Harmonizing Pathological and Normal Pixels for Pseudo-Healthy Synthesis

• Published in: IEEE transactions on medical imaging Vol. 41; no. 9; pp. 2457 - 2468
• Main Authors: Zhang, Yunlong, Lin, Xin, Zhuang, Yihong, Sun, Liyan, Huang, Yue, Ding, Xinghao, Wang, Guisheng, Yang, Lin, Yu, Yizhou
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: adversarial training; Algorithms; Biomedical imaging; Generative adversarial networks; Generators; Image contrast; Image enhancement; Image processing; Image quality; Image segmentation; label noise; Lesions; low-contrast medical image segmentation; Measurement; Medical image synthesis; Medical imaging; Noise measurement; Pathology; Synthesis; Training

Synthesizing a subject-specific pathology-free image from a pathological image is valuable for algorithm development and clinical practice. In recent years, several approaches based on the Generative Adversarial Network (GAN) have achieved promising results in pseudo-healthy synthesis. However, the...