# SAMPO-Path: Segmentation Intent-Aligned Preference Optimization for Pathology Foundation Model Segmentation

arXiv: https://arxiv.org/abs/2508.02464 · HTML: https://mlsanity.com/paper/2508.02464/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 40 references that are in the map.
- First posted on arXiv 4 Aug 2025.

## Builds on (most cited first, 23 of 23)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.12620/) (2023)
- [HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Images](https://mlsanity.com/paper/1812.06499/) (2018)
- [Customized Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.13785/) (2023)
- [Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images](https://mlsanity.com/paper/1808.08114/) (2018)
- [Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement](https://mlsanity.com/paper/2503.06520/) (2025)
- [PanNuke Dataset Extension, Insights and Baselines](https://mlsanity.com/paper/2003.10778/) (2020)
- [Methods for Segmentation and Classification of Digital Microscopy Tissue Images](https://mlsanity.com/paper/1810.13230/) (2018)
- [CryoNuSeg: A Dataset for Nuclei Instance Segmentation of Cryosectioned H&E-Stained Histological Images](https://mlsanity.com/paper/2101.00442/) (2021)
- [Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decoding](https://mlsanity.com/paper/2403.18271/) (2024)
- [All-in-SAM: from Weak Annotation to Pixel-wise Nuclei Segmentation with Prompt-based Finetuning](https://mlsanity.com/paper/2307.00290/) (2023)
- [PixelThink: Towards Efficient Chain-of-Pixel Reasoning](https://mlsanity.com/paper/2505.23727/) (2025)
- [Segment Any Cell: A SAM-based Auto-prompting Fine-tuning Framework for Nuclei Segmentation](https://mlsanity.com/paper/2401.13220/) (2024)
- [A Survey on Human Preference Learning for Large Language Models](https://mlsanity.com/paper/2406.11191/) (2024)
- [Unleashing the Power of Prompt-driven Nucleus Instance Segmentation](https://mlsanity.com/paper/2311.15939/) (2023)
- [TransNuSeg: A Lightweight Multi-Task Transformer for Nuclei Segmentation](https://mlsanity.com/paper/2307.08051/) (2023)
- [MediSee: Reasoning-based Pixel-level Perception in Medical Images](https://mlsanity.com/paper/2504.11008/) (2025)
- [DINO-R1: Incentivizing Reasoning Capability in Vision Foundation Models](https://mlsanity.com/paper/2505.24025/) (2025)
- [ProMISe: Promptable Medical Image Segmentation using SAM](https://mlsanity.com/paper/2403.04164/) (2024)

## Built on by (most cited first, 2 of 2)

- [Model Agnostic Preference Optimization for Medical Image Segmentation](https://mlsanity.com/paper/2512.15009/) (2025)
- [Region-Normalized DPO for Medical Image Segmentation under Noisy Judges](https://mlsanity.com/paper/2601.23222/) (2026)

## Abstract (arXiv)

Foundation models have shown strong performance in multi-object segmentation with visual prompts, yet histopathology images remain challenging due to high cellular density, heterogeneity, and the gap between pixel-level supervision and clinical segmentation intent (e.g., selectively segmenting nuclei of a specific type). In practice, such intents are expressed through diverse and noisy prompts, causing prompt-intent misalignment and inconsistent predictions. We introduce SAMPO (Segmentation Anything Model with Preference Optimization), a preference-aligned fine-tuning framework that explicitly aligns pathology foundation models with clinical segmentation intent. SAMPO is the first to adapt Direct Preference Optimization (DPO) to pure vision foundation models, enabling accurate segmentation from minimal and imperfect prompts. The framework features three key components: (1) online prompt-centric preference mining to synthesize preference pairs across prompt qualities; (2) multi-mask preference learning to leverage output ambiguity for fine-grained ranking supervision; and (3) a hybrid loss combining preference optimization with pixel-level supervision for stable training. Trained on two datasets covering four tasks and evaluated on corresponding test sets and 12 external validation datasets, SAMPO consistently improves segmentation accuracy, robustness to prompt variations, and clinical intent adherence in dense histopathology images.