MAD: Microenvironment-Aware Distillation -- A Pretraining Strategy for Virtual Spatial Omics from Microscopy

• URL: http://arxiv.org/abs/2603.13401v1
• Date: Wed, 11 Mar 2026 22:06:20 GMT
• Title: MAD: Microenvironment-Aware Distillation -- A Pretraining Strategy for Virtual Spatial Omics from Microscopy
• Abstract summary: We introduce MAD (microenvironment-aware distillation), a pretraining strategy that learns cell-centric embeddings.<n> MAD achieves state-of-the-art prediction performance on downstream tasks including cell subtyping, transcriptomic prediction, and bioinformatic inference.
• Score: 6.991792373060689
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Bridging microscopy and omics would allow us to read molecular states from images-at single-cell resolution and tissue scale-without the cost and throughput limits of omics technologies. Self-supervised pretraining offers a scalable approach with minimal labels, yet how to encode single-cell identity within tissue environments-and the extent of biological information such models can capture-remains an open question. Here, we introduce MAD (microenvironment-aware distillation), a pretraining strategy that learns cell-centric embeddings by jointly self-distilling the morphology view and the microenvironment view of the same indexed cell into a unified embedding space. Across diverse tissues and imaging modalities, MAD achieves state-of-the-art prediction performance on downstream tasks including cell subtyping, transcriptomic prediction, and bioinformatic inference. MAD even outperforms foundation models with a similar number of model parameters that have been trained on substantially larger datasets. These results demonstrate that MAD's dual-view joint self-distillation effectively captures the complexity and diversity of cells within tissues. Together, this establishes MAD as a general tool for representation learning in microscopy, enabling virtual spatial omics and biological insights from vast microscopy datasets.

Related papers

• scMIR: a vision-language foundation model for single-cell light microscopy image representation [9.935076530517575]
  We propose scMIR, a vision-language foundation model for single-cell light microscopy image representation.<n> scMIR combines self-supervised image reconstruction with text-guided cross-modal alignment.<n> scMIR shows a strong generalization ability across various tasks without requiring task-specific fine-tuning.
  arXiv  Detail & Related papers  (2026-07-21T01:59:07Z)
• Predicting Immune Biomarkers with MultiModal Mixture-of-Expert Pathology Foundation Models Empowers Precision Oncology [47.79180201495836]
  MixTIME is a multimodal foundation model that integrates pathology foundation models trained across distinct modalities.<n>It predicts multiplex immunofluorescence (mIF) protein expression from hematoxylin and eosin whole-slide images.<n>MixTIME achieves state-of-the-art performance across 17 protein markers as measured by correlation metrics.
  arXiv  Detail & Related papers  (2026-06-16T16:22:42Z)
• MMBU: A Massive Multi-modal Biomedical Understanding Benchmark to Probe the Perception Capabilities of Vision-Language Models [83.50100003741628]
  Vision and language models (VLMs) hold immense promise to transform biomedical imaging.<n>We introduce the Massive Multimodal Biomedical Understanding (MMBU) benchmark.<n>It is the largest vision and language benchmark to date, covering 35 submodalities with rich structured metadata.
  arXiv  Detail & Related papers  (2026-06-04T20:24:47Z)
• Lingshu-Cell: A generative cellular world model for transcriptome modeling toward virtual cells [48.885716676667776]
  Lingshu-Cell is a discrete diffusion model that learns transcriptomic state distributions and supports conditional simulation under perturbations.<n>It captures complex transcriptome-wide expression dependencies across approximately 18,000 genes without relying on prior gene selection.<n>It achieves leading performance on the Virtual Cell Challenge H1 genetic perturbation benchmark and in predicting cytokine-induced responses in human PBMCs.
  arXiv  Detail & Related papers  (2026-03-26T09:46:27Z)
• Big Data, Tiny Targets: An Exploratory Study in Machine Learning-enhanced Detection of Microplastic from Filters [0.6489352828665196]
  Microplastics (MPs) are ubiquitous pollutants with demonstrated potential to impact ecosystems and human health.<n>Machine learning (ML) has emerged as a powerful tool in advancing microplastic detection.
  arXiv  Detail & Related papers  (2025-10-20T20:35:50Z)
• Interpretable deep learning illuminates multiple structures fluorescence imaging: a path toward trustworthy artificial intelligence in microscopy [10.395551533758358]
  We present the Adaptive Explainable Multi-Structure Network (AEMS-Net), a deep-learning framework that enables simultaneous prediction of two subcellular structures from a single image.<n>We demonstrate that AEMS-Net allows real-time recording of interactions between mitochondria and microtubules, requiring only half the conventional sequential-channel imaging procedures.
  arXiv  Detail & Related papers  (2025-01-09T07:36:28Z)
• CryoFM: A Flow-based Foundation Model for Cryo-EM Densities [50.291974465864364]
  We present CryoFM, a foundation model designed as a generative model, learning the distribution of high-quality density maps.<n>Built on flow matching, CryoFM is trained to accurately capture the prior distribution of biomolecular density maps.
  arXiv  Detail & Related papers  (2024-10-11T08:53:58Z)
• Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biology [2.7280901660033643]
  This work explores the scaling properties of weakly supervised classifiers and self-supervised masked autoencoders (MAEs) Our results show that ViT-based MAEs outperform weakly supervised classifiers on a variety of tasks, achieving as much as a 11.5% relative improvement when recalling known biological relationships curated from public databases. We develop a new channel-agnostic MAE architecture (CA-MAE) that allows for inputting images of different numbers and orders of channels at inference time.
  arXiv  Detail & Related papers  (2024-04-16T02:42:06Z)
• Style transfer between Microscopy and Magnetic Resonance Imaging via Generative Adversarial Network in small sample size settings [45.62331048595689]
  Cross-modal augmentation of Magnetic Resonance Imaging (MRI) and microscopic imaging based on the same tissue samples is promising.<n>We tested a method for generating microscopic histological images from MRI scans of the human corpus callosum using conditional generative adversarial network (cGAN) architecture.
  arXiv  Detail & Related papers  (2023-10-16T13:58:53Z)
• A novel framework employing deep multi-attention channels network for the autonomous detection of metastasizing cells through fluorescence microscopy [0.20999222360659603]
  We developed a computational framework that can distinguish between normal and metastasizing human cells. The method relies on fluorescence microscopy images showing the spatial organization of actin and vimentin filaments in normal and metastasizing single cells.
  arXiv  Detail & Related papers  (2023-09-02T11:20:10Z)
• AMIGO: Sparse Multi-Modal Graph Transformer with Shared-Context Processing for Representation Learning of Giga-pixel Images [53.29794593104923]
  We present a novel concept of shared-context processing for whole slide histopathology images. AMIGO uses the celluar graph within the tissue to provide a single representation for a patient. We show that our model is strongly robust to missing information to an extent that it can achieve the same performance with as low as 20% of the data.
  arXiv  Detail & Related papers  (2023-03-01T23:37:45Z)
• Towards an Automatic Analysis of CHO-K1 Suspension Growth in Microfluidic Single-cell Cultivation [63.94623495501023]
  We propose a novel Machine Learning architecture, which allows us to infuse a neural deep network with human-powered abstraction on the level of data. Specifically, we train a generative model simultaneously on natural and synthetic data, so that it learns a shared representation, from which a target variable, such as the cell count, can be reliably estimated.
  arXiv  Detail & Related papers  (2020-10-20T08:36:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.