Multi-level classification of emphysema in HRCT lung images

Emphysema is a common chronic respiratory disorder characterised by the destruction of lung tissue. It is a progressive disease where the early stages are characterised by a diffuse appearance of small air spaces, and later stages exhibit large air spaces called bullae. A bullous region is a sharply demarcated region of emphysema. In this paper, it is shown that an automated texture-based system based on co-training is capable of achieving multiple levels of emphysema extraction in high-resolution computed tomography (HRCT) images. Co-training is a semi-supervised technique used to improve classifiers that are trained with very few labelled examples using a large pool of unseen examples over two disjoint feature sets called views. It is also shown that examples labelled by experts can be incorporated within the system in an incremental manner. The results are also compared against “density mask”, currently a standard approach used for emphysema detection in medical image analysis and other computerized techniques used for classification of emphysema in the literature. The new system can classify diffuse regions of emphysema starting from a bullous setting. The classifiers built at different iterations also appear to show an interesting correlation with different levels of emphysema, which deserves more exploration.

---

Mithun Prasad (Corresponding author)Email:

Arcot SowmyaEmail:

Peter WilsonEmail:

---

Mithun Prasad   received his PhD from the University of New South Wales, Sydney, Australia in 2006. He was a postdoctoral scholar at the University of California, Los Angeles and now a research associate at Rensselaer Polytechnic Institute, NY. His research interests are computer aided diagnosis, cell and tissue image analysis. Arcot Sowmya   is a Professor, School of Computer Science and Engineering, UNSW, Sydney. She holds a PhD degree in Computer Science from Indian Institute of Technology, Bombay, besides other degrees in Mathematics and Computer Science. Her areas of research include learning in vision as well as embedded system design. Her research has been applied to extraction of linear features in remotely sensed images as well as feature extraction, recognition and computer aided diagnosis in medical images. Peter Wilson   is a clinical Radiologist at Pittwater Radiology in Sydney. He was trained at Royal North Shore Hospital and taught Body Imaging at the University of Rochester, NY, prior to taking up his current position.