Archive

Automatic Anatomy Recognition in Medical Images

Automated analysis of medical images for diagnostic and data mining purposes are being widely developed. An essential step in high throughput processing is to know what anatomy is included in a given image so that the right analysis can be triggered automatically. CVIB PhD student Xiaoyong Wang, working with faculty and staff scientists, has developed an image classification technique using a feature vector based on image subsampling. Machine learning was performed using a large clinical trial database of labeled images.…

0
Read More

Robustness-Driven Feature Selection in Classification of Interstitial Lung Disease

Lack of classifier robustness to CT acquisition parameter variations is a barrier to widespread adoption of CAD systems. As part of his PhD research, CVIB graduate Dr Danny Chong developed a new Robustness-Driven Feature Selection (RDFS) algorithm that preferentially selects features that are relatively invariant CT technical factors. Working with CVIB faculty and staff, Dr. Chong showed that use of RDFS with 3D texture features improved CT classification of fibrotic interstitial lung disease in multi-center clinical trials. The research was…

0
Read More