João Magalhães

Learn More
Mutations in the BRAF gene have recently been detected in a wide range of neoplastic lesions with a particularly high prevalence in melanoma and papillary thyroid carcinoma (PTC). The hot-spot mutation BRAF(V599E) is frequently detected in PTC (36-69%), in contrast to its absence in other benign or malignant thyroid lesions. In order to unravel whether(More)
Follicular thyroid carcinoma is being diagnosed less and less frequently despite the increasing incidence of well-differentiated thyroid carcinomas everywhere. This review will discuss the reasons underlying such an observation focusing on the evolution of the morphological and immunohistochemical diagnostic criteria of follicular thyroid tumors. It will(More)
A high prevalence of the BRAFV600E somatic mutation was recently reported in several series of papillary thyroid carcinomas (PTC). This mutation appears to be particularly prevalent in PTC with a predominantly papillary architecture. Another BRAF mutation (K601E) was detected in a follicular adenoma and in some cases of the follicular variant of PTC. The(More)
The BRAF gene has been shown to be a major target for mutations in papillary thyroid carcinoma (PTC) (36-69%), which forms almost all of the over 2000 cases of thyroid carcinoma that have occurred in Chernobyl. BRAF is activated by point mutation, and were it to occur at a high frequency in Chernobyl-related tumors, it would challenge the dominant role of(More)
This paper describes the participation of the NovaSearch group at TREC Clinical Decision Support 2014. As this is the first edition of the track, we decided to assess the performance of multiple information retrieval techniques: retrieval functions, re-ranking, query expansion and classification of medical articles into question categories. The best(More)
In this paper we describe the geographic information retrieval system developed and results achieved by the Multimedia & Information Systems team for GeoCLEF 2006. We detail our methods for generating and applying co-occurrence models for the purpose of place name disambiguation, our use of named entity recognition tools and text indexing applications. The(More)
This paper is about automatically annotating images with keywords in order to be able to retrieve images with text searches. Our approach is to model keywords such as 'mountain' and 'city' in terms of visual features that were extracted from images. In contrast to other algorithms, each specific keyword-model considers not only its own training data but(More)
Modern medical information retrieval systems are paramount to manage the insurmountable quantities of clinical data. These systems empower health care experts in the diagnosis of patients and play an important role in the clinical decision process. However, the ever-growing heterogeneous information generated in medical environments poses several challenges(More)