Incidence Lung Cancer after a Negative CT Screening in the National Lung Screening Trial: Deep Learning-Based Detection of Missed Lung Cancers
We aimed to analyse the CT examinations of the previous screening round (CT<sub>prev</sub>) in NLST participants with incidence lung cancer and evaluate the value of DL-CAD in detection of missed lung cancers. Thoracic radiologists reviewed CT<sub>prev</sub> in participants w...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-12-01
|
Series: | Journal of Clinical Medicine |
Subjects: | |
Online Access: | https://www.mdpi.com/2077-0383/9/12/3908 |
id |
doaj-f1e89a390c8c44e6a73aa01eded449eb |
---|---|
record_format |
Article |
spelling |
doaj-f1e89a390c8c44e6a73aa01eded449eb2020-12-03T00:00:09ZengMDPI AGJournal of Clinical Medicine2077-03832020-12-0193908390810.3390/jcm9123908Incidence Lung Cancer after a Negative CT Screening in the National Lung Screening Trial: Deep Learning-Based Detection of Missed Lung CancersJungheum Cho0Jihang Kim1Kyong Joon Lee2Chang Mo Nam3Sung Hyun Yoon4Hwayoung Song5Junghoon Kim6Ye Ra Choi7Kyung Hee Lee8Kyung Won Lee9Department of Radiology, Seoul National University Bundang Hospital, Seongnam-si 13620, KoreaDepartment of Radiology, Seoul National University Bundang Hospital, Seongnam-si 13620, KoreaDepartment of Radiology, Seoul National University Bundang Hospital, Seongnam-si 13620, KoreaAI Research Group, Monitor Corporation, Seoul 06628, KoreaDepartment of Radiology, Seoul National University Bundang Hospital, Seongnam-si 13620, KoreaDepartment of Radiology, Seoul National University Bundang Hospital, Seongnam-si 13620, KoreaDepartment of Radiology, Seoul National University Bundang Hospital, Seongnam-si 13620, KoreaDepartment of Radiology, Seoul Metropolitan Government-Seoul National University Boramae Medical Center, Seoul 07061, KoreaDepartment of Radiology, Seoul National University Bundang Hospital, Seongnam-si 13620, KoreaDepartment of Radiology, Seoul National University Bundang Hospital, Seongnam-si 13620, KoreaWe aimed to analyse the CT examinations of the previous screening round (CT<sub>prev</sub>) in NLST participants with incidence lung cancer and evaluate the value of DL-CAD in detection of missed lung cancers. Thoracic radiologists reviewed CT<sub>prev</sub> in participants with incidence lung cancer, and a DL-CAD analysed CT<sub>prev</sub> according to NLST criteria and the lung CT screening reporting & data system (Lung-RADS) classification. We calculated patient-wise and lesion-wise sensitivities of the DL-CAD in detection of missed lung cancers. As per the NLST criteria, 88% (100/113) of CT<sub>prev</sub> were positive and 74 of them had missed lung cancers. The DL-CAD reported 98% (98/100) of the positive screens as positive and detected 95% (70/74) of the missed lung cancers. As per the Lung-RADS classification, 82% (93/113) of CT<sub>prev</sub> were positive and 60 of them had missed lung cancers. The DL-CAD reported 97% (90/93) of the positive screens as positive and detected 98% (59/60) of the missed lung cancers. The DL-CAD made false positive calls in 10.3% (27/263) of controls, with 0.16 false positive nodules per scan (41/263). In conclusion, the majority of CT<sub>prev</sub> in participants with incidence lung cancers had missed lung cancers, and the DL-CAD detected them with high sensitivity and a limited false positive rate.https://www.mdpi.com/2077-0383/9/12/3908lung neoplasmsdeep learningcomputer-aided diagnosismultidetector computed tomographyearly detection of cancer |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jungheum Cho Jihang Kim Kyong Joon Lee Chang Mo Nam Sung Hyun Yoon Hwayoung Song Junghoon Kim Ye Ra Choi Kyung Hee Lee Kyung Won Lee |
spellingShingle |
Jungheum Cho Jihang Kim Kyong Joon Lee Chang Mo Nam Sung Hyun Yoon Hwayoung Song Junghoon Kim Ye Ra Choi Kyung Hee Lee Kyung Won Lee Incidence Lung Cancer after a Negative CT Screening in the National Lung Screening Trial: Deep Learning-Based Detection of Missed Lung Cancers Journal of Clinical Medicine lung neoplasms deep learning computer-aided diagnosis multidetector computed tomography early detection of cancer |
author_facet |
