Brain tumor feature extraction and edge enhancement algorithm based on U-Net network
Background: Statistics show that each year more than 100,000 patients pass away from brain tumors. Due to the diverse morphology, hazy boundaries, or unbalanced categories of medical data lesions, segmentation prediction of brain tumors has significant challenges. Purpose: In this thesis, we highlig...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-11-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S240584402309744X |
| _version_ | 1797429602302296064 |
|---|---|
| author | Dapeng Cheng Xiaolian Gao Yanyan Mao Baozhen Xiao Panlu You Jiale Gai Minghui Zhu Jialong Kang Feng Zhao Ning Mao |
| author_facet | Dapeng Cheng Xiaolian Gao Yanyan Mao Baozhen Xiao Panlu You Jiale Gai Minghui Zhu Jialong Kang Feng Zhao Ning Mao |
| author_sort | Dapeng Cheng |
| collection | DOAJ |
| description | Background: Statistics show that each year more than 100,000 patients pass away from brain tumors. Due to the diverse morphology, hazy boundaries, or unbalanced categories of medical data lesions, segmentation prediction of brain tumors has significant challenges. Purpose: In this thesis, we highlight EAV-UNet, a system designed to accurately detect lesion regions. Optimizing feature extraction, utilizing automatic segmentation techniques to detect anomalous regions, and strengthening the structure. We prioritize the segmentation problem of lesion regions, especially in cases where the margins of the tumor are more hazy. Methods: The VGG-19 network structure is incorporated into the coding stage of the U-Net, resulting in a deeper network structure, and an attention mechanism module is introduced to augment the feature information. Additionally, an edge detection module is added to the encoder to extract edge information in the image, which is then passed to the decoder to aid in reconstructing the original image. Our method uses the VGG-19 in place of the U-Net encoder. To strengthen feature details, we integrate a CBAM (Channel and Spatial Attention Mechanism) module into the decoder to enhance it. To extract vital edge details from the data, we incorporate an edge recognition section into the encoder. Results: All evaluation metrics show major improvements with our recommended EAV-UNet technique, which is based on a thorough analysis of experimental data. Specifically, for low contrast and blurry lesion edge images, the EAV-Unet method consistently produces forecasts that are very similar to the initial images. This technique reduced the Hausdorff distance to 1.82, achieved an F1 score of 96.1%, and attained a precision of 93.2% on Dataset 1. It obtained an F1 score of 76.8%, a Precision of 85.3%, and a Hausdorff distance reduction to 1.31 on Dataset 2. Dataset 3 displayed a Hausdorff distance cut in 2.30, an F1 score of 86.9%, and Precision of 95.3%. Conclusions: We conducted extensive segmentation experiments using various datasets related to brain tumors. We refined the network architecture by employing smaller convolutional kernels in our strategy. To further improve segmentation accuracy, we integrated attention modules and an edge enhancement module to reinforce edge information and boost attention scores. |
| first_indexed | 2024-03-09T09:15:30Z |
| format | Article |
| id | doaj.art-1a7c01468cec43838f13885270d2589d |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-03-09T09:15:30Z |
| publishDate | 2023-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-1a7c01468cec43838f13885270d2589d2023-12-02T07:06:06ZengElsevierHeliyon2405-84402023-11-01911e22536Brain tumor feature extraction and edge enhancement algorithm based on U-Net networkDapeng Cheng0Xiaolian Gao1Yanyan Mao2Baozhen Xiao3Panlu You4Jiale Gai5Minghui Zhu6Jialong Kang7Feng Zhao8Ning Mao9School of Computer Science and Technology, Shandong Business and Technology University, No.191 Binhai Middle Road, Yantai City, Shandong Province, Yantai, 264000, China; Shandong Co-Innovation Center of Future Intelligent Computing, No.191 Binhai Middle Road, Yantai City, Shandong Province, Yantai, 264000, China; Corresponding author at: School of Computer Science and Technology, Shandong Business and Technology University, Yantai, China.School of Computer Science and Technology, Shandong Business and Technology University, No.191 Binhai Middle Road, Yantai City, Shandong Province, Yantai, 264000, ChinaSchool of Computer Science and Technology, Shandong Business and Technology University, No.191 Binhai Middle Road, Yantai City, Shandong Province, Yantai, 264000, ChinaEarly Spring Garden Primary School, 6452 Fushou East Street, Weifang City, Shandong Province, Weifang, 261000, ChinaSchool of Computer Science and Technology, Shandong Business and Technology University, No.191 Binhai Middle Road, Yantai City, Shandong Province, Yantai, 264000, ChinaSchool of Computer Science and Technology, Shandong Business and Technology University, No.191 Binhai Middle Road, Yantai City, Shandong Province, Yantai, 264000, ChinaSchool of Computer Science and Technology, Shandong Business and Technology University, No.191 Binhai Middle Road, Yantai City, Shandong Province, Yantai, 264000, ChinaSchool of Information and Electronic Engineering, Shandong Business and Technology University, No.191 Binhai Middle Road, Yantai City, Shandong Province, Yantai, 264000, ChinaSchool of Computer Science and Technology, Shandong Business and Technology University, No.191 Binhai Middle Road, Yantai City, Shandong Province, Yantai, 264000, China; Shandong Co-Innovation Center of Future Intelligent Computing, No.191 Binhai Middle Road, Yantai City, Shandong Province, Yantai, 264000, ChinaDepartment of Radiology, Yantai Yuhuangding Hospital, No.20, Yudong Road, Yantai City, Shandong Province, Yantai, 264000, ChinaBackground: Statistics show that each year more than 100,000 patients pass away from brain tumors. Due to the diverse morphology, hazy boundaries, or unbalanced categories of medical data lesions, segmentation prediction of brain tumors has significant challenges. Purpose: In this thesis, we highlight EAV-UNet, a system designed to accurately detect lesion regions. Optimizing feature extraction, utilizing automatic segmentation techniques to detect anomalous regions, and strengthening the structure. We prioritize the segmentation problem of lesion regions, especially in cases where the margins of the tumor are more hazy. Methods: The VGG-19 network structure is incorporated into the coding stage of the U-Net, resulting in a deeper network structure, and an attention mechanism module is introduced to augment the feature information. Additionally, an edge detection module is added to the encoder to extract edge information in the image, which is then passed to the decoder to aid in reconstructing the original image. Our method uses the VGG-19 in place of the U-Net encoder. To strengthen feature details, we integrate a CBAM (Channel and Spatial Attention Mechanism) module into the decoder to enhance it. To extract vital edge details from the data, we incorporate an edge recognition section into the encoder. Results: All evaluation metrics show major improvements with our recommended EAV-UNet technique, which is based on a thorough analysis of experimental data. Specifically, for low contrast and blurry lesion edge images, the EAV-Unet method consistently produces forecasts that are very similar to the initial images. This technique reduced the Hausdorff distance to 1.82, achieved an F1 score of 96.1%, and attained a precision of 93.2% on Dataset 1. It obtained an F1 score of 76.8%, a Precision of 85.3%, and a Hausdorff distance reduction to 1.31 on Dataset 2. Dataset 3 displayed a Hausdorff distance cut in 2.30, an F1 score of 86.9%, and Precision of 95.3%. Conclusions: We conducted extensive segmentation experiments using various datasets related to brain tumors. We refined the network architecture by employing smaller convolutional kernels in our strategy. To further improve segmentation accuracy, we integrated attention modules and an edge enhancement module to reinforce edge information and boost attention scores.http://www.sciencedirect.com/science/article/pii/S240584402309744XU-NetVGG-19Attention mechanismEdge detection |
| spellingShingle | Dapeng Cheng Xiaolian Gao Yanyan Mao Baozhen Xiao Panlu You Jiale Gai Minghui Zhu Jialong Kang Feng Zhao Ning Mao Brain tumor feature extraction and edge enhancement algorithm based on U-Net network Heliyon U-Net VGG-19 Attention mechanism Edge detection |
| title | Brain tumor feature extraction and edge enhancement algorithm based on U-Net network |
| title_full | Brain tumor feature extraction and edge enhancement algorithm based on U-Net network |
| title_fullStr | Brain tumor feature extraction and edge enhancement algorithm based on U-Net network |
| title_full_unstemmed | Brain tumor feature extraction and edge enhancement algorithm based on U-Net network |
| title_short | Brain tumor feature extraction and edge enhancement algorithm based on U-Net network |
| title_sort | brain tumor feature extraction and edge enhancement algorithm based on u net network |
| topic | U-Net VGG-19 Attention mechanism Edge detection |
| url | http://www.sciencedirect.com/science/article/pii/S240584402309744X |
| work_keys_str_mv | AT dapengcheng braintumorfeatureextractionandedgeenhancementalgorithmbasedonunetnetwork AT xiaoliangao braintumorfeatureextractionandedgeenhancementalgorithmbasedonunetnetwork AT yanyanmao braintumorfeatureextractionandedgeenhancementalgorithmbasedonunetnetwork AT baozhenxiao braintumorfeatureextractionandedgeenhancementalgorithmbasedonunetnetwork AT panluyou braintumorfeatureextractionandedgeenhancementalgorithmbasedonunetnetwork AT jialegai braintumorfeatureextractionandedgeenhancementalgorithmbasedonunetnetwork AT minghuizhu braintumorfeatureextractionandedgeenhancementalgorithmbasedonunetnetwork AT jialongkang braintumorfeatureextractionandedgeenhancementalgorithmbasedonunetnetwork AT fengzhao braintumorfeatureextractionandedgeenhancementalgorithmbasedonunetnetwork AT ningmao braintumorfeatureextractionandedgeenhancementalgorithmbasedonunetnetwork |