Filters








14,457 Hits in 4.2 sec

MSU-Net: Multi-Scale U-Net for 2D Medical Image Segmentation

Run Su, Deyun Zhang, Jinhuai Liu, Chuandong Cheng
2021 Frontiers in Genetics  
Aiming at the limitation of the convolution kernel with a fixed receptive field and unknown prior to optimal network width in U-Net, multi-scale U-Net (MSU-Net) is proposed by us for medical image segmentation  ...  In addition, the multi-scale block is extended to other variants of the original U-Net to verify its universality. Five different medical image segmentation datasets are used to evaluate MSU-Net.  ...  ACKNOWLEDGMENTS The authors express their sincere gratitude to the creator of the public dataset for many valuable discussions and educational help in the growing field of medical image analysis.  ... 
doi:10.3389/fgene.2021.639930 pmid:33679900 pmcid:PMC7928319 fatcat:6xywspboybaprnmygz5ufahra4

SA-Net: A scale-attention network for medical image segmentation

Jingfei Hu, Hua Wang, Jie Wang, Yunqi Wang, Fang He, Jicong Zhang
2021 PLoS ONE  
SA-Net can better learn the multi-scale features and achieve more accurate segmentation for different medical image. In addition, this work validates the proposed method across multiple datasets.  ...  Based on exploratory experiments, features at multiple scales have been found to be of great importance for the segmentation of medical images.  ...  Therefore, design good multi-scale features for medical images segmentation is essential.  ... 
doi:10.1371/journal.pone.0247388 pmid:33852577 pmcid:PMC8046243 fatcat:zme55aqkunezzn45yr33ug5x74

Fabric Image Representation Encoding Networks for Large-scale 3D Medical Image Analysis [article]

Siyu Liu, Wei Dai, Craig Engstrom, Jurgen Fripp, Peter B. Greer, Stuart Crozier, Jason A. Dowling, Shekhar S. Chandra
2020 arXiv   pre-print
FIRENet was trained for feature learning via automated semantic segmentation of pelvic structures and obtained a state-of-the-art median DSC score of 0.867.  ...  The lack of large-scale labelled 3D medical imaging datasets restrict constructing such generalised networks.  ...  field sizes for multi-scale feature extraction.  ... 
arXiv:2006.15578v2 fatcat:txa2zt4d35dg3apyecnsoglliy

C2FTrans: Coarse-to-Fine Transformers for Medical Image Segmentation [article]

Xian Lin, Li Yu, Kwang-Ting Cheng, Zengqiang Yan
2022 arXiv   pre-print
To address this problem, we propose C2FTrans, a novel multi-scale architecture that formulates medical image segmentation as a coarse-to-fine procedure.  ...  Convolutional neural networks (CNN), the most prevailing architecture for deep-learning based medical image analysis, are still functionally limited by their intrinsic inductive biases and inadequate receptive  ...  for medical image segmentation.  ... 
arXiv:2206.14409v2 fatcat:gfmmolmiefbnhbsruu2nezba2e

DDNet: 3D densely connected convolutional networks with feature pyramids for nasopharyngeal carcinoma segmentation

Xiaojie Li, Mingxuan Tang, Feng Guo, Yuanxi Li, Kunling Cao, Qi Song, Xi Wu, Shanhui Sun, Jiliu Zhou
2021 IET Image Processing  
In this paper, we propose a threedimensional densely connected convolutional neural network with multi-scale feature pyramids for NPC segmentation.  ...  The concatenated pyramid feature carries multi-scale and hierarchical semantic information which is effective for segmenting different size of tumors and perceiving hierarchical context information.  ...  Considering the specific characteristics of medical images, a general framework is required for medical image data.  ... 
doi:10.1049/ipr2.12248 fatcat:n7bghjcc2vfoxal4kcftfto5am

Learning U-Net Based Multi-Scale Features in Encoding-Decoding for MR Image Brain Tissue Segmentation

Jiao-Song Long, Guang-Zhi Ma, En-Min Song, Ren-Chao Jin
2021 Sensors  
Therefore, it can be a useful tool for diagnostic applications, such as brain MRI segmentation and diagnosing.  ...  As an excellent convolutional neural network (CNN), U-Net is widely used in MR image segmentation as it usually generates high-precision features.  ...  For the latter, mainstream methods [21, 22] adopt multiple rates of atrous convolution with a larger receptive field to harness multi-scale context information.  ... 
doi:10.3390/s21093232 pmid:34067101 fatcat:ns243edwgjfv7jhnwxus4jd2gm

CE-Net: Context Encoder Network for 2D Medical Image Segmentation

Zaiwang Gu, Jun Cheng, Huazhu Fu, Kang Zhou, Huaying Hao, Yitian Zhao, Tianyang Zhang, Shenghua Gao, Jiang Liu
2019 IEEE Transactions on Medical Imaging  
With the rapid development of a convolutional neural network in image processing, deep learning has been used for medical image segmentation, such as optic disc segmentation, blood vessel detection, lung  ...  Medical image segmentation is an important step in medical image analysis.  ...  Earlier deep learning approaches for medical image segmentation are mostly based on image patches. Ciresan et al.  ... 
doi:10.1109/tmi.2019.2903562 pmid:30843824 fatcat:b7p7plxshfhfrk76z76v6pvvyu

Pyramid Medical Transformer for Medical Image Segmentation [article]

