Pathology images enhanced with pseudo 3d views from single slides
PathoS2VD: From 2D Histopathology to Pseudo Z-Stack Representations
Computer Vision and Pattern Recognition
Summary
Pathology usually looks at very thin 2D slices of tissue to diagnose diseases, but these slices miss important 3D details. The authors created a computer model that learns what tissues look like along the depth from special 3D images, then uses that knowledge to generate fake stacks of images from just one 2D slice. These fake stacks better capture the shape changes across layers that doctors would see in real 3D. Their method improved computer diagnosis of prostate cancer compared to just using usual 2D images.
What this means in practice
- •For clinical pathology labs: Integrate generated pseudo z-stacks from existing 2D slides to improve automated cancer diagnosis accuracy.
- •For medical imaging software developers: Develop tools that create depth-aware views from single-plane histology images to support pathologist review.
Authors
Jiamu Wang, Keunho Byeon, Ji-Uk Kim, Jin Tae Kwak, Heounjeong Go
Abstract
For decades, diagnostic pathology has relied on thin two-dimensional (2D) tissue sections, despite biological tissues exhibiting inherently three-dimensional (3D) morphological organization. Because a single section captures only one focal plane, important morphological cues along the z-axis are inevitably discarded, limiting tissue representation for both human interpretation and computational analysis. In this work, we propose a generative framework that learns z-axis morphological priors from pathology z-stack data, offering a cost-effective alternative to dedicated volumetric imaging, and transfers this knowledge to conventional single-plane histopathology. Specifically, an image-to-video (I2V) latent diffusion model (LDM) is trained to synthesize a pseudo z-stack from a single 2D image, capturing plausible morphological variations across adjacent focal planes rather than reconstructing physical tissue volumes. To enable deployment on large-scale clinical datasets without native z-stack acquisition, we further introduce a prior-preserving mixture fine-tuning strategy that adapts the model to new domains while retaining the learned z-axis morphological prior. Extensive experiments demonstrate that the synthesized pseudo z-stacks exhibit realistic cross-plane morphological continuity and consistently improve downstream prostate cancer classification compared with conventional 2D representations. Our results suggest that learning transferable z-axis priors from limited z-stack data provides a practical way to enrich routine pathology images with complementary morphological information. Code: https://github.com/QuIIL/PathoS2VD.