2024-01-23-ke24a.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
Video pretraining advances 3D deep learning on chest CT tasks	Pretraining on large natural image classification datasets such as ImageNet has aided model development on data-scarce 2D medical tasks. 3D medical tasks often have much less data than 2D medical tasks, prompting practitioners to rely on pretrained 2D models to featurize slices. However, these 2D models have been surpassed by 3D models on 3D computer vision benchmarks since they do not natively leverage cross-sectional or temporal information. In this study, we explore whether natural video pretraining for 3D models can enable higher performance on smaller datasets for 3D medical tasks. We demonstrate video pretraining improves the average performance of seven 3D models on two chest CT datasets, regardless of finetuning dataset size, and that video pretraining allows 3D models to outperform 2D baselines. Lastly, we observe that pretraining on the large-scale out-of-domain Kinetics dataset improves performance more than pretraining on a typically-sized in-domain CT dataset. Our results show consistent benefits of video pretraining across a wide array of architectures, tasks, and training dataset sizes, supporting a shift from small-scale in-domain pretraining to large-scale out-of-domain pretraining for 3D medical tasks.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	ke24a	0	Video pretraining advances 3D deep learning on chest CT tasks	758	774	758-774	758	false	Ke, Alexander and Huang, Shih-Cheng and O'Connell, Chloe P and Klimont, Michal and Yeung, Serena and Rajpurkar, Pranav	given family Alexander Ke given family Shih-Cheng Huang given family Chloe P O’Connell given family Michal Klimont given family Serena Yeung given family Pranav Rajpurkar	2024-01-23		Medical Imaging with Deep Learning	227	inproceedings	date-parts 2024 1 23	https://proceedings.mlr.press/v227/ke24a/ke24a.pdf