Sep 2026· Journal of imaging informatics in medicine· 0 citations· 21 references
Medicine
TL;DR
AdvLIF is introduced, an adversarially regularized and physics-inspired framework for jointly generating H&E-like and complementary auxiliary modalities from IHC images and segmenting nuclei and achieves superior quantitative fidelity, exemplified by the lowest error on the IHC Quantification Difference metric.
Pixel diffusion models generate RGB images directly, avoiding the bottleneck of an autoencoder, yet their outputs still systematically underrepresent fine-scale natural-image statistics. We show that adversarial learning provides an effective post-training correction for this deficiency. Starting from a pretrained mode...
Xin Lin, Zhi-Fei Zhang, Yu-Qian Zhou et al.· 0 citations
StyleGANCA is proposed, the first lightweight general-purpose NCA-based generative adversarial network, enabling latent-controlled image generation through iterative local interactions and achieving competitive image quality with substantially fewer parameters than baseline architectures.
Anh Thi Luu, Nick Lemke, Anirban Mukhopadhyay· 1 citation
GAN-based image translation has been widely used for cross-domain medical image synthesis. However, most existing methods follow a one-to-one mapping paradigm, requiring a separate model for each target domain and increasing the training cost in multi-target tasks such as multi-sequence MRI synthesis. Although recent o...
Jinhao Li, Kai Hu, Runze Wang et al.· Computerized Medical Imaging...· 0 citations
Medical image segmentation requires high accuracy and robustness, yet practical commercial deployment also demands privacy preservation and computational efficiency. In this context, the U-Net architecture, which can be inherently decoupled into independent encoder and decoder components, serves as a natural commercial...
IGG (Image Generation informed by Geodesic dynamics), a novel framework that integrates topology-preserving geodesic principles into the diffusion-based generative process, where geometric object changes are learned as smooth and invertible smooth mappings from a given template/source image.
Nian Wu, Nivetha Jayakumar, Jiarui Xing et al.· 0 citations
