Check out the updated conference hotel
See the transformation
>
Conference 12031 > Paper 12031-180
Paper 12031-180

Real-time detection of patient head position and cephalometric landmarks from neuro-interventional procedure images using machine learning for patient eye-lens dose prediction

21 February 2022 • 6:00 PM - 7:30 PM PST | Golden State Hall

Abstract

Machine learning (ML) models were investigated to automatically detect the patient head shift from isocenter and cephalometric landmark locations as a surrogate for head size. Fluoroscopic images of a Kyoto Kagaku anthropomorphic head phantom were taken at various head shifts and magnification modes, to create an image database. One ML model predicts the patient head shift and the other model predicts the coordinates of the anatomical landmarks. The goal is to implement these two separate models into the Dose Tracking System (DTS) developed by our group for eye-lens dose prediction and eliminate the need for manual input by clinical staff.

Presenter

Canon Stroke and Vascular Research Ctr. (United States)
PhD candidate currently in my 4th year in the Medical Physics Program at the University at Buffalo.
Author
Univ. at Buffalo (United States)
Author
Univ. at Buffalo (United States)
Author
Univ. at Buffalo (United States)
Author
Univ. at Buffalo (United States)
Presenter/Author
Canon Stroke and Vascular Research Ctr. (United States)