A Computer-aided Diagnosis Method for Classification of Pneumoconiosis Patterns on HRCT Images

摘要

This paper describes a computer-aided diagnosis method to classify pneumoconiosis on HRCT images. In Japan, the pneumoconiosis is divided into: Type 1(no nodules), Type 2(few small nodules), Type 3-a(numerous small nodules) and Type 3-b(numerous small nodules and presence of large nodules). The classification is performed as follows. Firstly extracting large-sized nodules and recognizing the type 3-b cases. Secondly, employing Hessian-based filters to detect small-sized nodules on the rest cases. Finally, adopting a bag-of-features-based method to classify the other three kinds of cases. The proposed method achieved the classification accuracy of 90.6%, which would be helpful to classify pneumoconiosis on HRCT.