Publications by authors named "Otoichi Nakata"
Fully-Automated Spike Detection and Dipole Analysis of Epileptic MEG Using Deep Learning.
IEEE Trans Med Imaging
October 2022
Article Synopsis
- Magnetoencephalography (MEG) is used to assess interictal spikes in patients, but current manual analysis is time-consuming and relies heavily on the skill of neurophysiologists.
- A new AI-based method called FAMED has been developed to automate the spike identification and equivalent current dipole (ECD) estimation processes using deep learning techniques, specifically semantic segmentation.
- FAMED has shown excellent performance metrics, achieving a mean AUC of 0.9868 and a median distance of 0.63 cm between its ECD estimates and those of neurophysiologists, indicating it can enhance the efficiency and consistency of MEG analyses.
Aim: To evaluate the feasibility of a newly developed prototype MRI projection mapping (PM) system for localization of invasive breast cancer before breast-conserving surgery.
Methods: This prospective study enrolled 10 women with invasive breast cancer. MRI was performed in both prone and supine positions.