2024-01-23-crystal24a.md

title	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Domain Adaptation using Silver Standard Masks for Lateral Ventricle Segmentation in FLAIR MRI	Lateral ventricular volume (LVV) is an important biomarker for clinical investigation. We present the first transfer learning-based LVV segmentation method for fluid-attenuated inversion recovery (FLAIR) MRI. To mitigate covariate shifts between source and target domains, this work proposes an domain adaptation method that optimizes performance on three target datasets. Silver standard (SS) masks were generated from the target domain using a novel conventional image processing ventricular segmentation algorithm and used to supplement the gold standard (GS) data from the source domain, Canadian Atherosclerosis Imaging Network (CAIN). Four models were tested on held-out test sets from four datasets: 1) SS+GS: trained on target SS masks and fine-tuned on source GS masks, 2) GS+SS: trained on source GS masks and fine-tuned on target SS masks, 3) trained on source GS (GS CAIN Only) and 4) trained on target SS masks (SS Only). The SS+GS model had the best and most consistent performance (mean DSC = 0.89, CoV = 0.05) and showed significantly p < 0.05) higher DSC compared to the GS-only model on three target domains. Results suggest pre-training with noisy labels from the target domain allows the model to adapt to the dataset-specific characteristics and provides robust parameter initialization while fine-tuning with GS masks allows the model to learn detailed features. This method has wide application to other medical imaging problems where labeled data is scarce, and can be used as a per-dataset calibration method to accelerate wide-scale adoption.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	crystal24a	0	Domain Adaptation using Silver Standard Masks for Lateral Ventricle Segmentation in FLAIR MRI	1895	1909	1895-1909	1895	false	Crystal, Owen and Khademi, April and Moody, Alan R and Maralani, Pejman J and Black, Sandra E	given family Owen Crystal given family April Khademi given family Alan R Moody given family Pejman J Maralani given family Sandra E Black	2024-01-23		Medical Imaging with Deep Learning	227	inproceedings	date-parts 2024 1 23	https://proceedings.mlr.press/v227/crystal24a/crystal24a.pdf