Brain lesion image segmentation using modified U-NET architecture
Detecting stroke is important to reduce the likelihood of permanent disability and increase the chance of recovery. Brain stroke lesion segmentation is an important procedure, especially when a specific brain portion needs to be analyzed. In this project, a brain stroke lesion segmentation algorithm...
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English English |
| Published: |
Springer
2024
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/41975/1/Brain%20lesion%20image%20segmentation%20using%20modified%20U-NET.pdf http://umpir.ump.edu.my/id/eprint/41975/2/Intelligent%20Manufacturing%20and%20Mechatronics.pdf |
| _version_ | 1811138526602854400 |
|---|---|
| author | Lee, Xin Yin Mohd Jamil, Mohamed Mokhtarudin Ramli, Junid |
| author_facet | Lee, Xin Yin Mohd Jamil, Mohamed Mokhtarudin Ramli, Junid |
| author_sort | Lee, Xin Yin |
| collection | UMP |
| description | Detecting stroke is important to reduce the likelihood of permanent disability and increase the chance of recovery. Brain stroke lesion segmentation is an important procedure, especially when a specific brain portion needs to be analyzed. In this project, a brain stroke lesion segmentation algorithm using a modified U-Net (MUN) architecture will be developed. The MUN has a dimension-fusion capability, in which the images are analyzed separately using 2D U-Net and 3D image downsampling processes, before being fused at two points during the downsampling processes. The MUN accuracy is then compared with a regular 3D U-Net (UN). Three training options are further developed and compared. It is found that the MUN architecture produces higher training accuracy, but slower training duration compared to UN. Despite the capabilities of MUN, it cannot be further validated due to software limitations. Further improvement on the algorithm using other libraries is essential to enhance the capability of the MUN. |
| first_indexed | 2024-09-25T03:51:36Z |
| format | Conference or Workshop Item |
| id | UMPir41975 |
| institution | Universiti Malaysia Pahang |
| language | English English |
| last_indexed | 2024-09-25T03:51:36Z |
| publishDate | 2024 |
| publisher | Springer |
| record_format | dspace |
| spelling | UMPir419752024-07-17T04:12:02Z http://umpir.ump.edu.my/id/eprint/41975/ Brain lesion image segmentation using modified U-NET architecture Lee, Xin Yin Mohd Jamil, Mohamed Mokhtarudin Ramli, Junid QA75 Electronic computers. Computer science TJ Mechanical engineering and machinery TS Manufactures Detecting stroke is important to reduce the likelihood of permanent disability and increase the chance of recovery. Brain stroke lesion segmentation is an important procedure, especially when a specific brain portion needs to be analyzed. In this project, a brain stroke lesion segmentation algorithm using a modified U-Net (MUN) architecture will be developed. The MUN has a dimension-fusion capability, in which the images are analyzed separately using 2D U-Net and 3D image downsampling processes, before being fused at two points during the downsampling processes. The MUN accuracy is then compared with a regular 3D U-Net (UN). Three training options are further developed and compared. It is found that the MUN architecture produces higher training accuracy, but slower training duration compared to UN. Despite the capabilities of MUN, it cannot be further validated due to software limitations. Further improvement on the algorithm using other libraries is essential to enhance the capability of the MUN. Springer 2024 Conference or Workshop Item PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/41975/1/Brain%20lesion%20image%20segmentation%20using%20modified%20U-NET.pdf pdf en http://umpir.ump.edu.my/id/eprint/41975/2/Intelligent%20Manufacturing%20and%20Mechatronics.pdf Lee, Xin Yin and Mohd Jamil, Mohamed Mokhtarudin and Ramli, Junid (2024) Brain lesion image segmentation using modified U-NET architecture. In: Lecture Notes in Networks and Systems; 4th International conference on Innovative Manufacturing, Mechatronics and Materials Forum, iM3F2023 , 7 - 8 August 2023 , Pekan, Pahang. 549 -555., 850. ISSN 2367-3370 ISBN 978-981998818-1 (Published) https://doi.org/10.1007/978-981-99-8819-8_46 |
| spellingShingle | QA75 Electronic computers. Computer science TJ Mechanical engineering and machinery TS Manufactures Lee, Xin Yin Mohd Jamil, Mohamed Mokhtarudin Ramli, Junid Brain lesion image segmentation using modified U-NET architecture |
| title | Brain lesion image segmentation using modified U-NET architecture |
| title_full | Brain lesion image segmentation using modified U-NET architecture |
| title_fullStr | Brain lesion image segmentation using modified U-NET architecture |
| title_full_unstemmed | Brain lesion image segmentation using modified U-NET architecture |
| title_short | Brain lesion image segmentation using modified U-NET architecture |
| title_sort | brain lesion image segmentation using modified u net architecture |
| topic | QA75 Electronic computers. Computer science TJ Mechanical engineering and machinery TS Manufactures |
| url | http://umpir.ump.edu.my/id/eprint/41975/1/Brain%20lesion%20image%20segmentation%20using%20modified%20U-NET.pdf http://umpir.ump.edu.my/id/eprint/41975/2/Intelligent%20Manufacturing%20and%20Mechatronics.pdf |
| work_keys_str_mv | AT leexinyin brainlesionimagesegmentationusingmodifiedunetarchitecture AT mohdjamilmohamedmokhtarudin brainlesionimagesegmentationusingmodifiedunetarchitecture AT ramlijunid brainlesionimagesegmentationusingmodifiedunetarchitecture |