# RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2212.01737 · HTML: https://mlsanity.com/paper/2212.01737/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 53 references that are in the map.
- First posted on arXiv 4 Dec 2022.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2106.00908/) (2021)
- [Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning](https://mlsanity.com/paper/2011.08939/) (2020)
- [Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning](https://mlsanity.com/paper/2206.02647/) (2022)
- [Deep Reinforcement Learning: An Overview](https://mlsanity.com/paper/1701.07274/) (2017)
- [Multiple Instance Learning: A Survey of Problem Characteristics and Applications](https://mlsanity.com/paper/1612.03365/) (2016)
- [Mastering Complex Control in MOBA Games with Deep Reinforcement Learning](https://mlsanity.com/paper/1912.09729/) (2019)
- [Multi-scale Domain-adversarial Multiple-instance CNN for Cancer Subtype Classification with Unannotated Histopathological Images](https://mlsanity.com/paper/2001.01599/) (2020)
- [Towards Playing Full MOBA Games with Deep Reinforcement Learning](https://mlsanity.com/paper/2011.12692/) (2020)
- [Active MR k-space Sampling with Reinforcement Learning](https://mlsanity.com/paper/2007.10469/) (2020)
- [Deep reinforcement learning in medical imaging: A literature review](https://mlsanity.com/paper/2103.05115/) (2021)
- [JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2112.04907/) (2021)
- [Deep Reinforcement Learning for Surgical Gesture Segmentation and Classification](https://mlsanity.com/paper/1806.08089/) (2018)
- [Learning Where to See: A Novel Attention Model for Automated Immunohistochemical Scoring](https://mlsanity.com/paper/1903.10762/) (2019)
- [PixelRL: Fully Convolutional Network with Reinforcement Learning for Image Processing](https://mlsanity.com/paper/1912.07190/) (2019)
- [Synthetic Sample Selection via Reinforcement Learning](https://mlsanity.com/paper/2008.11331/) (2020)
- [Deep Q-Network-Driven Catheter Segmentation in 3D US by Hybrid Constrained Semi-Supervised Learning and Dual-UNet](https://mlsanity.com/paper/2006.14702/) (2020)
- [Auto-weighting for Breast Cancer Classification in Multimodal Ultrasound](https://mlsanity.com/paper/2008.03435/) (2020)
- [Reinforcement Learning of Musculoskeletal Control from Functional Simulations](https://mlsanity.com/paper/2007.06669/) (2020)
- [Intelligent Parameter Tuning in Optimization-based Iterative CT Reconstruction via Deep Reinforcement Learning](https://mlsanity.com/paper/1711.00414/) (2017)
- [Group-driven Reinforcement Learning for Personalized mHealth Intervention](https://mlsanity.com/paper/1708.04001/) (2017)
- [Augmenting Policy Learning with Routines Discovered from a Single Demonstration](https://mlsanity.com/paper/2012.12469/) (2020)
- [Adversarial Policy Gradient for Deep Learning Image Augmentation](https://mlsanity.com/paper/1909.04108/) (2019)

## Built on by (most cited first, 8 of 8)

- [Dynamic Policy-Driven Adaptive Multi-Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2403.07939/) (2024)
- [Affordable Generative Agents](https://mlsanity.com/paper/2402.02053/) (2024)
- [Advanced Deep Learning and Large Language Models: Comprehensive Insights for Cancer Detection](https://mlsanity.com/paper/2504.13186/) (2025)
- [Sequential Attention-based Sampling for Histopathological Analysis](https://mlsanity.com/paper/2507.05077/) (2025)
- [HistoGym: A Reinforcement Learning Environment for Histopathological Image Analysis](https://mlsanity.com/paper/2408.08847/) (2024)
- [The Impact of Image Resolution on Biomedical Multimodal Large Language Models](https://mlsanity.com/paper/2510.18304/) (2025)
- [Agentic Visual Reasoning in Whole-Slide Pathology Images via Active Perception](https://mlsanity.com/paper/2608.08648/) (2026)
- [PAVE: A Cognitive Architecture for Legitimate Violation in Generative Agent Societies](https://mlsanity.com/paper/2605.19351/) (2026)

## Abstract (arXiv)

Whole-slide images (WSI) in computational pathology have high resolution with gigapixel size, but are generally with sparse regions of interest, which leads to weak diagnostic relevance and data inefficiency for each area in the slide. Most of the existing methods rely on a multiple instance learning framework that requires densely sampling local patches at high magnification. The limitation is evident in the application stage as the heavy computation for extracting patch-level features is inevitable. In this paper, we develop RLogist, a benchmarking deep reinforcement learning (DRL) method for fast observation strategy on WSIs. Imitating the diagnostic logic of human pathologists, our RL agent learns how to find regions of observation value and obtain representative features across multiple resolution levels, without having to analyze each part of the WSI at the high magnification. We benchmark our method on two whole-slide level classification tasks, including detection of metastases in WSIs of lymph node sections, and subtyping of lung cancer. Experimental results demonstrate that RLogist achieves competitive classification performance compared to typical multiple instance learning algorithms, while having a significantly short observation path. In addition, the observation path given by RLogist provides good decision-making interpretability, and its ability of reading path navigation can potentially be used by pathologists for educational/assistive purposes. Our code is available at: urlhttps://github.com/tencent-ailab/RLogist.