DeepNavNet: Automated Landmark Localization for Neuronavigation
Functional neurosurgery requires neuroimaging technologies that enable precise navigation to targeted structures. Insufficient image resolution of deep brain structures necessitates alignment to a brain atlas to indirectly locate targets within preoperative magnetic resonance imaging (MRI) scans. In...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-06-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2021.670287/full |
| _version_ | 1818588543119785984 |
|---|---|
| author | Christine A. Edwards Christine A. Edwards Christine A. Edwards Abhinav Goyal Abhinav Goyal Aaron E. Rusheen Aaron E. Rusheen Abbas Z. Kouzani Kendall H. Lee Kendall H. Lee Kendall H. Lee Kendall H. Lee |
| author_facet | Christine A. Edwards Christine A. Edwards Christine A. Edwards Abhinav Goyal Abhinav Goyal Aaron E. Rusheen Aaron E. Rusheen Abbas Z. Kouzani Kendall H. Lee Kendall H. Lee Kendall H. Lee Kendall H. Lee |
| author_sort | Christine A. Edwards |
| collection | DOAJ |
| description | Functional neurosurgery requires neuroimaging technologies that enable precise navigation to targeted structures. Insufficient image resolution of deep brain structures necessitates alignment to a brain atlas to indirectly locate targets within preoperative magnetic resonance imaging (MRI) scans. Indirect targeting through atlas-image registration is innately imprecise, increases preoperative planning time, and requires manual identification of anterior and posterior commissure (AC and PC) reference landmarks which is subject to human error. As such, we created a deep learning-based pipeline that consistently and automatically locates, with submillimeter accuracy, the AC and PC anatomical landmarks within MRI volumes without the need for an atlas. Our novel deep learning pipeline (DeepNavNet) regresses from MRI scans to heatmap volumes centered on AC and PC anatomical landmarks to extract their three-dimensional coordinates with submillimeter accuracy. We collated and manually labeled the location of AC and PC points in 1128 publicly available MRI volumes used for training, validation, and inference experiments. Instantiations of our DeepNavNet architecture, as well as a baseline model for reference, were evaluated based on the average 3D localization errors for the AC and PC points across 311 MRI volumes. Our DeepNavNet model significantly outperformed a baseline and achieved a mean 3D localization error of 0.79 ± 0.33 mm and 0.78 ± 0.33 mm between the ground truth and the detected AC and PC points, respectively. In conclusion, the DeepNavNet model pipeline provides submillimeter accuracy for localizing AC and PC anatomical landmarks in MRI volumes, enabling improved surgical efficiency and accuracy. |
| first_indexed | 2024-12-16T09:26:25Z |
| format | Article |
| id | doaj.art-4a3cb66df1b445ea83c0e80776ca03e8 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-12-16T09:26:25Z |
| publishDate | 2021-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-4a3cb66df1b445ea83c0e80776ca03e82022-12-21T22:36:38ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2021-06-011510.3389/fnins.2021.670287670287DeepNavNet: Automated Landmark Localization for NeuronavigationChristine A. Edwards0Christine A. Edwards1Christine A. Edwards2Abhinav Goyal3Abhinav Goyal4Aaron E. Rusheen5Aaron E. Rusheen6Abbas Z. Kouzani7Kendall H. Lee8Kendall H. Lee9Kendall H. Lee10Kendall H. Lee11School of Engineering, Deakin University, Geelong, VIC, AustraliaDepartment of Neurologic Surgery, Mayo Clinic, Rochester, MN, United StatesMayo Clinic Graduate School of Biomedical Sciences, Mayo Clinic, Rochester, MN, United StatesDepartment of Neurologic Surgery, Mayo Clinic, Rochester, MN, United StatesMayo Clinic College of Medical Scientist Training Program, Mayo Clinic, Rochester, MN, United StatesDepartment of Neurologic Surgery, Mayo Clinic, Rochester, MN, United StatesMayo Clinic College of Medical Scientist Training Program, Mayo Clinic, Rochester, MN, United StatesSchool of Engineering, Deakin University, Geelong, VIC, AustraliaDepartment of Neurologic Surgery, Mayo Clinic, Rochester, MN, United StatesMayo Clinic Graduate School of Biomedical Sciences, Mayo Clinic, Rochester, MN, United StatesMayo Clinic College of Medical Scientist Training Program, Mayo Clinic, Rochester, MN, United StatesDepartment of Physiology and Biomedical Engineering, Mayo Clinic, Rochester, MN, United StatesFunctional neurosurgery requires neuroimaging technologies that enable precise navigation to targeted structures. Insufficient image resolution of deep brain structures necessitates alignment to a brain atlas to indirectly locate targets within preoperative magnetic resonance imaging (MRI) scans. Indirect targeting through atlas-image registration is innately imprecise, increases preoperative planning time, and requires manual identification of anterior and posterior commissure (AC and PC) reference landmarks which is subject to human error. As such, we created a deep learning-based pipeline that consistently and automatically locates, with submillimeter accuracy, the AC and PC anatomical landmarks within MRI volumes without the need for an atlas. Our novel deep learning pipeline (DeepNavNet) regresses from MRI scans to heatmap volumes centered on AC and PC anatomical landmarks to extract their three-dimensional coordinates with submillimeter accuracy. We collated and manually labeled the location of AC and PC points in 1128 publicly available MRI volumes used for training, validation, and inference experiments. Instantiations of our DeepNavNet architecture, as well as a baseline model for reference, were evaluated based on the average 3D localization errors for the AC and PC points across 311 MRI volumes. Our DeepNavNet model significantly outperformed a baseline and achieved a mean 3D localization error of 0.79 ± 0.33 mm and 0.78 ± 0.33 mm between the ground truth and the detected AC and PC points, respectively. In conclusion, the DeepNavNet model pipeline provides submillimeter accuracy for localizing AC and PC anatomical landmarks in MRI volumes, enabling improved surgical efficiency and accuracy.https://www.frontiersin.org/articles/10.3389/fnins.2021.670287/fulldeep brain stimulationdeep learninghuman-machine teaminglandmark localizationneuroimagingneuronavigation |
| spellingShingle | Christine A. Edwards Christine A. Edwards Christine A. Edwards Abhinav Goyal Abhinav Goyal Aaron E. Rusheen Aaron E. Rusheen Abbas Z. Kouzani Kendall H. Lee Kendall H. Lee Kendall H. Lee Kendall H. Lee DeepNavNet: Automated Landmark Localization for Neuronavigation Frontiers in Neuroscience deep brain stimulation deep learning human-machine teaming landmark localization neuroimaging neuronavigation |
| title | DeepNavNet: Automated Landmark Localization for Neuronavigation |
| title_full | DeepNavNet: Automated Landmark Localization for Neuronavigation |
| title_fullStr | DeepNavNet: Automated Landmark Localization for Neuronavigation |
| title_full_unstemmed | DeepNavNet: Automated Landmark Localization for Neuronavigation |
| title_short | DeepNavNet: Automated Landmark Localization for Neuronavigation |
| title_sort | deepnavnet automated landmark localization for neuronavigation |
| topic | deep brain stimulation deep learning human-machine teaming landmark localization neuroimaging neuronavigation |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2021.670287/full |
| work_keys_str_mv | AT christineaedwards deepnavnetautomatedlandmarklocalizationforneuronavigation AT christineaedwards deepnavnetautomatedlandmarklocalizationforneuronavigation AT christineaedwards deepnavnetautomatedlandmarklocalizationforneuronavigation AT abhinavgoyal deepnavnetautomatedlandmarklocalizationforneuronavigation AT abhinavgoyal deepnavnetautomatedlandmarklocalizationforneuronavigation AT aaronerusheen deepnavnetautomatedlandmarklocalizationforneuronavigation AT aaronerusheen deepnavnetautomatedlandmarklocalizationforneuronavigation AT abbaszkouzani deepnavnetautomatedlandmarklocalizationforneuronavigation AT kendallhlee deepnavnetautomatedlandmarklocalizationforneuronavigation AT kendallhlee deepnavnetautomatedlandmarklocalizationforneuronavigation AT kendallhlee deepnavnetautomatedlandmarklocalizationforneuronavigation AT kendallhlee deepnavnetautomatedlandmarklocalizationforneuronavigation |