notesum.ai

Published at November 26

Cross-modal Medical Image Generation Based on Pyramid Convolutional Attention Network

cs.CE

eess.IV

Released Date: November 26, 2024

Authors: Fuyou Mao¹, Lixin Lin¹, Ming Jiang², Dong Dai¹, Chao Yang³, Hao Zhang¹, Yan Tang¹

Aff.: ¹School of Electronic Information, Central South University, Changsha, China; ²School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin, 541000, China; ³School of Computer Science and Engineering, Central South University, Changsha, China

Arxiv: http://arxiv.org/abs/2411.17420v1

Patch Size	SSIM( $\uparrow$ )	PSNR( $\uparrow$ )	MAE( $\downarrow$ )
Adversarial Loss	0.9201±0.0017	28.07±0.08	0.0235±0.0002
MAE	0.9330±0.0013	28.68±0.09	0.0218±0.0002
MM-SSIM	0.9371±0.0027	28.92±0.14	0.0212±0.0004
MAE+SSIM	0.9446±0.0015	29.31±0.11	0.0201±0.0003
MAE+ MM-SSIM	0.9486±0.0011	29.65±0.15	0.0194±0.0003