A Spatio-Temporal Fully Convolutional Network for Breast Lesion Segmentation in DCE-MRI

2018 ◽  
pp. 358-368 ◽  
Author(s):  
Mingjian Chen ◽  
Hao Zheng ◽  
Changsheng Lu ◽  
Enmei Tu ◽  
Jie Yang ◽  
...  
Keyword(s):  
Breast Lesion ◽  
Lesion Segmentation ◽  
Convolutional Network ◽  
Fully Convolutional Network ◽  
Dce Mri ◽  
Spatio Temporal

Breast Lesion Segmentation in DCE- MRI Imaging

2018 ◽  
Author(s):  
Mariusz Frackiewicz ◽  
Zuzanna Koper ◽  
Henryk Palus ◽  
Damian Borys ◽  
Krzysztof Psiuk-Maksymowicz
Keyword(s):  
Breast Lesion ◽  
Mri Imaging ◽  
Lesion Segmentation ◽  
Dce Mri

scholarly journals Improved U-Net: Fully Convolutional Network Model for Skin-Lesion Segmentation

2020 ◽  
Vol 10 (10) ◽  
pp. 3658
Author(s):  
Karshiev Sanjar ◽  
Olimov Bekhzod ◽  
Jaeil Kim ◽  
Jaesoo Kim ◽  
Anand Paul ◽  
...  
Keyword(s):  
Skin Lesion ◽  
Interpolation Method ◽  
Medical Personnel ◽  
Activation Function ◽  
Lesion Segmentation ◽  
Bilinear Interpolation ◽  
Convolutional Network ◽  
Fully Convolutional Network ◽  
Computer Vision Applications ◽  
Parametric Rectified Linear Unit

The early and accurate diagnosis of skin cancer is crucial for providing patients with advanced treatment by focusing medical personnel on specific parts of the skin. Networks based on encoder–decoder architectures have been effectively implemented for numerous computer-vision applications. U-Net, one of CNN architectures based on the encoder–decoder network, has achieved successful performance for skin-lesion segmentation. However, this network has several drawbacks caused by its upsampling method and activation function. In this paper, a fully convolutional network and its architecture are proposed with a modified U-Net, in which a bilinear interpolation method is used for upsampling with a block of convolution layers followed by parametric rectified linear-unit non-linearity. To avoid overfitting, a dropout is applied after each convolution block. The results demonstrate that our recommended technique achieves state-of-the-art performance for skin-lesion segmentation with 94% pixel accuracy and a 88% dice coefficient, respectively.

PsLSNet: Automated psoriasis skin lesion segmentation using modified U-Net-based fully convolutional network

2019 ◽  
Vol 52 ◽  
pp. 226-237 ◽  
Author(s):  
Manoranjan Dash ◽  
Narendra D. Londhe ◽  
Subhojit Ghosh ◽  
Ashish Semwal ◽  
Rajendra S. Sonawane
Keyword(s):  
Skin Lesion ◽  
Lesion Segmentation ◽  
Convolutional Network ◽  
Fully Convolutional Network

scholarly journals Dense pooling layers in fully convolutional network for skin lesion segmentation

2019 ◽  
Vol 78 ◽  
pp. 101658 ◽  
Author(s):  
Ebrahim Nasr-Esfahani ◽  
Shima Rafiei ◽  
Mohammad H. Jafari ◽  
Nader Karimi ◽  
James S. Wrobel ◽  
...  
Keyword(s):  
Skin Lesion ◽  
Lesion Segmentation ◽  
Convolutional Network ◽  
Fully Convolutional Network

Mixed 2D and 3D convolutional network with multi-scale context for lesion segmentation in breast DCE-MRI

2021 ◽  
Vol 68 ◽  
pp. 102607
Author(s):  
Hongyu Wang ◽  
Jiaqi Cao ◽  
Jun Feng ◽  
Yilin Xie ◽  
Di Yang ◽  
...  
Keyword(s):  
Lesion Segmentation ◽  
Convolutional Network ◽  
Dce Mri ◽  
Multi Scale ◽  
2D And 3D
Sign in / Sign up

Export Citation Format

Share Document