Developing CT image-processing tools to accelerate progress in lung cancer drug development.
Explore the source record for details and available documents.
Antineoplastic Agents↗
Biomedical subjects
Ricardo S Avila
Publications and source records attributed to Ricardo S Avila.
Model-based analysis of local shape for lesion detection in CT scans.
Thin-slice computer tomography provides high-resolution images that facilitate the diagnosis of early-stage lung cancer. However, the sheer size of the CT volumes introduces variability in radiological readings, driving the need for automated detection systems. The main contribution of this paper is a technique for combining geometric and intensity models with the analysis of local curvature for detecting pulmonary lesions in CT. The local shape at each voxel is represented via the principal curvatures of its associated isosurface without explicitly extracting the isosurface. The comparison of these curvatures to values derived from analytical shape models is then used to label the voxel as belonging to particular anatomical structures, e.g., nodules or vessels. The algorithm was evaluated on 242 CT exams with expert-determined ground truth. The performance of the algorithm is quantified by free-response receiver-operator characteristic curves, as well as by its potential for improvement in radiologist sensitivity.
Algorithms↗
Pulmonary nodule detection with low-dose CT of the lung: agreement among radiologists.
OBJECTIVE: The purpose of our study was to assess relative intra- and interobserver agreement in detecting pulmonary nodules when interpreting low-dose chest CT screening examinations. MATERIALS AND METHODS: Two hundred ninety-three selected low-dose CT examinations of the lung were independently interpreted by three radiologists to detect and classify pulmonary nodules. The data set selected was enriched with examinations depicting pulmonary nodules. A subset of 30 examinations was interpreted twice. All pulmonary nodules greater than 1.0 mm were marked. All nodules greater than 3.0 mm were marked, measured, and scored as to their probability of being benign or malignant. Nodule-based and examination-based relative reviewer agreements were evaluated using percentage of agreement and kappa statistics. Similar assessments were performed on the subset of examinations interpreted twice. RESULTS: The three radiologists identified a total of 470, 729, and 876 pulmonary nodules of which 395, 641, and 778 were rated as noncalcified with some level of suspicion for being malignant. Nodule-based interobserver agreement among the radiologists was poor (highest kappa value in a paired comparison, 0.120). Examination-based agreement was higher (highest kappa value in a paired comparison, 0.458). Intraobserver agreement was higher than interobserver agreement for examination-based agreement (highest kappa = 0.889) but lower for nodule-based agreement (highest kappa = -0.035). Agreement improved as the suspicion of malignancy increased. CONCLUSION: Unaided intra- and interobserver agreement in detecting pulmonary nodules in low-dose CT of the lung is relatively low. Computer-assisted detection may provide the consistency that is needed for this purpose.
Female↗
Model-based detection of lung nodules in computed tomography exams. Thoracic computer-aided diagnosis.
RATIONALE AND OBJECTIVES: In this study, we developed a prototype model-based computer aided detection (CAD) system designed to automatically detect both solid and subsolid pulmonary nodules in computed tomography (CT) images. By using this CAD algorithm, along with the radiologist's initial interpretation, we aim to improve the sensitivity of radiologic readings of CT lung exams. MATERIALS AND METHODS: We have developed a model-based CAD algorithm through the use of precise mathematic models that capture scanner physics and anatomic information. Our model-based CAD algorithm uses multiple segmentation algorithms to extract noteworthy structures in the lungs and a Bayesian statistical model selection framework to determine the probability of various anatomical events throughout the lung. We tested this algorithm on 50 low-dose CT lung cancer screening cases in which ground truth was produced through readings by three expert chest radiologists. RESULTS: Using this model-based CAD algorithm on 50 low-dose CT cases, we measured potential sensitivity improvements of 7% and 5% in two radiologists with respect to all noncalcified nodules, solid and subsolid, greater than 5 mm in diameter. The third radiologist did not miss any nodules in the ground truth set. The CAD algorithm produced 8.3 false positives per case. CONCLUSION: Our prototype CAD system demonstrates promising results as a tool to improve the quality of radiologic readings by increasing radiologist sensitivity. A significant advantage of this model-based approach is that it can be easily extended to support additional anatomic models as clinical understanding and scanning practices improve.
Algorithms↗