Authors :
Muhammad Zubair Khan
Volume/Issue :
Volume 6 - 2021, Issue 4 - April
Google Scholar :
http://bitly.ws/9nMw
Scribd :
https://bit.ly/3gghmaL
Abstract :
Alom et al. in their article with
title Recurrent Residual U-Net for Medical Image
Segmentation, published in March 2019 in Journal of
Medical Imaging, proposed two deep network
architectures for medical image semantic segmentation
[1]. These models are evaluated using existing
benchmark medical image datasets. This work aims to
penetrate the deep learning concept in medicine to
minimize human intervention in medical diagnosis. To
achieve this goal, the author utilized the power of
existing state-of-the-art deep network architectures
designed for medical image segmentation, including UNET, residual network, and recurrent convolutional
neural network. It is found that deep learning generally
anddefined deep neural architectures particularly has an
enormous impact to accurately perform medical image
analysis.
Keywords :
Deep Learning, Critical Review, Image Segmenta- Tion, Convolution Neural Network Sequence.
Alom et al. in their article with
title Recurrent Residual U-Net for Medical Image
Segmentation, published in March 2019 in Journal of
Medical Imaging, proposed two deep network
architectures for medical image semantic segmentation
[1]. These models are evaluated using existing
benchmark medical image datasets. This work aims to
penetrate the deep learning concept in medicine to
minimize human intervention in medical diagnosis. To
achieve this goal, the author utilized the power of
existing state-of-the-art deep network architectures
designed for medical image segmentation, including UNET, residual network, and recurrent convolutional
neural network. It is found that deep learning generally
anddefined deep neural architectures particularly has an
enormous impact to accurately perform medical image
analysis.
Keywords :
Deep Learning, Critical Review, Image Segmenta- Tion, Convolution Neural Network Sequence.
