IBM Research at Image CLEF 2015: Medical Clustering Task Suman Sedai, Xi Liang, Mani Abedini, Qiang Chen, Rajib Chakravorty, Rahil Garnavi IBM Research Australia Level 5, 204 Lygon Street, Carlton Victoria 3053, Australia {ssedai,xiliang,mabedini,qiangchen,rachakra,rahilgar}@au1.ibm.com http://www.research.ibm.com/labs/australia Abstract. In this paper, we present the learning strategies and fea- ture extraction techniques that were applied by the IBM Research Aus- tralia team to the Medical Clustering challenge of ImageCLEF 2015. The challenge is to automatically annotate and categorize X-ray images into head-neck, body, upper-limb, lower-limb and foreign object cate- gories. Our proposed methodology and details of experiments for each submitted run has been discussed in this paper, followed by final results provided by the competition organizers. The key components used in our submissions are based on sparse coding of SIFT, local binary patterns and multi-scale local binary patterns with spatial pyramid, advanced fisher vector, various SVM kernels, and an effective fusion methodol- ogy, to ensure high classification accuracy. Comprehensive experiments demonstrate the effectiveness of the proposed system. Six out of the ten submissions of IBM Research were among the top 10 best results, where two of our submissions outperformed all other submissions, therefore the team has achieved the first place in the competition. Keywords: Medical image classification, Local binary pattern, Sparse coding, Fisher vector, Fisher encoding, Spatial pyramid 1 Introduction ImageCLEF medical clustering task [0] is a new category in ImageCLEF 2015 [0]. The objective of this task is to categorize digital X-ray images into four clusters: head-neck, upper-limb, body, and lower-limb [0]. X-ray is the most common med- ical image modality as it accounts for one third of the the radiographs taken in a typical radiology department [0]. Automatic categorization of medical images has a number of applications including efficient retrieval, archiving, and patient similarity matching. For example, for search and retrieval task, the image needs to be pre-classified. However, X-ray image classification is a challenging task due to variation in the patients location, exposure, subject motion and the presence of artifacts and foreign objects. In this work, we present a X-ray annotation and categorization system which accurately performs in presence of such artifacts.