Zhuangzhuang Zhang, Weixiong Zhang
2022 arXiv   pre-print
Deep neural networks have been a prevailing technique in the field of medical image processing.  ...  To address these issues, we developed a novel method to integrate multi-scale attention and CNN feature extraction using a pyramidal network architecture, namely Pyramid Medical Transformer (PMTrans).  ...  We propose a novel, pyramid medical transformer (PMTrans) approach that explores and incorporates multi-resolution attention.  ... 
arXiv:2104.14702v3 fatcat:gaur4ehgarhl7aaosnjbgfuu5m

Multi-Scale Fusion U-Net for the Segmentation of Breast Lesions

Jingyao Li, Lianglun Cheng, Tingjian Xia, Haomin Ni, Jiao Li
2021 IEEE Access  
INDEX TERMS Breast cancer, deep learning, image segmentation, multi-scale feature, wavelet transform.  ...  Moreover, there are some convolutional layers with different receptive fields in MDCM, which improves the network's ability to extract multi-scale features.  ...  In addition, due to the scarcity of medical image data, transfer learning has been applied to the field of medical image processing by many scholars.  ... 
doi:10.1109/access.2021.3117578 fatcat:34zlsm37rrca3n2h5m7q62fawy

Segmentation of Head and Neck Tumours Using Modified U-net

Baixiang Zhao, John Soraghan, Gaetano Di Caterina, Derek Grose
2019 2019 27th European Signal Processing Conference (EUSIPCO)  
In this work, the dilated convolution is introduced into U-net, to obtain larger receptive field so that extract multi-scale features.  ...  A new neural network for automatic head and neck cancer (HNC) segmentation from magnetic resonance imaging (MRI) is presented.  ...  Also, from the review of deep learning research on medical image [9] , currently no efficient deep learning approach is applied on head and neck cancer segmentation.  ... 
doi:10.23919/eusipco.2019.8902637 dblp:conf/eusipco/ZhaoSCG19 fatcat:sfktjzeejrbajgsffud4hfoybm

How to improve the deep residual network to segment multi-modal brain tumor images

Yi Ding, Chang Li, Qiqi Yang, Zhen Qin, Zhiguang Qin
2019 IEEE Access  
INDEX TERMS Multi-modal brain tumor segmentation, BRATS2015, deep learning, middle supervision.  ...  It can solve the problem of vanishing gradient and increase the receptive field without reducing the resolution.  ...  [11] proposed a 3D multi-scale CNN for brain tumor segmentation, and a 3D Conditional Random Fields(CRF) to optimize the softmax probability maps. Zhao et al.  ... 
doi:10.1109/access.2019.2948120 fatcat:u6hw5ilhvfecrf3teaqxehotse

MISSU: 3D Medical Image Segmentation via Self-distilling TransUNet [article]

Nan Wang, Shaohui Lin, Xiaoxiao Li, Ke Li, Yunhang Shen, Yue Gao, Lizhuang Ma
2022 arXiv   pre-print
To this end, we propose to self-distill a Transformer-based UNet for medical image segmentation, which simultaneously learns global semantic information and local spatial-detailed features.  ...  This motivates us to design the efficiently Transformer-based UNet model and study the feasibility of Transformer-based network architectures for medical image segmentation tasks.  ...  RELATED WORK A. Medical image segmentation As discussed in Sec. I, local-to-global feature modeling is essential for medical image segmentation.  ... 
arXiv:2206.00902v1 fatcat:earitthqrvgntoxmunjvlj22mi

UXNet: Searching Multi-level Feature Aggregation for 3D Medical Image Segmentation [article]

Yuanfeng Ji, Ruimao Zhang, Zhen Li, Jiamin Ren, Shaoting Zhang, Ping Luo
2020 arXiv   pre-print
Aggregating multi-level feature representation plays a critical role in achieving robust volumetric medical image segmentation, which is important for the auxiliary diagnosis and treatment.  ...  proposes a novel NAS method for 3D medical image segmentation, named UXNet, which searches both the scale-wise feature aggregation strategies as well as the block-wise operators in the encoder-decoder  ...  have various size of 3D receptive field capturing the multi-scale context.  ... 
arXiv:2009.07501v1 fatcat:e7myaq2hqrcm3dzbmu6cwq2oom

Cascaded atrous convolution and spatial pyramid pooling for more accurate tumor target segmentation for rectal cancer radiotherapy

Kuo Men, Pamela Boimel, James Janopaul-Naylor, Haoyu Zhong, Mi Huang, Huaizhi Geng, Chingyun Cheng, Yong Fan, John P Plastaras, Edgar Ben-Josef, Ying Xiao
2018 Physics in Medicine and Biology  
In conclusion, the proposed CAC-SPP which could extract high-resolution features with large receptive fields and capture multi-scale context yields improve the accuracy of segmentation performance for  ...  Convolutional neural networks (CNN) has become the state-of-the-art method for medical segmentation.  ...  These modifications can extract high-resolution features with large receptive fields and capture multi-scale contextual information.  ... 
doi:10.1088/1361-6560/aada6c pmid:30109986 pmcid:PMC6207191 fatcat:poroieosqncphf5hsey5ud2h4y

Quadruple Augmented Pyramid Network for Multi-class COVID-19 Segmentation via CT [article]

Ziyang Wang, Irina Voiculescu
2021 arXiv   pre-print
information for semantic segmentation.  ...  In this paper, a multi-class COVID-19 CT segmentation is proposed aiming at helping radiologists estimate the extent of effected lung volume.  ...  In this work, we propose a novel Quadruple Augmented Pyramid Network(QAP-Net) for multi-class COVID-19 segmentation.  ... 
arXiv:2103.05546v2 fatcat:jbvap4cf4nhybct5ijsevu27f4
« Previous Showing results 1 — 15 out of 14,457 results