Discriminating TB lung nodules from early lung cancers using deep learning

• Published in: BMC medical informatics and decision making 2022-06, Vol.22 (1), p.1-161, Article 161
• Main Authors: Tan, Heng, Bates, Jason H. T, Matthew Kinsey, C
• Format: Article
• Language: English
• Subjects: Accuracy; Artificial neural networks; Computed tomography; Datasets; Deep learning; Developing countries; Health informatics; Identification and classification; Infectious diseases; Invasiveness; Latent TB; LDCs; Lung cancer; Lung nodules; Machine learning; Medical imaging; Methods; Morbidity; Mortality; Neural networks; Nodules; Public health; Pulmonary tuberculosis; Smoking; Transfer learning; Tuberculosis
• ISSN: 1472-6947; 1472-6947
• DOI: 10.1186/s12911-022-01904-8

Background In developing countries where both high rates of smoking and endemic tuberculosis (TB) are often present, identification of early lung cancer can be significantly confounded by the presence of nodules such as those due to latent TB (LTB). It is very challenging to distinguish lung cancer and LTB without invasive procedures, which have their own risks of morbidity and even mortality. Methods Our method uses a customized VGG16-based 15-layer 2-dimensional deep convolutional neural network (DNN) architecture with transfer learning. The DNN was trained and tested on sets of CT images set extracted from the National Lung Screening Trial and the National Institute of Allergy and Infectious Disease TB Portals. Performance of the DNN was evaluated under locked and step-wise unlocked pretrained weight conditions. Results The DNN with unlocked pretrained weights achieved an accuracy of 90.4% with an F score of 90.1%. Conclusions Our findings support the potential for a DNN to serve as a noninvasive screening tool capable of reliably detecting and distinguishing between lung cancer and LTB. Keywords: Lung cancer, Latent TB, Deep learning