Deep learning architecture with transformer and semantic field alignment for voxel-level dose prediction on brain tumors.
Sign Up to like & getrecommendations! Published in 2022 at "Medical physics"
DOI: 10.1002/mp.16122
Abstract: PURPOSE The use of convolution neural networks (CNN) to accurately predict dose distributions can accelerate intensity-modulated radiation therapy (IMRT) planning. The purpose of our study is to develop a novel deep learning architecture for precise… read more here.
Keywords: level dose; voxel level; brain tumors; dose distributions ... See more keywords
Weakly-supervised convolutional neural networks for multimodal image registration
Sign Up to like & getrecommendations! Published in 2018 at "Medical image analysis"
DOI: 10.1016/j.media.2018.07.002
Abstract: HighlightsA method to infer voxel‐level correspondence from higher‐level anatomical labels.Efficient and fully‐automated registration for MR and ultrasound prostate images.Validation experiments with 108 pairs of labelled interventional patient images.Open‐source implementation. ABSTRACT One of the fundamental challenges… read more here.
Keywords: voxel level; image; image registration; multimodal image ... See more keywords
MetricUNet: Synergistic image- and voxel-level learning for precise prostate segmentation via online sampling
Sign Up to like & getrecommendations! Published in 2021 at "Medical image analysis"
DOI: 10.1016/j.media.2021.102039
Abstract: Fully convolutional networks (FCNs), including UNet and VNet, are widely-used network architectures for semantic segmentation in recent studies. However, conventional FCN is typically trained by the cross-entropy or Dice loss, which only calculates the error… read more here.
Keywords: voxel level; image; network; segmentation ... See more keywords
Differences in network centrality between high and low myopia: a voxel-level degree centrality study
Sign Up to like & getrecommendations! Published in 2020 at "Acta Radiologica"
DOI: 10.1177/0284185120902385
Abstract: Background Previous studies have linked high myopia (HM) to brain activity, and the difference between HM and low myopia (LM) can be assessed. Purpose To study the differences in functional networks of brain activity between… read more here.
Keywords: voxel level; brain activity; study; centrality ... See more keywords