Corpus Callosum (CC) segmentation is required when the analysis from this structure is desirable. Many of these studies require the CC segmentation on diffusion tensor images (DTI). However, few methods perform segmentation directly in the DTI. Segmenting on DTI makes it possible to disregard the registration step after segmenting on T1 images. This work studies the possibility of improving automated segmentation of the CC using silver standard annotations. With incomplete silver standard annotations, limited to 5 or 7 central slices, experiments performed throughout this work were done to compare methods of pre-training and fine tuning in an attempt to translate silver standard knowledge to improved performance in 3D CC segmentation. Experiments include 3D and 2D U-Net as deep learning architectures. Results point to central limited silver standard annotations not being useful for improving the performance in gold standard 3D annotations. Our best method involved training a 3D U-Net with gold standards and post processing, achieving a 3D Dice of 83.33 Dice, surpassing 2D U-Net.
The Corpus Callosum is the major interhemispheric commisure and, because of its highly organized fibers, it is often studied using diffusion tensor images (DTI). A firstnecessary step for CC studies is its segmentation, preferably automated. Since most available softwares are not able to perform CC volumetric segmentation, and the only ones that do it, are based on T1-weighted images and not DTI, this work presents the extension of an open-source software, called inCCsight, incorporating a DTI-based CC volumetric segmentation method into it. The software is open-source and offers the possibility of incorporating customized plots and integrating other segmentation and/or parcellation methods by the user.
Nos últimos anos, a quantidade de veículos que circulam nas avenidas e rodovias brasileiras, tem crescido bastante. Com isso, aumentou o tempo que as pessoas passam conduzindo seus veículos, o que ocasiona mais estresse, cansaço e falta de atenção. Em virtude dessas situações, a quantidade de acidentes também expandiu. Além disso, dirigir, principalmente para pessoas que trabalham com isso, diariamente, se torna ainda mais cansativo e estressante, além do que, é uma ação que nescessita de muita disposição e atenção de quem está a praticando. Esses fatos, foram relevantes para o crescimento na quantidade de acidentes, que do ano de 2016 para 2017 foi de 7.272, e aproximadamente 38% desses, foram causados por condutores sonolentos. Então, neste trabalho, será apresentado a utilização de três técnicas de Inteligência Artificil (IA): Rede Neural Artificial e duas Redes Neurais Convolucionais. Essas técnicas, foram submetidas aos processamentos offline (o qual necessitou de uma base de dados com 811 fotos) e online. As acurácias dos processos offline obtidos para as três técnicas foram aproximadamente, 77% para a rede neural artificial e 95% para as redes neurais convolucionais. Já as acurácias dos testes online para a rede neural artificial, LeNet-5 e VGG16 foram respectivamente: 57,48%, 90.52% e 78.85%. os resultados dos testes oline, mostram que a melhor técnica para solucionar o problema proposto foi a LeNet-5.
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.