Recently, using local visual feature for image representation has become very popular, and been proved to be very effective for image categorization or retrieval. Based on the success of the above-mentioned visual features for general image recognition, we also use them as medical image representation for modality classification. In computer vision, studies have shown that the simple global features such as histogram of edge, gray or color intensity, can represent images, and give the acceptable performance in image retrieval or recognition research fields. Therefore, in this paper, we propose to use both visual and textual features for medical image representation, and combine the different features using normalized kernel function in SVM. Some works have shown that image modality can be extracted from the image itself using visual features. However, this modality is typically extracted from the caption and is often not correct or present”. Many image retrieval websites (Goldminer, Yottalook) allow users to limit the search results to a particular modality.
![textual features textual features](http://3.bp.blogspot.com/-EbAEziaq3e0/UUsN1gQpJ8I/AAAAAAAAA6Q/laWfy_XOpdg/s640/text%2Bfeatures.jpg)
“In user studies, clinicians have indicated that modality is one of the most important filters that they would like to be able to limit their search by. Imaging modality is an important aspect of the image for medical retrieval. The proposed strategy is evaluated with the provided modality dataset by ImageCLEF 2010. Furthermore, for some easy misclassified modality pairs such as CT and MR or PET and NM modalities, a local classifier is used for distinguishing samples in the pair modality to improve performance. Then, we combine the different features using normalized kernel functions for SVM classification. For textual feature of image representation, the binary histogram of some predefined vocabulary words from image captions is used. To extract visual features from the images, we used histogram descriptor of edge, gray, or color intensity and block-based variation as global features and SIFT histogram as local feature.
![textual features textual features](https://ecdn.teacherspayteachers.com/thumbitem/Informational-Text-Features-Clipart-Collection-1563468731/original-396363-3.jpg)
![textual features textual features](http://mrsjennshaffer.weebly.com/uploads/1/0/9/5/10953424/text-features_1.jpg)
This paper is focused on the process of featureĮxtraction from medical images and fuses the different extracted visual features and textual feature for modality classification. We describe an approach for the automatic modality classification in medical image retrieval task of the 2010 CLEF cross-language image retrieval campaign (ImageCLEF).