Evaluation of generalization ability for deep learning-based auto-segmentation accuracy in limited field of view CBCT of male pelvic region.

Journal: Journal of applied clinical medical physics

Published Date: Jan 19, 2023

Abstract

PURPOSE: The aim of this study was to evaluate generalization ability of segmentation accuracy for limited FOV CBCT in the male pelvic region using a full-image CNN. Auto-segmentation accuracy was evaluated using various datasets with different intensity distributions and FOV sizes.

Authors

Hideaki Hirashima

Department of Radiation Oncology and Image-applied Therapy, Graduate School of Medicine, Kyoto University, Kyoto, 606-8507, Japan.
Mitsuhiro Nakamura

Department of Radiation Oncology and Image-Applied Therapy, Kyoto University, Japan.
Keiho Imanishi
Megumi Nakao
Takashi Mizowaki

Department of Radiation Oncology and Image-applied Therapy, Graduate School of Medicine, Kyoto University, Kyoto, 606-8507, Japan.

Keywords

Deep Learning Humans Image Processing, Computer-Assisted Male Pelvis Radiotherapy Planning, Computer-Assisted Spiral Cone-Beam Computed Tomography

External Resources

View on PubMed Access via DOI PubMed (36659871)

Evaluation of generalization ability for deep learning-based auto-segmentation accuracy in limited field of view CBCT of male pelvic region.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals