Autoencoder-Driven Fiducial Landmark Identification in 3D Brain MRI for Neuroimaging Alignment
Accurate identification of fiducial markers, such as the left pre-auricle (LPA), right pre-auricle (RPA), and nasion, is critical for head localization, source reconstruction, anatomical alignment, and ensuring reproducibility in functional and structural neuroimaging studies. However, manual annota...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11048582/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839648891333509120 |
|---|---|
| author | G. Deepali H. Anitha B. P. Swathi M. V. Suhas |
| author_facet | G. Deepali H. Anitha B. P. Swathi M. V. Suhas |
| author_sort | G. Deepali |
| collection | DOAJ |
| description | Accurate identification of fiducial markers, such as the left pre-auricle (LPA), right pre-auricle (RPA), and nasion, is critical for head localization, source reconstruction, anatomical alignment, and ensuring reproducibility in functional and structural neuroimaging studies. However, manual annotation of these landmarks is time-consuming, prone to human error, and further complicated by variations in MRI acquisition protocols and incomplete head coverage. In this work, we propose a deep learning-based framework using autoencoders to automatically detect fiducial markers in 3D brain MRI scans. The method integrates a structured preprocessing pipeline, including intensity normalization, spatial resampling, and noise reduction, to ensure data consistency. A tailored autoencoder architecture is then trained to reconstruct MRI slices while learning the spatial characteristics of MRI slices at fiducial points across axial, coronal, and sagittal planes. Fiducial localization is determined based on the slice with the lowest reconstruction error, ensuring precise identification. Our approach significantly enhances registration accuracy, achieving an average ground truth Euclidean distance of 1.42 mm for LPA and 1.89 mm for RPA, with low variance across a dataset of 500 MRI volumes. The results demonstrate that automated fiducial detection can reduce manual intervention, improve anatomical alignment, and enhance the robustness of neuroimaging workflows. This method offers a scalable and efficient solution for clinical and research applications, facilitating more reliable head modeling, source localization, and multimodal image integration. |
| format | Article |
| id | doaj-art-64f1d4a642b6491e90ec7a64c01d37f6 |
| institution | Matheson Library |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-64f1d4a642b6491e90ec7a64c01d37f62025-06-27T23:00:37ZengIEEEIEEE Access2169-35362025-01-011310895510896710.1109/ACCESS.2025.358227311048582Autoencoder-Driven Fiducial Landmark Identification in 3D Brain MRI for Neuroimaging AlignmentG. Deepali0H. Anitha1https://orcid.org/0000-0001-5898-4442B. P. Swathi2https://orcid.org/0000-0002-6708-6385M. V. Suhas3https://orcid.org/0000-0002-5337-7157Department of Electronics and Communication Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, IndiaSchool of Computer Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, IndiaSchool of Computer Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, IndiaDepartment of Electronics and Communication Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, IndiaAccurate identification of fiducial markers, such as the left pre-auricle (LPA), right pre-auricle (RPA), and nasion, is critical for head localization, source reconstruction, anatomical alignment, and ensuring reproducibility in functional and structural neuroimaging studies. However, manual annotation of these landmarks is time-consuming, prone to human error, and further complicated by variations in MRI acquisition protocols and incomplete head coverage. In this work, we propose a deep learning-based framework using autoencoders to automatically detect fiducial markers in 3D brain MRI scans. The method integrates a structured preprocessing pipeline, including intensity normalization, spatial resampling, and noise reduction, to ensure data consistency. A tailored autoencoder architecture is then trained to reconstruct MRI slices while learning the spatial characteristics of MRI slices at fiducial points across axial, coronal, and sagittal planes. Fiducial localization is determined based on the slice with the lowest reconstruction error, ensuring precise identification. Our approach significantly enhances registration accuracy, achieving an average ground truth Euclidean distance of 1.42 mm for LPA and 1.89 mm for RPA, with low variance across a dataset of 500 MRI volumes. The results demonstrate that automated fiducial detection can reduce manual intervention, improve anatomical alignment, and enhance the robustness of neuroimaging workflows. This method offers a scalable and efficient solution for clinical and research applications, facilitating more reliable head modeling, source localization, and multimodal image integration.https://ieeexplore.ieee.org/document/11048582/Fiducial marker detection3D brain MRIMEG-MRI registrationautoencoderdeep learninganatomical landmark localization |
| spellingShingle | G. Deepali H. Anitha B. P. Swathi M. V. Suhas Autoencoder-Driven Fiducial Landmark Identification in 3D Brain MRI for Neuroimaging Alignment IEEE Access Fiducial marker detection 3D brain MRI MEG-MRI registration autoencoder deep learning anatomical landmark localization |
| title | Autoencoder-Driven Fiducial Landmark Identification in 3D Brain MRI for Neuroimaging Alignment |
| title_full | Autoencoder-Driven Fiducial Landmark Identification in 3D Brain MRI for Neuroimaging Alignment |
| title_fullStr | Autoencoder-Driven Fiducial Landmark Identification in 3D Brain MRI for Neuroimaging Alignment |
| title_full_unstemmed | Autoencoder-Driven Fiducial Landmark Identification in 3D Brain MRI for Neuroimaging Alignment |
| title_short | Autoencoder-Driven Fiducial Landmark Identification in 3D Brain MRI for Neuroimaging Alignment |
| title_sort | autoencoder driven fiducial landmark identification in 3d brain mri for neuroimaging alignment |
| topic | Fiducial marker detection 3D brain MRI MEG-MRI registration autoencoder deep learning anatomical landmark localization |
| url | https://ieeexplore.ieee.org/document/11048582/ |
| work_keys_str_mv | AT gdeepali autoencoderdrivenfiduciallandmarkidentificationin3dbrainmriforneuroimagingalignment AT hanitha autoencoderdrivenfiduciallandmarkidentificationin3dbrainmriforneuroimagingalignment AT bpswathi autoencoderdrivenfiduciallandmarkidentificationin3dbrainmriforneuroimagingalignment AT mvsuhas autoencoderdrivenfiduciallandmarkidentificationin3dbrainmriforneuroimagingalignment |