1. Automatic Detection of Subsolid Pulmonary Nodules in Thoracic Computed Tomography Images
- Author
-
Colin Jacobs, Thorsten Twellmann, Mathias Prokop, Harry J. de Koning, Matthijs Oudkerk, Cornelia M. Schaefer-Prokop, Eva M. van Rikxoort, Bram van Ginneken, Jan-Martin Kuhnigk, Ernst T. Scholten, Pim A. de Jong, Public Health, Rehabilitation Medicine, and Publica
- Subjects
Lung Neoplasms ,Vascular damage Radboud Institute for Health Sciences [Radboudumc 16] ,CAD ,LUNG NODULES ,Subsolid nodule ,Ground-glass opacity ,Pattern Recognition, Automated ,TEXTURE CLASSIFICATION ,Computed tomography (CT) ,Early Detection of Cancer ,Radiological and Ultrasound Technology ,FLEISCHNER-SOCIETY ,Computer Graphics and Computer-Aided Design ,Radiographic Image Interpretation, Computer-Assisted ,Computer Vision and Pattern Recognition ,Radiology ,medicine.symptom ,Lung cancer ,MULTIPLE NEURAL-NETWORKS ,Algorithms ,Rare cancers Radboud Institute for Health Sciences [Radboudumc 9] ,LOCAL BINARY PATTERNS ,medicine.medical_specialty ,Local binary patterns ,Health Informatics ,Context (language use) ,Sensitivity and Specificity ,SCANS ,SDG 3 - Good Health and Well-being ,Lung nodule ,AIDED DETECTION ,medicine ,Humans ,Radiology, Nuclear Medicine and imaging ,business.industry ,Computer aided detection (CAD) ,Reproducibility of Results ,Solitary Pulmonary Nodule ,Nodule (medicine) ,DETECTION SYSTEM ,CT IMAGES ,GROUND-GLASS OPACITY ,medicine.disease ,Data set ,Inflammatory diseases Radboud Institute for Health Sciences [Radboudumc 5] ,Tomography, X-Ray Computed ,Nuclear medicine ,business ,Lung cancer screening - Abstract
Contains fulltext : 136826.pdf (Publisher’s version ) (Open Access) Subsolid pulmonary nodules occur less often than solid pulmonary nodules, but show a much higher malignancy rate. Therefore, accurate detection of this type of pulmonary nodules is crucial. In this work, a computer-aided detection (CAD) system for subsolid nodules in computed tomography images is presented and evaluated on a large data set from a multi-center lung cancer screening trial. The paper describes the different components of the CAD system and presents experiments to optimize the performance of the proposed CAD system. A rich set of 128 features is defined for subsolid nodule candidates. In addition to previously used intensity, shape and texture features, a novel set of context features is introduced. Experiments show that these features significantly improve the classification performance. Optimization and training of the CAD system is performed on a large training set from one site of a lung cancer screening trial. Performance analysis on an independent test from another site of the trial shows that the proposed system reaches a sensitivity of 80% at an average of only 1.0 false positive detections per scan. A retrospective analysis of the output of the CAD system by an experienced thoracic radiologist shows that the CAD system is able to find subsolid nodules which were not contained in the screening database.
- Published
- 2014