NovaSearch on medical ImageCLEF 2013

This article presents the participation of the Center of Informatics and Information Technology group CITI in medical ImageCLEF 2013. This is our first participation and we submitted runs on the modality classification task, the ad-hoc image retrieval task and case retrieval task. We are developing a system to integrate textual and visual retrieval into a framework for multimodal retrieval. Our approach for multimodal case retrieval achieved best global performance using Segmented (6-6 grid) Local Binary Pattern (LBP) histograms and Segmented HSV histograms for images and Lucene with query expansion (using the first top 3 results). In modality classification we achieved one of the largest MAP gains in the multimodal classification task, resulting in the third best team result.