-Tosio; S Lantuejoul; J F Timsit; D Moro-Sibilot; C Brambilla; G R Ferretti Journal: Eur J Radiol Date: 2009-10-04 Impact factor: 3.528
Authors: Michael K Gould; Jessica Donington; William R Lynch; Peter J Mazzone; David E Midthun; David P Naidich; Renda Soylemez Wiener Journal: Chest Date: 2013-05 Impact factor: 9.410