# Spatial-temporal Hierarchical Reinforcement Learning for Interpretable Pathology Image Super-Resolution

arXiv: https://arxiv.org/abs/2406.18310 · HTML: https://mlsanity.com/paper/2406.18310/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in RL for clinical treatment and surgery, one of 15 directions in Deep reinforcement learning methods.
- Builds on 14 of its 55 references that are in the map.
- First posted on arXiv 26 Jun 2024.

## Placed in

- Deep reinforcement learning methods / [RL for clinical treatment and surgery](https://mlsanity.com/deeprl/rl-for-clinical-treatment-and-surgery/)

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Rotation Equivariant CNNs for Digital Pathology](https://mlsanity.com/paper/1806.03962/) (2018)
- [Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index](https://mlsanity.com/paper/1308.3052/) (2013)
- [Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution](https://mlsanity.com/paper/2203.09195/) (2022)
- [Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling](https://mlsanity.com/paper/2108.05301/) (2021)
- [Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning](https://mlsanity.com/paper/1804.03312/) (2018)
- [Channel Splitting Network for Single MR Image Super-Resolution](https://mlsanity.com/paper/1810.06453/) (2018)
- [Human Pose Estimation on Privacy-Preserving Low-Resolution Depth Images](https://mlsanity.com/paper/2007.08340/) (2020)
- [EndoL2H: Deep Super-Resolution for Capsule Endoscopy](https://mlsanity.com/paper/2002.05459/) (2020)
- [Fully Convolutional Network with Multi-Step Reinforcement Learning for Image Processing](https://mlsanity.com/paper/1811.04323/) (2018)
- [A Mixed-Supervision Multilevel GAN Framework for Image Quality Enhancement](https://mlsanity.com/paper/2106.15575/) (2021)
- [Dynamically Unfolding Recurrent Restorer: A Moving Endpoint Control Method for Image Restoration](https://mlsanity.com/paper/1805.07709/) (2018)
- [Unsupervised Domain Adaptation for Low-dose CT Reconstruction via Bayesian Uncertainty Alignment](https://mlsanity.com/paper/2302.13251/) (2023)

## Built on by (most cited first, 4 of 4)

- [MRI Super-Resolution with Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/2511.16854/) (2025)
- [Content Generation Models in Computational Pathology: A Comprehensive Survey on Methods, Applications, and Challenges](https://mlsanity.com/paper/2505.10993/) (2025)
- [Toward Efficient Weakly Supervised Semantic Segmentation Using Only Low-Magnification Histopathological Images](https://mlsanity.com/paper/2607.10783/) (2026)
- [S3-Diff: Structural Semantic Synergy Diffusion Model for High Fidelity Super Resolution of Pathological Images](https://mlsanity.com/paper/2608.03540/) (2026)

## Abstract (arXiv)

Pathology image are essential for accurately interpreting lesion cells in cytopathology screening, but acquiring high-resolution digital slides requires specialized equipment and long scanning times. Though super-resolution (SR) techniques can alleviate this problem, existing deep learning models recover pathology image in a black-box manner, which can lead to untruthful biological details and misdiagnosis. Additionally, current methods allocate the same computational resources to recover each pixel of pathology image, leading to the sub-optimal recovery issue due to the large variation of pathology image. In this paper, we propose the first hierarchical reinforcement learning framework named Spatial-Temporal hierARchical Reinforcement Learning (STAR-RL), mainly for addressing the aforementioned issues in pathology image super-resolution problem. We reformulate the SR problem as a Markov decision process of interpretable operations and adopt the hierarchical recovery mechanism in patch level, to avoid sub-optimal recovery. Specifically, the higher-level spatial manager is proposed to pick out the most corrupted patch for the lower-level patch worker. Moreover, the higher-level temporal manager is advanced to evaluate the selected patch and determine whether the optimization should be stopped earlier, thereby avoiding the over-processed problem. Under the guidance of spatial-temporal managers, the lower-level patch worker processes the selected patch with pixel-wise interpretable actions at each time step. Experimental results on medical images degraded by different kernels show the effectiveness of STAR-RL. Furthermore, STAR-RL validates the promotion in tumor diagnosis with a large margin and shows generalizability under various degradations. The source code is available at https://github.com/CUHK-AIM-Group/STAR-RL.