Challenges and Recent Solutions for Image Segmentation in the Era of Deep Learning

被引:63
作者
Goceri, Evgin [1 ]
机构
[1] Akdeniz Univ, Engn Fac, Dept Biomed Engn, Antalya, Turkey
来源
2019 NINTH INTERNATIONAL CONFERENCE ON IMAGE PROCESSING THEORY, TOOLS AND APPLICATIONS (IPTA) | 2019年
关键词
CNN; deep learning; image segmentation; neural networks; transfer learning; NEURAL-NETWORK; MRI; CNN; EXTRACTION;
D O I
10.1109/ipta.2019.8936087
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Image segmentation has a key role in computer vision and image processing. Superiority of deep learning based segmentation techniques has been shown in various studies in the literature. However, there are challenging issues affecting performances of these methods. Therefore, in this paper, these challenges that are mostly related to architecture and training of deep neural networks are explained. In addition, the state-of-the-art solutions applied in the literature are presented to help researchers to design proper network architectures according to their problems and to be aware of possible challenging issues and recent solutions.
引用
收藏
页数:6
相关论文
共 91 条
[1]   Recurrent residual U-Net for medical image segmentation [J].
Alom, Md Zahangir ;
Yakopcic, Chris ;
Hasan, Mahmudul ;
Taha, Tarek M. ;
Asari, Vijayan K. .
JOURNAL OF MEDICAL IMAGING, 2019, 6 (01)
[2]   Lung Nodule Detection using 3D Convolutional Neural Networks Trained on Weakly Labeled Data [J].
Anirudhi, Rushil ;
Thiagarajan, Jayaraman J. ;
Bremer, Timo ;
Kim, Hyojin .
MEDICAL IMAGING 2016: COMPUTER-AIDED DIAGNOSIS, 2015, 9785
[3]  
[Anonymous], 2017, P IEEE C COMP VIS PA
[4]  
[Anonymous], SPIE MED IMAGING ORL
[5]  
[Anonymous], ARXIV190510268V1
[6]  
[Anonymous], SPIE MED IMAGING COM
[7]  
[Anonymous], 2015, ARXIV151100561
[8]  
[Anonymous], P COMP VIS PATT REC
[9]  
[Anonymous], 2017, LUNG CANC
[10]  
[Anonymous], MICCAI BRATS