2021
DOI: 10.1016/j.aej.2020.10.046
|View full text |Cite
|
Sign up to set email alerts
|

Efficient 3D Deep Learning Model for Medical Image Semantic Segmentation

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
36
0
2

Year Published

2021
2021
2023
2023

Publication Types

Select...
7
2
1

Relationship

0
10

Authors

Journals

citations
Cited by 95 publications
(38 citation statements)
references
References 18 publications
0
36
0
2
Order By: Relevance
“…First, 3D segmentation modeling requires more complex modeling and much higher computational resources [ 1 ], which in turn affects a modeling ability to carry out the training with large datasets. Some studies reported that 2D U-Net achieved better results than 3D U-Net’s in terms of accuracy, memory consumption, and training time [ 33 ].…”
Section: Discussionmentioning
confidence: 99%
“…First, 3D segmentation modeling requires more complex modeling and much higher computational resources [ 1 ], which in turn affects a modeling ability to carry out the training with large datasets. Some studies reported that 2D U-Net achieved better results than 3D U-Net’s in terms of accuracy, memory consumption, and training time [ 33 ].…”
Section: Discussionmentioning
confidence: 99%
“…Some researchers applied two-dimensional (2D) convolutional neural networks (CNN) to deal with liver segmentation by learning 2D context of the image (21,22). Others designed models with 3D contexts only in small voxels due to the high computation cost and memory consumption of 3D CNN (23)(24)(25). Furthermore, they used several 2D CNNs that are combined to enhance 2D contexts during the liver segmentation (26,27).…”
Section: Deep Learning Methodsmentioning
confidence: 99%
“…The DC metric [56,58,59] is expressed as Equation ( 4). This equation divides the intersection of the predicted mask N, and the original mask S times two by the sum of N and S.…”
Section: Metricsmentioning
confidence: 99%