Automated confidence estimation in deep learning auto-segmentation for brain organs at risk on MRI for radiotherapy.

Journal: Journal of applied clinical medical physics

Published Date: Sep 16, 2024

Abstract

PURPOSE: We have built a novel AI-driven QA method called AutoConfidence (ACo), to estimate segmentation confidence on a per-voxel basis without gold standard segmentations, enabling robust, efficient review of automated segmentation (AS). We have demonstrated this method in brain OAR AS on MRI, using internal and external (third-party) AS models.

Authors

Nouf M Alzahrani

Information Technology Department, Collage of Computer Science and Information Technology, Al Baha University, Al Bahah 65731, Saudi Arabia.
Ann M Henry

Leeds Cancer Centre, Leeds Teaching Hospitals NHS Trust, United Kingdom; Radiotherapy Research Group, Leeds Institute of Medical Research, University of Leeds, United Kingdom.
Bashar M Al-Qaisieh

Department of Medical Physics and Engineering, St James's University Hospital, Leeds, UK.
Louise J Murray

School of Medicine, University of Leeds, Leeds, UK.
Michael G Nix

Leeds Cancer Centre, Leeds Teaching Hospitals NHS Trust, United Kingdom.

Keywords

Algorithms Brain Neoplasms Deep Learning Glioma Humans Image Processing, Computer-Assisted Magnetic Resonance Imaging Organs at Risk Radiotherapy Dosage Radiotherapy Planning, Computer-Assisted Radiotherapy, Intensity-Modulated Retrospective Studies

External Resources

View on PubMed Access via DOI PubMed (39284283)

Automated confidence estimation in deep learning auto-segmentation for brain organs at risk on MRI for radiotherapy.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals