How Many Private Data Are Needed for Deep Learning in Lung Nodule Detection on CT Scans? A Retrospective Multicenter Study
Open Access
Abstract
Early detection of lung nodules is essential for preventing lung cancer. However, the number of radiologists who can diagnose lung nodules is limited, and considerable effort and time are required. To address this problem, researchers are investigating the automation of deep-learning-based lung nodule detection. However, deep learning requires large amounts of data, which can be difficult to collect. Therefore, data collection should be optimized to facilitate experiments at the beginning of lung nodule detection studies. We collected chest computed tomography scans from 515 patients with lung nodules from three hospitals and high-quality lung nodule annotations reviewed by radiologists. We conducted several experiments using the collected datasets and publicly available data from LUNA16. The object detection model, YOLOX was used in the lung nodule detection experiment. Similar or better performance was obtained when training the model with the collected data rather than LUNA16 with large amounts of data. We also show that weight transfer learning from pre-trained open data is very useful when it is difficult to collect large amounts of data. Good performance can otherwise be expected when reaching more than 100 patients. This study offers valuable insights for guiding data collection in lung nodules studies in the future.Keywords
Funding Information
- Korea Health Information Service (KHIS) (NRF-2022R1F1A1076454)
- Ministry of Health & Welfare, Republic of Korea (NRF-2022R1F1A1076454)
- National Research Foundation of Korea (NRF) (NRF-2022R1F1A1076454)
- Ministry of Education (NRF-2022R1F1A1076454)
- Kangwon National University (NRF-2022R1F1A1076454)
This publication has 36 references indexed in Scilit:
- A survey of transfer learningJournal of Big Data, 2016
- Computer-aided detection of lung nodules using outer surface featuresBio-Medical Materials and Engineering, 2015
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Treatment of non-small cell lung cancer (NSCLC)2013
- Impact of a Computer-Aided Detection (CAD) System Integrated into a Picture Archiving and Communication System (PACS) on Reader Sensitivity and Efficiency for the Detection of Lung Nodules in Thoracic CT ExamsJournal of Digital Imaging, 2012
- Reduced Lung-Cancer Mortality with Low-Dose Computed Tomographic ScreeningNew England Journal of Medicine, 2011
- The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A Completed Reference Database of Lung Nodules on CT ScansMedical Physics, 2011
- Comparing and combining algorithms for computer-aided detection of pulmonary nodules in computed tomography scans: The ANODE09 studyMedical Image Analysis, 2010
- On Combining Computer-Aided Detection SystemsIEEE Transactions on Medical Imaging, 2010
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009