Large-scale EM Benchmark for Multi-Organelle Instance Segmentation in the Wild

• URL: http://arxiv.org/abs/2601.12464v1
• Date: Sun, 18 Jan 2026 16:09:27 GMT
• Title: Large-scale EM Benchmark for Multi-Organelle Instance Segmentation in the Wild
• Authors: Yanrui Lu, Danyang Chen, Haowen Xiao, Jiarui Zhu, Fukang Ge, Binqian Zou, Jiali Guan, Jiayin Liang, Yuting Wang, Ziqian Guan, Xiangcheng Bao, Jinhao Bi, Lin Gu, Jun He, Yingying Zhu,
• Abstract summary: We develop a benchmark for multi-organelle instance segmentation, comprising over 100,000 2D EM images across variety cell types and five organelle classes that capture real-world variability.<n>Our results show several limitations: current models struggle to generalize across heterogeneous EM data and perform poorly on organelles with global, distributed morphologies.<n>These findings underscore the fundamental mismatch between local-context models and the challenge of modeling long-range structural continuity in the presence of real-world variability.
• Score: 8.670858548670742
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate instance-level segmentation of organelles in electron microscopy (EM) is critical for quantitative analysis of subcellular morphology and inter-organelle interactions. However, current benchmarks, based on small, curated datasets, fail to capture the inherent heterogeneity and large spatial context of in-the-wild EM data, imposing fundamental limitations on current patch-based methods. To address these limitations, we developed a large-scale, multi-source benchmark for multi-organelle instance segmentation, comprising over 100,000 2D EM images across variety cell types and five organelle classes that capture real-world variability. Dataset annotations were generated by our designed connectivity-aware Label Propagation Algorithm (3D LPA) with expert refinement. We further benchmarked several state-of-the-art models, including U-Net, SAM variants, and Mask2Former. Our results show several limitations: current models struggle to generalize across heterogeneous EM data and perform poorly on organelles with global, distributed morphologies (e.g., Endoplasmic Reticulum). These findings underscore the fundamental mismatch between local-context models and the challenge of modeling long-range structural continuity in the presence of real-world variability. The benchmark dataset and labeling tool will be publicly released soon.

Related papers

• scMRDR: A scalable and flexible framework for unpaired single-cell multi-omics data integration [53.683726781791385]
  We introduce a scalable and flexible generative framework called single-cell Multi-omics Regularized Disentangled Representations (scMRDR) for unpaired multi-omics integration.<n>Our method achieves excellent performance on benchmark datasets in terms of batch correction, modality alignment, and biological signal preservation.
  arXiv  Detail & Related papers  (2025-10-28T21:28:39Z)
• MSDM: Generating Task-Specific Pathology Images with a Multimodal Conditioned Diffusion Model for Cell and Nuclei Segmentation [0.3650448386461648]
  We introduce a Multimodal Semantic Diffusion Model for generating pixel-precise image-mask pairs for cell and nuclei segmentation.<n>By conditioning the generative process with cellular/nuclear morphologies, MSDM generates datasests with desired morphological properties.<n>We highlight the effectiveness of multimodal diffusion-based augmentation for advancing the robustness and generalizability of cell and nuclei segmentation models.
  arXiv  Detail & Related papers  (2025-10-10T08:23:14Z)
• AMA-SAM: Adversarial Multi-Domain Alignment of Segment Anything Model for High-Fidelity Histology Nuclei Segmentation [2.52189149988768]
  We introduce Adrial Multi-domain Alignment of Segment Anything Model (AMA-SAM) that extends the Segment Anything Model (SAM) to overcome obstacles through two key innovations.<n>First, we propose a Conditional Gradient Reversal Layer (CGRL) that harmonizes features from diverse domains to promote domain-invariant representation learning.<n>Second, we address SAM's inherent low-resolution output by designing a High-Resolution Decoder (HR-Decoder) which directly produces fine-grained segmentation maps.
  arXiv  Detail & Related papers  (2025-03-27T16:59:39Z)
• Toward Generalizable Multiple Sclerosis Lesion Segmentation Models [0.0]
  This study aims to develop models that generalize across diverse evaluation datasets. We used all high-quality publicly-available MS lesion segmentation datasets on which we systematically trained a state-of-the-art UNet++ architecture.
  arXiv  Detail & Related papers  (2024-10-25T15:21:54Z)
• Multi-Modal and Multi-Attribute Generation of Single Cells with CFGen [76.02070962797794]
  This work introduces CellFlow for Generation (CFGen), a flow-based conditional generative model that preserves the inherent discreteness of single-cell data.<n>CFGen generates whole-genome multi-modal single-cell data reliably, improving the recovery of crucial biological data characteristics.
  arXiv  Detail & Related papers  (2024-07-16T14:05:03Z)
• GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models [56.63218531256961]
  We introduce GenBench, a benchmarking suite specifically tailored for evaluating the efficacy of Genomic Foundation Models. GenBench offers a modular and expandable framework that encapsulates a variety of state-of-the-art methodologies. We provide a nuanced analysis of the interplay between model architecture and dataset characteristics on task-specific performance.
  arXiv  Detail & Related papers  (2024-06-01T08:01:05Z)
• Learning Multiscale Consistency for Self-supervised Electron Microscopy Instance Segmentation [48.267001230607306]
  We propose a pretraining framework that enhances multiscale consistency in EM volumes. Our approach leverages a Siamese network architecture, integrating strong and weak data augmentations. It effectively captures voxel and feature consistency, showing promise for learning transferable representations for EM analysis.
  arXiv  Detail & Related papers  (2023-08-19T05:49:13Z)
• Topologically Regularized Multiple Instance Learning to Harness Data Scarcity [15.06687736543614]
  Multiple Instance Learning models have emerged as a powerful tool to classify patients' microscopy samples. We introduce a topological regularization term to MIL to mitigate this challenge. We show an average enhancement of 2.8% for MIL benchmarks, 15.3% for synthetic MIL datasets, and 5.5% for real-world biomedical datasets over the current state-of-the-art.
  arXiv  Detail & Related papers  (2023-07-26T08:14:18Z)
• 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)
• DuAT: Dual-Aggregation Transformer Network for Medical Image Segmentation [21.717520350930705]
  Transformer-based models have been widely demonstrated to be successful in computer vision tasks. However, they are often dominated by features of large patterns leading to the loss of local details. We propose a Dual-Aggregation Transformer Network called DuAT, which is characterized by two innovative designs. Our proposed model outperforms state-of-the-art methods in the segmentation of skin lesion images, and polyps in colonoscopy images.
  arXiv  Detail & Related papers  (2022-12-21T07:54:02Z)
• 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)
• Generalized Matrix Factorization: efficient algorithms for fitting generalized linear latent variable models to large data arrays [62.997667081978825]
  Generalized Linear Latent Variable models (GLLVMs) generalize such factor models to non-Gaussian responses. Current algorithms for estimating model parameters in GLLVMs require intensive computation and do not scale to large datasets. We propose a new approach for fitting GLLVMs to high-dimensional datasets, based on approximating the model using penalized quasi-likelihood.
  arXiv  Detail & Related papers  (2020-10-06T04:28:19Z)

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.