Predicting Malignant Nodules by Fusing Deep Features with Classical Radiomics Features
Lung cancer, Lung, Feature extraction, Cancer, RGB color model, Control systems, Computed tomography, Neural networks, Image classification, Cameras
Digital Object Identifier (DOI)
Lung cancer has a high incidence and mortality rate. Early detection and diagnosis of lung cancers is best achieved with low-dose computed tomography (CT). Classical radiomics features extracted from lung CT images have been shown as able to predict cancer incidence and prognosis. With the advancement of deep learning and convolutional neural networks (CNNs), deep features can be identified to analyze lung CTs for prognosis prediction and diagnosis. Due to a limited number of available images in the medical field, the transfer learning concept can be helpful. Using subsets of participants from the National Lung Screening Trial (NLST), we utilized a transfer learning approach to differentiate lung cancer nodules versus positive controls. We experimented with three different pretrained CNNs for extracting deep features and used five different classifiers. Experiments were also conducted with deep features from different color channels of a pretrained CNN. Selected deep features were combined with radiomics features. A CNN was designed and trained. Combinations of features from pretrained, CNNs trained on NLST data, and classical radiomics were used to build classifiers. The best accuracy (76.79%) was obtained using feature combinations. An area under the receiver operating characteristic curve of 0.87 was obtained using a CNN trained on an augmented NLST data cohort.
Was this content written or created while at USF?
Citation / Publisher Attribution
Journal of Medical Imaging, v. 5, issue 1, art. 011021
Scholar Commons Citation
Paul, Rahul; Hawkins, Samuel; Schabath, Matthew B.; Gillies, Robert J.; Hall, Lawrence O.; and Goldgof, Dmitry, "Predicting Malignant Nodules by Fusing Deep Features with Classical Radiomics Features" (2018). Computer Science and Engineering Faculty Publications. 116.