Morphology-Aware Implicit Super-Resolution Network for Pathological Images

2026-08-04

AI Summary

This work addresses the tendency of existing super-resolution methods to oversmooth cellular structures and blur boundaries in digital pathology images. To mitigate this, the authors reformulate super-resolution as a continuous coordinate-driven implicit reconstruction problem and introduce a position-aware adaptive kernel generation mechanism. For the first time, they incorporate a morphology-fidelity prior derived from a pre-trained segmentation network, enabling semantics-guided region awareness and sub-pixel detail recovery. Evaluated on the TCGA and SurGen datasets, the proposed method significantly outperforms current state-of-the-art approaches, reducing LPIPS and ST-LPIPS by 38.37% and 39.55%, respectively, while maintaining high PSNR and SSIM values. This advancement effectively enhances the diagnostic relevance of cellular boundaries and nuclear textures.

Abstract

Accurate diagnosis in Digital Pathology (DP) relies on high-resolution whole-slide images, yet clinical deployment is often limited by hardware costs. Super-Resolution (SR) offers a promising alternative by computationally enhancing low-resolution acquisitions. However, existing SR methods frequently struggle to preserve fine-grained cellular morphology, leading to texture oversmoothing and blurred structural boundaries under complex tissue variability. To address this issue, we propose Morph-ISR, a morphology-aware implicit super-resolution framework for DP that restores diagnostically relevant details with sub-pixel precision. Morph-ISR reformulates SR as a continuous coordinate-based reconstruction problem and integrates an Implicit Position-aware Kernel Generator (IPKG) to adaptively model spatially varying tissue morphology. To further enhance structural fidelity, a Morphological Fidelity Prior (MFP) is introduced, leveraging semantic guidance from a pre-trained cell segmentation network to enforce boundary-preserving and region-aware reconstruction, thereby improving the representation of critical cellular boundaries and nuclear textures. Experiments on TCGA and SurGen datasets show that Morph-ISR achieves the best LPIPS and ST-LPIPS among the evaluated methods, reducing them by up to 38.37% and 39.55%, respectively, over the second-best methods while maintaining strong PSNR and SSIM. These results demonstrate superior preservation of diagnostically relevant cellular boundaries and nuclear textures, while compact parameterization and high throughput support efficient edge deployment. Code and trained models will be released upon publication.

Problem

• Super-Resolution
• Digital Pathology
• Cellular Morphology
• Structural Boundaries
• Texture Preservation

Innovation

• Implicit Super-Resolution
• Morphology-Aware
• Position-aware Kernel
• Morphological Fidelity Prior
• Digital Pathology