Medical image classification by supervised machine learning
Pei-Cheng Cheng, Been-Chian Chien, Wei‐Pang Yang · 2006
Abstract:- In this paper, Support Vector Machine (SVM) was used to learn image feature characteristics for image classification. Several image visual features describe the shape, edge, and texture of image (including histogram, spatial layout, coherence moment and gabor features) have been employed in this paper to categorize the 500 test images into 46 classes. The result shows that the spatial relationship of pixels is a very important feature in medical image data, because medical image data always have similar anatomic regions (lung, liver, head, and so on).