2023
DOI: 10.3390/bioengineering10010119
|View full text |Cite
|
Sign up to set email alerts
|

U-Net Model with Transfer Learning Model as a Backbone for Segmentation of Gastrointestinal Tract

Abstract: The human gastrointestinal (GI) tract is an important part of the body. According to World Health Organization (WHO) research, GI tract infections kill 1.8 million people each year. In the year 2019, almost 5 million individuals were detected with gastrointestinal disease. Radiation therapy has the potential to improve cure rates in GI cancer patients. Radiation oncologists direct x-ray beams at the tumour while avoiding the stomach and intestines. The current objective is to direct the x-ray beam toward the m… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
15
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
6
1
1

Relationship

1
7

Authors

Journals

citations
Cited by 35 publications
(15 citation statements)
references
References 29 publications
0
15
0
Order By: Relevance
“…Moreover, many research studies have found that EfficientNet is more effective and accurate than others. This has been observed in various fields such as medical (Zhou et al 2022 ; Sharma et al 2023 ) as well as engineering (Nguon et al 2022 ; Jin et al 2022 ).…”
Section: Resultsmentioning
confidence: 81%
See 1 more Smart Citation
“…Moreover, many research studies have found that EfficientNet is more effective and accurate than others. This has been observed in various fields such as medical (Zhou et al 2022 ; Sharma et al 2023 ) as well as engineering (Nguon et al 2022 ; Jin et al 2022 ).…”
Section: Resultsmentioning
confidence: 81%
“…Moreover, the U-Net architecture is famous for the application of the ready frameworks model as an encoder and a decoder(Costa et al 2021 ). Particularly EfficientNet is a convenient architecture that can be adopted as an encoder of the U-Net architecture and allows it to reach higher accuracy within the limited number of the dataset (Nguon et al 2022 ; Sharma et al 2023 ).…”
Section: Introductionmentioning
confidence: 99%
“…The advantages of accurate segmentation of tiny targets and its adaptive network structure are shown by the U-Net framework, which was developed in 2015 ( 37 ). The incorporation of a U-Net as a deep learning model in diverse medical applications ( 39–44 ) has served as a prominent trigger for the motivation behind this investigation. The utilization of U-Net has been widely observed in wound segmentation.…”
Section: Discussionmentioning
confidence: 99%
“…Various techniques have been employed, including UNet with an attention mechanism [ 43 ], Levit-UNet++ [ 44 ], a combination of UNet and Mask RCNN [ 45 ], Multiview UNet [ 46 ], and an Ensemble Model [ 47 ], each achieving different levels of segmentation accuracy with Dice values ranging from 0.36 to 0.88. More recent approaches in 2023 include FPN+Efficient Net B0 [ 47 ] with a Dice coefficient of 0.8975, UNet model [ 48 ] with a Dice coefficient of 0.8854, and PSPNet+ResNet 34 [ 49 ] with a Dice coefficient of 0.8842. The UMobileNet V2 Model, featuring a MobileNetV2 encoder embedded within a UNet architecture, outperforms previous methods with a Dice coefficient of 0.8984, demonstrating promising results in segmenting gastrointestinal structures in the specified dataset.…”
Section: State-of-the-art Comparisonmentioning
confidence: 99%