508 Deep Learning Segmentation of the Nucleus Basalis of Meynert for Deep Brain Stimulation Surgical Planning. (April 2023)

• Record Type: Journal Article
• Authors: Doss, Derek; Johnson, Graham Walter; Narasimhan, Saramati; Jiang, Jasmine; Gonzalez, Hernan F.J.; Paulo, Danika Lea; Chang, Catie; Morgan, Victoria; Constantinidis, Christos; Dawant, Benoit M.; Englot, Dario J.
• Is Part Of: Neurosurgery. Volume 69(2023)Supplement 1
• Page Start: 112
• Page End: 113
• Publication Date: 2023-04
• Subjects: Nervous system -- Surgery -- Periodicals; 617.48005
• DOI: 10.1227/neu.0000000000002375_508
• Languages: English
• ISSNs: 0148-396X

Abstract

Abstract : INTRODUCTION: The nucleus basalis of Meynert (NBM) is a subcortical structure involved in arousal and cognition being explored as a deep brain stimulation (DBS) target for Alzheimer's disease and other disorders. Given the small size of the NBM and variability between patients, accurate patient-specific targeting for DBS is needed. Accurate patient-specific manual segmentation is possible but requires high resolution 7T MRI. Therefore, the current standard is a non-patient-specific probabilistic atlas (Zaborszky 2008). METHODS: Paired 3T and 7T MRI datasets of 21 healthy subjects were obtained and the NBM was expertly segmented on 7T MRI. The 7T NBM segmentation was then used on the 3T MRI. To increase generalizability, we augmented the dataset to a total of 210 images. An external dataset of 14 patients with temporal lobe epilepsy (TLE) was used to validate the network's performance on brains with pathological changes (Alvim 2016). A 3D-Unet convolutional neural network was constructed, and a 5-fold cross-validation was performed for model selection. The model was evaluated on healthy subjects using the held-out test dataset and on the external dataset of 14 TLE patients. RESULTS: When tested on the held-out dataset, the deep learning network demonstrated significantly improved dice coefficient compared against the probabilistic atlas for both healthy subjects (0.68 ± 0.08, 0.47 ± 0.06) and patients with TLE (0.63 ± 0.08, 0.38 ± 0.19). Additionally, the centroid distance was significantly decreased when using the network in patients with TLE (1.22 ± 0.33 mm, 3.25 ± 2.57 mm). CONCLUSIONS: We developed the first network, to our knowledge, for automatic and accurate patient-specific segmentation of the NBM using deep learning. The proposed network has less error than accepted targeting margins. This segmentation strategy allows accurate patient-specific targeting of the NBM for DBS.