A Hybrid Method for Multiple Sclerosis Lesion Segmentation Using Wavelet and Dense U-Net

被引:0
作者
Alijamaat, Ali [1 ]
Mirhosseini, Seyed Mohsen [2 ]
Aliakbari, Reyhaneh [3 ]
机构
[1] Islamic Azad Univ, Dept Comp Engn, Abhar Branch, Abhar, Iran
[2] Islamic Azad Univ, Dept Comp Engn, Karaj Branch, Karaj, Iran
[3] Univ Manitoba, Coll Rehabil Sci, Dept Rehabil Sci, Winnipeg, MB, Canada
关键词
Deep learning; multiple sclerosis; U-Net; wavelet; ARCHITECTURE;
D O I
10.1142/S1469026824500081
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Multiple Sclerosis (MS) is one of the debilitating disorders of the central nervous system. This disease causes lesions in the white matter of the brain tissue. It can also lead to many physical and psychological disorders in movement, vision, and memory. Lesion segmentation in MRI images to determine the number and size of lesions is one of the diagnostic problems for specialists. Using automated diagnostic tools as an aid can help professionals. Traditional image processing and deep learning methods are used to automate lesion segmentation. The U-Net is one of the most widely used deep learning architectures for MS lesion segmentation. The images are used in the Fourier domain in the U-Net network, which does not include all its features. Our proposed method combines the HAR wavelet transform and the Dense net-based U-Net. This makes local features and lesions of different sizes more prominent and leads to higher quality segmentation. The proposed method had a better Dice value than the compared methods in the experiments.
引用
收藏
页数:11
相关论文
共 27 条
[1]  
Abadi M, 2016, PROCEEDINGS OF OSDI'16: 12TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, P265
[2]   Automatic and Robust Segmentation of Multiple Sclerosis Lesions with Convolutional Neural Networks [J].
Afzal, H. M. Rehan ;
Luo, Suhuai ;
Ramadan, Saadallah ;
Lechner-Scott, Jeannette ;
Amin, Mohammad Ruhul ;
Li, Jiaming ;
Afzal, M. Kamran .
CMC-COMPUTERS MATERIALS & CONTINUA, 2021, 66 (01) :977-991
[3]  
Alijamaat A., 2021, INT J COMPUT ASSIST, V16, P1
[4]   Multi-branch convolutional neural network for multiple sclerosis lesion segmentation [J].
Aslani, Shahab ;
Dayan, Michael ;
Storelli, Loredana ;
Filippi, Massimo ;
Murino, Vittorio ;
Rocca, Maria A. ;
Sona, Diego .
NEUROIMAGE, 2019, 196 :1-15
[5]   A multiresolution image based approach for correction of partial volume effects in emission tomography [J].
Boussion, N ;
Hatt, M ;
Lamare, F ;
Bizais, Y ;
Turzo, A ;
Rest, CCL ;
Visvikis, D .
PHYSICS IN MEDICINE AND BIOLOGY, 2006, 51 (07) :1857-1876
[6]   VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images [J].
Chen, Hao ;
Dou, Qi ;
Yu, Lequan ;
Qin, Jing ;
Heng, Pheng-Ann .
NEUROIMAGE, 2018, 170 :446-455
[7]  
García-Lorenzo D, 2009, LECT NOTES COMPUT SC, V5762, P584, DOI 10.1007/978-3-642-04271-3_71
[8]   Spatial decision forests for MS lesion segmentation in multi-channel magnetic resonance images [J].
Geremia, Ezequiel ;
Clatz, Olivier ;
Menze, Bjoern H. ;
Konukoglu, Ender ;
Criminisi, Antonio ;
Ayache, Nicholas .
NEUROIMAGE, 2011, 57 (02) :378-390
[9]  
Ghosal P, 2019, 2019 FIFTH INTERNATIONAL CONFERENCE ON IMAGE INFORMATION PROCESSING (ICIIP 2019), P526, DOI 10.1109/ICIIP47207.2019.8985674
[10]   Multi-scale classification of disease using structural MRI and wavelet transform [J].
Hackmack, Kerstin ;
Paul, Friedemann ;
Weygandt, Martin ;
Allefeld, Carsten ;
Haynes, John-Dylan .
NEUROIMAGE, 2012, 62 (01) :48-58