Magnetic resonance imaging image-based segmentation of brain tumor using the modified transfer learning method
Purpose: The goal of this study was to improve overall brain tumor segmentation (BraTS) accuracy. In this study, a form of convolutional neural network called three-dimensional (3D) U-Net was utilized to segment various tumor regions on brain 3D magnetic resonance imaging images using a transfer lea...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wolters Kluwer Medknow Publications
2022-01-01
|
| Series: | Journal of Medical Physics |
| Subjects: | |
| Online Access: | http://www.jmp.org.in/article.asp?issn=0971-6203;year=2022;volume=47;issue=4;spage=315;epage=321;aulast=Singh |
| _version_ | 1797904834552135680 |
|---|---|
| author | Sandeep Singh Benoy Kumar Singh Anuj Kumar |
| author_facet | Sandeep Singh Benoy Kumar Singh Anuj Kumar |
| author_sort | Sandeep Singh |
| collection | DOAJ |
| description | Purpose: The goal of this study was to improve overall brain tumor segmentation (BraTS) accuracy. In this study, a form of convolutional neural network called three-dimensional (3D) U-Net was utilized to segment various tumor regions on brain 3D magnetic resonance imaging images using a transfer learning technique. Materials and Methods: The dataset used for this study was obtained from the multimodal BraTS challenge. The total number of studies was 2240, obtained from BraTS 2018, BraTS 2019, BraTS 2020, and BraTS 2021 challenges, and each study had five series: T1, contrast-enhanced-T1, Flair, T2, and segmented mask file (seg), all in Neuroimaging Informatics Technology Initiative (NIFTI) format. The proposed method employs a 3D U-Net that was trained separately on each of the four datasets by transferring weights across them. Results: The overall training accuracy, validation accuracy, mean dice coefficient, and mean intersection over union achieved were 99.35%, 98.93%, 0.9875%, and 0.8738%, respectively. Conclusion: The proposed method for tumor segmentation outperforms the existing method. |
| first_indexed | 2024-04-10T09:55:14Z |
| format | Article |
| id | doaj.art-47ed389a52b44d3e87bd8bea83d82068 |
| institution | Directory Open Access Journal |
| issn | 0971-6203 1998-3913 |
| language | English |
| last_indexed | 2024-04-10T09:55:14Z |
| publishDate | 2022-01-01 |
| publisher | Wolters Kluwer Medknow Publications |
| record_format | Article |
| series | Journal of Medical Physics |
| spelling | doaj.art-47ed389a52b44d3e87bd8bea83d820682023-02-16T12:33:57ZengWolters Kluwer Medknow PublicationsJournal of Medical Physics0971-62031998-39132022-01-0147431532110.4103/jmp.jmp_52_22Magnetic resonance imaging image-based segmentation of brain tumor using the modified transfer learning methodSandeep SinghBenoy Kumar SinghAnuj KumarPurpose: The goal of this study was to improve overall brain tumor segmentation (BraTS) accuracy. In this study, a form of convolutional neural network called three-dimensional (3D) U-Net was utilized to segment various tumor regions on brain 3D magnetic resonance imaging images using a transfer learning technique. Materials and Methods: The dataset used for this study was obtained from the multimodal BraTS challenge. The total number of studies was 2240, obtained from BraTS 2018, BraTS 2019, BraTS 2020, and BraTS 2021 challenges, and each study had five series: T1, contrast-enhanced-T1, Flair, T2, and segmented mask file (seg), all in Neuroimaging Informatics Technology Initiative (NIFTI) format. The proposed method employs a 3D U-Net that was trained separately on each of the four datasets by transferring weights across them. Results: The overall training accuracy, validation accuracy, mean dice coefficient, and mean intersection over union achieved were 99.35%, 98.93%, 0.9875%, and 0.8738%, respectively. Conclusion: The proposed method for tumor segmentation outperforms the existing method.http://www.jmp.org.in/article.asp?issn=0971-6203;year=2022;volume=47;issue=4;spage=315;epage=321;aulast=Singhconvolutional neural networksdeep learningtransfer learningthree-dimensional image processing |
| spellingShingle | Sandeep Singh Benoy Kumar Singh Anuj Kumar Magnetic resonance imaging image-based segmentation of brain tumor using the modified transfer learning method Journal of Medical Physics convolutional neural networks deep learning transfer learning three-dimensional image processing |
| title | Magnetic resonance imaging image-based segmentation of brain tumor using the modified transfer learning method |
| title_full | Magnetic resonance imaging image-based segmentation of brain tumor using the modified transfer learning method |
| title_fullStr | Magnetic resonance imaging image-based segmentation of brain tumor using the modified transfer learning method |
| title_full_unstemmed | Magnetic resonance imaging image-based segmentation of brain tumor using the modified transfer learning method |
| title_short | Magnetic resonance imaging image-based segmentation of brain tumor using the modified transfer learning method |
| title_sort | magnetic resonance imaging image based segmentation of brain tumor using the modified transfer learning method |
| topic | convolutional neural networks deep learning transfer learning three-dimensional image processing |
| url | http://www.jmp.org.in/article.asp?issn=0971-6203;year=2022;volume=47;issue=4;spage=315;epage=321;aulast=Singh |
| work_keys_str_mv | AT sandeepsingh magneticresonanceimagingimagebasedsegmentationofbraintumorusingthemodifiedtransferlearningmethod AT benoykumarsingh magneticresonanceimagingimagebasedsegmentationofbraintumorusingthemodifiedtransferlearningmethod AT anujkumar magneticresonanceimagingimagebasedsegmentationofbraintumorusingthemodifiedtransferlearningmethod |