Adversarial cycle-consistent synthesis of cerebral microbleeds for data augmentation

Autor:	Faryna, Khrystyna, Koschmieder, Kevin, Paul, Marcella M., Heuvel, Thomas van den, van der Eerden, Anke, Manniesing, Rashindra, van Ginneken, Bram
Rok vydání:	2021
Předmět:	Electrical Engineering and Systems Science - Image and Video Processing Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	We propose a novel framework for controllable pathological image synthesis for data augmentation. Inspired by CycleGAN, we perform cycle-consistent image-to-image translation between two domains: healthy and pathological. Guided by a semantic mask, an adversarially trained generator synthesizes pathology on a healthy image in the specified location. We demonstrate our approach on an institutional dataset of cerebral microbleeds in traumatic brain injury patients. We utilize synthetic images generated with our method for data augmentation in cerebral microbleeds detection. Enriching the training dataset with synthetic images exhibits the potential to increase detection performance for cerebral microbleeds in traumatic brain injury patients. Comment: Accepted in Medical Imaging meets NIPS Workshop, NIPS 2020
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2101.06468 Zobrazit plný text záznamu View this record from Arxiv