[2009.04985] Unsupervised Domain Adaptation via CycleGAN for White Matter Hyperintensity Segmentation in Multicenter MR Imagesopen searchopen navigation menucontact arXivsubscribe to arXiv mailings

Automatic segmentation of white matter hyperintensities in magnetic resonance images is of paramount clinical and research importance. Quantification of these lesions serve as a predictor for risk of stroke, dementia and mortality. During the last years, convolutional neural networks (CNN) specifically tailored for biomedical image segmentation have outperformed all previous techniques in this task. However, they are extremely data-dependent, and maintain a good performance only when data distribution between training and test datasets remains unchanged. When such distribution changes but we still aim at performing the same task, we incur in a domain adaptation problem (e.g. using a different MR machine or different acquisition parameters for training and test data). In this work, we explore the use of cycle-consistent adversarial networks (CycleGAN) to perform unsupervised domain adaptation on multicenter MR images with brain lesions. We aim at learning a mapping function to transform

Date: 2020/09/13 15:51

Related Entries

Read more お手軽で欲しい機能が揃っている実験管理ツールGuild AIの紹介 - kuromt blog
46 users, 9 mentions 2020/09/11 14:01
Read more 数多の画像変換が可能!StyleGANの新たなEncoder!pixel2Style2pixel | AI-SCHOLAR | AI:(人工知能)論文・技術情報メディア
1 users, 2 mentions 2020/09/14 12:25
Read more 誰の声でも100人の声に変えられる声変換システム - Dwango Media Village(ドワンゴメディアヴィレッジ,dmv)
698 users, 302 mentions 2020/09/14 11:22
Read more 強化学習の基礎と深層強化学習
68 users, 16 mentions 2020/09/14 11:22
Read more RTX3080 TensorFlow and NAMD Performance on Linux (Preliminary)
1 users, 19 mentions 2020/09/18 20:21