Translator Disclaimer
24 March 2016 Quantitative imaging features to predict cancer status in lung nodules
Author Affiliations +
Background: We propose a systematic methodology to quantify incidentally identified lung nodules based on observed radiological traits on a point scale. These quantitative traits classification model was used to predict cancer status. Materials and Methods: We used 102 patients’ low dose computed tomography (LDCT) images for this study, 24 semantic traits were systematically scored from each image. We built a machine learning classifier in cross validation setting to find best predictive imaging features to differentiate malignant from benign lung nodules. Results: The best feature triplet to discriminate malignancy was based on long axis, concavity and lymphadenopathy with average AUC of 0.897 (Accuracy of 76.8%, Sensitivity of 64.3%, Specificity of 90%). A similar semantic triplet optimized on Sensitivity/Specificity (Youden’s J index) included long axis, vascular convergence and lymphadenopathy which had an average AUC of 0.875 (Accuracy of 81.7%, Sensitivity of 76.2%, Specificity of 95%). Conclusions: Quantitative radiological image traits can differentiate malignant from benign lung nodules. These semantic features along with size measurement enhance the prediction accuracy.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ying Liu, Yoganand Balagurunathan, Thomas Atwater, Sanja Antic, Qian Li, Ronald Walker, Gary T. Smith, Pierre P. Massion, Matthew B. Schabath, and Robert J. Gillies "Quantitative imaging features to predict cancer status in lung nodules", Proc. SPIE 9787, Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment, 97870L (24 March 2016);

Back to Top