The framework contains two tasks: semantic segmentation (main task) and super resolution (auxiliary task).
(2) A simple and effective spatial-aware inter-scale transformer is designed to interact among consensual regions in multiple scales, which can highlight the cross-scale dependency and resolve the complex scale variations.
Multimodal sentiment analysis and depression estimation are two important research topics that aim to predict human mental states using multimodal data.
Different from the texture transfer processing of RGB image, we use HR PAN images as the reference images and perform texture transfer for each frequency band of MS images, which is named 2. 5D texture transfer.
To further boost model adaptation performance, we propose a novel method called Attention-based Cross-layer Domain Alignment (ACDA), which captures the semantic relationship between the source and target domains across model layers and calibrates each level of semantic information automatically through a dynamic attention mechanism.
Therefore, Vision Transformers have emerged as alternative segmentation structures recently, for their innate ability of capturing long-range correlations through Self-Attention (SA).
In this work, we propose a novel LiTS method to adequately aggregate multi-phase information and refine uncertain region segmentation.
The experiments demonstrated that the prediction accuracy can be improved significantly from 78. 61% (existing radiomics method) and 79. 14% (deep learning method) to 83. 28% by the proposed GGR.
Our Graph- PGCR module is plug-and-play, which can be integrated into any architecture to improve its performance.
no code implementations • 27 Feb 2021 • Yingying Xu, Ming Cai, Lanfen Lin, Yue Zhang, Hongjie Hu, Zhiyi Peng, Qiaowei Zhang, Qingqing Chen, Xiongwei Mao, Yutaro Iwamoto, Xian-Hua Han, Yen-Wei Chen, Ruofeng Tong
In this paper, we propose a phase attention residual network (PA-ResSeg) to model multi-phase features for accurate liver tumor segmentation, in which a phase attention (PA) is newly proposed to additionally exploit the images of arterial (ART) phase to facilitate the segmentation of portal venous (PV) phase.
Semi-supervised learning (SSL) algorithms have attracted much attentions in medical image segmentation by leveraging unlabeled data, which challenge in acquiring massive pixel-wise annotated samples.
We construct a parallel connection structure based on the group convolution and feature aggregation to build a 3D CNN that is as wide as possible with few parameters.
Deep learning techniques have led to state-of-the-art image super resolution with natural images.
Deep learning techniques have successfully been employed in numerous computer vision tasks including image segmentation.
Many deep learning based methods have been proposed for retinal vessel segmentation, however few of them focus on the connectivity of segmented vessels, which is quite important for a practical computer-aided diagnosis system on retinal images.
UNet, which is one of deep learning networks with an encoder-decoder architecture, is widely used in medical image segmentation.
Ranked #1 on Medical Image Segmentation on LiTS2017
In recent years, intravital skin imaging has been increasingly used in mammalian skin research to investigate cell behaviors.