Abstract
Patients are often anxious to quickly discover reliable analysis and concise explanation of their medical images while waiting for the physician decision. The fact of making important choices individually in his own corner may lead the physician to commit errors leading to malpractices and consequently to unforeseeable damages. In order to minimize medical errors by fostering collaboration between physicians and/or patients, we propose in this paper, as a first contribution, a medical social network destined to gather patients' medical images and physicians' annotations expressing their medical reviews and advices. The need, to automatically extract information and analyze opinions, becomes obviously a requirement due to the huge number of comments expressing specialists' recommendations and/or remarks. For this purpose, we propose a second contribution consisting of providing a kind of comments' summary which extracts the major current terms and relevant words existing on physicians' reports. Furthermore, this extracted information will present a new and robust input for image indexation enhanced methods. In fact, significant extracted terms will be used later to index images in order to facilitate their search through the underlying social network. To overcome the above challenges, we propose an approach which focuses on algorithms mainly based on statistical methods and external semantic resources destined to filter selected extracted information.