Jungheum Cho Jihang Kim Kyong Joon Lee Chang Mo Nam Sung Hyun Yoon Hwayoung Song Junghoon Kim Ye Ra Choi Kyung Hee Lee Kyung Won Lee |
author_sort |
Jungheum Cho |
title |
Incidence Lung Cancer after a Negative CT Screening in the National Lung Screening Trial: Deep Learning-Based Detection of Missed Lung Cancers |
title_short |
Incidence Lung Cancer after a Negative CT Screening in the National Lung Screening Trial: Deep Learning-Based Detection of Missed Lung Cancers |
title_full |
Incidence Lung Cancer after a Negative CT Screening in the National Lung Screening Trial: Deep Learning-Based Detection of Missed Lung Cancers |
title_fullStr |
Incidence Lung Cancer after a Negative CT Screening in the National Lung Screening Trial: Deep Learning-Based Detection of Missed Lung Cancers |
title_full_unstemmed |
Incidence Lung Cancer after a Negative CT Screening in the National Lung Screening Trial: Deep Learning-Based Detection of Missed Lung Cancers |
title_sort |
incidence lung cancer after a negative ct screening in the national lung screening trial: deep learning-based detection of missed lung cancers |
publisher |
MDPI AG |
series |
Journal of Clinical Medicine |
issn |
2077-0383 |
publishDate |
2020-12-01 |
description |
We aimed to analyse the CT examinations of the previous screening round (CT<sub>prev</sub>) in NLST participants with incidence lung cancer and evaluate the value of DL-CAD in detection of missed lung cancers. Thoracic radiologists reviewed CT<sub>prev</sub> in participants with incidence lung cancer, and a DL-CAD analysed CT<sub>prev</sub> according to NLST criteria and the lung CT screening reporting & data system (Lung-RADS) classification. We calculated patient-wise and lesion-wise sensitivities of the DL-CAD in detection of missed lung cancers. As per the NLST criteria, 88% (100/113) of CT<sub>prev</sub> were positive and 74 of them had missed lung cancers. The DL-CAD reported 98% (98/100) of the positive screens as positive and detected 95% (70/74) of the missed lung cancers. As per the Lung-RADS classification, 82% (93/113) of CT<sub>prev</sub> were positive and 60 of them had missed lung cancers. The DL-CAD reported 97% (90/93) of the positive screens as positive and detected 98% (59/60) of the missed lung cancers. The DL-CAD made false positive calls in 10.3% (27/263) of controls, with 0.16 false positive nodules per scan (41/263). In conclusion, the majority of CT<sub>prev</sub> in participants with incidence lung cancers had missed lung cancers, and the DL-CAD detected them with high sensitivity and a limited false positive rate. |
topic |
lung neoplasms deep learning computer-aided diagnosis multidetector computed tomography early detection of cancer |
url |
https://www.mdpi.com/2077-0383/9/12/3908 |
work_keys_str_mv |
AT jungheumcho incidencelungcancerafteranegativectscreeninginthenationallungscreeningtrialdeeplearningbaseddetectionofmissedlungcancers AT jihangkim incidencelungcancerafteranegativectscreeninginthenationallungscreeningtrialdeeplearningbaseddetectionofmissedlungcancers AT kyongjoonlee incidencelungcancerafteranegativectscreeninginthenationallungscreeningtrialdeeplearningbaseddetectionofmissedlungcancers AT changmonam incidencelungcancerafteranegativectscreeninginthenationallungscreeningtrialdeeplearningbaseddetectionofmissedlungcancers AT sunghyunyoon incidencelungcancerafteranegativectscreeninginthenationallungscreeningtrialdeeplearningbaseddetectionofmissedlungcancers AT hwayoungsong incidencelungcancerafteranegativectscreeninginthenationallungscreeningtrialdeeplearningbaseddetectionofmissedlungcancers AT junghoonkim incidencelungcancerafteranegativectscreeninginthenationallungscreeningtrialdeeplearningbaseddetectionofmissedlungcancers AT yerachoi incidencelungcancerafteranegativectscreeninginthenationallungscreeningtrialdeeplearningbaseddetectionofmissedlungcancers AT kyungheelee incidencelungcancerafteranegativectscreeninginthenationallungscreeningtrialdeeplearningbaseddetectionofmissedlungcancers AT kyungwonlee incidencelungcancerafteranegativectscreeninginthenationallungscreeningtrialdeeplearningbaseddetectionofmissedlungcancers |
_version_ |
1724401916838936576 |