Brain MRI sequence and view plane identification using deep learning
Brain magnetic resonance imaging (MRI) scans are available in a wide variety of sequences, view planes, and magnet strengths. A necessary preprocessing step for any automated diagnosis is to identify the MRI sequence, view plane, and magnet strength of the acquired image. Automatic identification of...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-04-01
|
| Series: | Frontiers in Neuroinformatics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fninf.2024.1373502/full |
| _version_ | 1797197031688634368 |
|---|---|
| author | Syed Saad Azhar Ali |
| author_facet | Syed Saad Azhar Ali |
| author_sort | Syed Saad Azhar Ali |
| collection | DOAJ |
| description | Brain magnetic resonance imaging (MRI) scans are available in a wide variety of sequences, view planes, and magnet strengths. A necessary preprocessing step for any automated diagnosis is to identify the MRI sequence, view plane, and magnet strength of the acquired image. Automatic identification of the MRI sequence can be useful in labeling massive online datasets used by data scientists in the design and development of computer aided diagnosis (CAD) tools. This paper presents a deep learning (DL) approach for brain MRI sequence and view plane identification using scans of different data types as input. A 12-class classification system is presented for commonly used MRI scans, including T1, T2-weighted, proton density (PD), fluid attenuated inversion recovery (FLAIR) sequences in axial, coronal and sagittal view planes. Multiple online publicly available datasets have been used to train the system, with multiple infrastructures. MobileNet-v2 offers an adequate performance accuracy of 99.76% with unprocessed MRI scans and a comparable accuracy with skull-stripped scans and has been deployed in a tool for public use. The tool has been tested on unseen data from online and hospital sources with a satisfactory performance accuracy of 99.84 and 86.49%, respectively. |
| first_indexed | 2024-04-24T06:37:30Z |
| format | Article |
| id | doaj.art-3ed534b857ff4075b58fcfb8fd7eec50 |
| institution | Directory Open Access Journal |
| issn | 1662-5196 |
| language | English |
| last_indexed | 2024-04-24T06:37:30Z |
| publishDate | 2024-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroinformatics |
| spelling | doaj.art-3ed534b857ff4075b58fcfb8fd7eec502024-04-23T04:26:52ZengFrontiers Media S.A.Frontiers in Neuroinformatics1662-51962024-04-011810.3389/fninf.2024.13735021373502Brain MRI sequence and view plane identification using deep learningSyed Saad Azhar AliBrain magnetic resonance imaging (MRI) scans are available in a wide variety of sequences, view planes, and magnet strengths. A necessary preprocessing step for any automated diagnosis is to identify the MRI sequence, view plane, and magnet strength of the acquired image. Automatic identification of the MRI sequence can be useful in labeling massive online datasets used by data scientists in the design and development of computer aided diagnosis (CAD) tools. This paper presents a deep learning (DL) approach for brain MRI sequence and view plane identification using scans of different data types as input. A 12-class classification system is presented for commonly used MRI scans, including T1, T2-weighted, proton density (PD), fluid attenuated inversion recovery (FLAIR) sequences in axial, coronal and sagittal view planes. Multiple online publicly available datasets have been used to train the system, with multiple infrastructures. MobileNet-v2 offers an adequate performance accuracy of 99.76% with unprocessed MRI scans and a comparable accuracy with skull-stripped scans and has been deployed in a tool for public use. The tool has been tested on unseen data from online and hospital sources with a satisfactory performance accuracy of 99.84 and 86.49%, respectively.https://www.frontiersin.org/articles/10.3389/fninf.2024.1373502/fullbrain MRIsequence identificationview planedeep learningcomputer aided diagnosisassistive tool |
| spellingShingle | Syed Saad Azhar Ali Brain MRI sequence and view plane identification using deep learning Frontiers in Neuroinformatics brain MRI sequence identification view plane deep learning computer aided diagnosis assistive tool |
| title | Brain MRI sequence and view plane identification using deep learning |
| title_full | Brain MRI sequence and view plane identification using deep learning |
| title_fullStr | Brain MRI sequence and view plane identification using deep learning |
| title_full_unstemmed | Brain MRI sequence and view plane identification using deep learning |
| title_short | Brain MRI sequence and view plane identification using deep learning |
| title_sort | brain mri sequence and view plane identification using deep learning |
| topic | brain MRI sequence identification view plane deep learning computer aided diagnosis assistive tool |
| url | https://www.frontiersin.org/articles/10.3389/fninf.2024.1373502/full |
| work_keys_str_mv | AT syedsaadazharali brainmrisequenceandviewplaneidentificationusingdeeplearning |