Gliomas are the most common malignant brain tumors that are treated with chemoradiotherapy and surgery. Magnetic Resonance Imaging (MRI) is used by radiotherapists to manually segment brain lesions and to observe their development throughout the therapy. The manual image segmentation process is time-consuming and results tend to vary among different human raters. Therefore, there is a substantial demand for automatic image segmentation algorithms that produce a reliable and accurate segmentation of various brain tissue types. Recent advances in deep learning have led to convolutional neural network architectures that excel at various visual recognition tasks. They have been successfully applied to the medical context including medical image segmentation. In particular, fully convolutional networks (FCNs) such as the U-Net produce state-of-the-art results in the automatic segmentation of brain tumors. MRI brain scans are volumetric and exist in various coregistered modalities that serve as input channels for these FCN architectures. Training algorithms for brain tumor segmentation on this complex input requires large amounts of computational resources and is prone to overfitting. In this work, we construct FCNs with pretrained convolutional encoders. We show that we can stabilize the training process this way and produce more robust predictions. We evaluate our methods on publicly available data as well as on a privately acquired clinical dataset. We also show that the impact of pretraining is even higher for predictions on the clinical data.
RESUMO A Ciência Forense Digital surgiu da necessidade de tratar problemas forenses na era digital. Seu mais recente desafio está relacionado ao surgimento das mídias sociais, intensificado pelos avanços da Inteligência Artificial. A produção massiva de dados nas mídias sociais tornou a análise forense mais complexa, especialmente pelo aperfeiçoamento de modelos computacionais capazes de gerar conteúdo artificial com alto realismo. Assim, tem-se a necessidade da aplicação de técnicas de Inteligência Artificial para tratar esse imenso volume de informação. Neste artigo, apresentamos desafios e oportunidades associados à aplicação dessas técnicas, além de fornecer exemplos de seu uso em situações reais. Discutimos os problemas que surgem em contextos sensíveis e como a comunidade científica tem abordado esses tópicos. Por fim, delineamos futuros caminhos de pesquisa a serem explorados.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.