Reducing False-Positives in Lung Nodules Detection Using Balanced Datasets

• Main Authors: Jinglun Liang (Author), Guoliang Ye (Author), Jianwen Guo (Author), Qifan Huang (Author), Shaohui Zhang (Author)
• Format: Book
• Published: Frontiers Media S.A., 2021-05-01T00:00:00Z.
• Subjects: article
• Online Access: Connect to this object online.
• Notes: 2296-2565; 10.3389/fpubh.2021.671070
• Keywords: pulmonary nodule detection; lung image classification; deep learning; convolutional neural network; transfer learning; Public aspects of medicine; RA1-1270
• Source: Frontiers in Public Health, Vol 9 (2021)

Malignant pulmonary nodules are one of the main manifestations of lung cancer in early CT image screening. Since lung cancer may have no early obvious symptoms, it is important to develop a computer-aided detection (CAD) system to assist doctors to detect the malignant pulmonary nodules in the early stage of lung cancer CT diagnosis. Due to the recent successful applications of deep learning in image processing, more and more researchers have been trying to apply it to the diagnosis of pulmonary nodules. However, due to the ratio of nodules and non-nodules samples used in the training and testing datasets usually being different from the practical ratio of lung cancer, the CAD classification systems may easily produce higher false-positives while using this imbalanced dataset. This work introduces a filtering step to remove the irrelevant images from the dataset, and the results show that the false-positives can be reduced and the accuracy can be above 98%. There are two steps in nodule detection. Firstly, the images with pulmonary nodules are screened from the whole lung CT images of the patients. Secondly, the exact locations of pulmonary nodules will be detected using Faster R-CNN. Final results show that this method can effectively detect the pulmonary nodules in the CT images and hence potentially assist doctors in the early diagnosis of lung cancer.