1. Lung nodule detection via Bayesian voxel labeling.
- Author
-
Mendonça PR, Bhotika R, Zhao F, and Miller JV
- Subjects
- Bayes Theorem, Computer Simulation, Humans, Lung Neoplasms diagnostic imaging, Models, Biological, Models, Statistical, Radiographic Image Enhancement methods, Reproducibility of Results, Sensitivity and Specificity, Subtraction Technique, Algorithms, Artificial Intelligence, Imaging, Three-Dimensional methods, Information Storage and Retrieval methods, Pattern Recognition, Automated methods, Radiographic Image Interpretation, Computer-Assisted methods, Solitary Pulmonary Nodule diagnostic imaging, Tomography, X-Ray Computed methods
- Abstract
This paper describes a system for detecting pulmonary nodules in CT images. It aims to label individual image voxels in accordance to one of a number of anatomical (pulmonary vessels or junctions), pathological (nodules), or spurious (noise) events. The approach is orthodoxly Bayesian, with particular care taken in the objective establishment of prior probabilities and the incorporation of relevant medical knowledge. We provide, under explicit modeling assumptions, closed-form expressions for all the probability distributions involved. The technique is applied to real data, and we present a discussion of its performance.
- Published
- 2007
- Full Text
- View/download PDF