首页|ARGA-Unet:Advanced U-net segmentation model using residual grouped convolution and attention mechanism for brain tumor MRI image segmentation

ARGA-Unet:Advanced U-net segmentation model using residual grouped convolution and attention mechanism for brain tumor MRI image segmentation

扫码查看
原文链接
  • 万方数据
Background Magnetic resonance imaging(MRI)has played an important role in the rapid growth of medical imaging diagnostic technology,especially in the diagnosis and treatment of brain tumors owing to its non-invasive characteristics and superior soft tissue contrast.However,brain tumors are characterized by high non-uniformity and non-obvious boundaries in MRI images because of their invasive and highly heterogeneous nature.In addition,the labeling of tumor areas is time-consuming and laborious.Methods To address these issues,this study uses a residual grouped convolution module,convolutional block attention module,and bilinear interpolation upsampling method to improve the classical segmentation network U-net.The influence of network normalization,loss function,and network depth on segmentation performance is further considered.Results In the experiments,the Dice score of the proposed segmentation model reached 97.581%,which is 12.438%higher than that of traditional U-net,demonstrating the effective segmentation of MRI brain tumor images.Conclusions In conclusion,we use the improved U-net network to achieve a good segmentation effect of brain tumor MRI images.

Brain tumorMRIU-netSegmentationAttention mechanismDeep learning

Siyi XUN、Yan ZHANG、Sixu DUAN、Mingwei WANG、Jiangang CHEN、Tong TONG、Qinquan GAO、Chantong LAM、Menghan HU、Tao TAN

展开 >

Faculty of Applied Sciences,Macao Polytechnic University,Macao,999078,China

Jinan Branch of China Telecom Co.Ltd.,Jinan 250000,China

School of Physics and Electronics,Shandong Normal University,Jinan 250000,China

Department of Dardiovascular Medicine,Affiliated Hospital of Hangzhou Normal University,Hangzhou 310000,China

Clinical School of Medicine,Hangzhou Normal University,Hangzhou 310000,China

Hangzhou Institute of Cardiovascular Diseases,Hangzhou 310000,China

Shanghai Key Laboratory of Multidimensional Information Processing,Shanghai 200000,China

School of Communication&Electronic Engineering,East China Normal University,Shanghai 200000,China

Engineering Research Center of Traditional Chinese Medicine Intelligent Rehabilitation,Ministry of Education,Shanghai 200000,China

College of Physics and Information Engineering,Fuzhou University,Fuzhou 350000,China

Faculty of Applied Sciences,Macao Polytechnic University,Macao 999078,China

展开 >

2024

10.1016/j.vrih.2023.05.001

虚拟现实与智能硬件(中英文)

虚拟现实与智能硬件(中英文)

ISSN：
年,卷(期)：2024.6(3)