Data Synthesis Improves 3D Myotube Instance Segmentation

• URL: http://arxiv.org/abs/2604.14720v1
• Date: Thu, 16 Apr 2026 07:30:20 GMT
• Title: Data Synthesis Improves 3D Myotube Instance Segmentation
• Abstract summary: We introduce a geometry-driven pipeline that models individual myotubes via centerlines, locally varying radii, branching structures, and ellipsoidal end caps from real microscopy observations.<n>A compact 3D U-Net with self-supervised encoder pretraining, trained exclusively on synthetic data, achieves a mean IPQ of 0.22 on real data, significantly outperforming three established zero-shot segmentation models.
• Score: 1.4621946932173584
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Myotubes are multinucleated muscle fibers serving as key model systems for studying muscle physiology, disease mechanisms, and drug responses. Mechanistic studies and drug screening thereby rely on quantitative morphological readouts such as diameter, length, and branching degree, which in turn require precise three-dimensional instance segmentation. Yet established pretrained biomedical segmentation models fail to generalize to this domain due to the absence of large annotated myotube datasets. We introduce a geometry-driven synthesis pipeline that models individual myotubes via polynomial centerlines, locally varying radii, branching structures, and ellipsoidal end caps derived from real microscopy observations. Synthetic volumes are rendered with realistic noise, optical artifacts, and CycleGAN-based Domain Adaptation (DA). A compact 3D U-Net with self-supervised encoder pretraining, trained exclusively on synthetic data, achieves a mean IPQ of 0.22 on real data, significantly outperforming three established zero-shot segmentation models, demonstrating that biophysics-driven synthesis enables effective instance segmentation in annotation-scarce biomedical domains.

Related papers

• A Physics-Flavored Transformer Network for Parametrizing Contraction Dynamics of Engineered Skeletal Muscle Tissues [0.0]
  We present a Physics-Flavored Neural Network (PFNN) that automates the kinetic phenotyping of ESMs.<n>Our architecture integrates a stretched-exponential physical model into a CNN-Transformer, enabling the extraction of physically meaningful parameters.<n>Our results demonstrate that this physics-flavored approach achieves high-fidelity parameterization across diverse contractile phenotypes and cell lines.
  arXiv  Detail & Related papers  (2026-08-04T16:59:30Z)
• VesselSim: learning 3D blood vessel segmentation without expert annotations [7.634402582162916]
  We propose VesselSim, a two-stage framework for universal 3D blood vessel segmentation.<n>A 3D U-Net is trained solely on synthetic data to generate 16,500 anatomically plausible 3D angiographic volumes.<n>VesselSim achieves competitive performance with state-of-the-art segmentation foundation models.
  arXiv  Detail & Related papers  (2026-05-25T19:04:18Z)
• Data-Efficient Meningioma Segmentation via Implicit Spatiotemporal Mixing and Sim2Real Semantic Injection [6.992254817538211]
  We propose a novel dual-augmentation framework that integrates spatial manifold expansion and semantic object injection.<n>We show that our framework significantly enhances the data efficiency and robustness of state-of-the-art models, including nnU-Net and U-Mamba.
  arXiv  Detail & Related papers  (2026-01-19T09:11:28Z)
• SynapFlow: A Modular Framework Towards Large-Scale Analysis of Dendritic Spines [4.377081487137802]
  Dendritic spines are key structural components of excitatory synapses in the brain.<n>Despite their relevance, large-scale analyses of the structural dynamics of dendritic spines in 3D+time microscopy data remain challenging.<n>Here, we present a modular machine learning-based pipeline designed to automate the detection, time-tracking, and feature extraction of dendritic spines.
  arXiv  Detail & Related papers  (2025-09-23T12:47:43Z)
• Towards Generalized Synapse Detection Across Invertebrate Species [0.07999703756441755]
  SimpSyn is a single-stage Residual U-Net trained to predict dual-channel spherical masks around pre- and post-synaptic sites.<n>It consistently outperforms Synful in F1-score across all volumes for synaptic site detection.
  arXiv  Detail & Related papers  (2025-09-21T11:40:49Z)
• Synthetic Data for Blood Vessel Network Extraction [18.95453617434051]
  Blood vessel networks in the brain play a crucial role in stroke research, where understanding their topology is essential.<n> extracting detailed topological vessel network information from microscopy data remains a significant challenge.<n>This work combines synthetic data generation with deep learning to automatically extract vessel networks as graphs from volumetric microscopy data.
  arXiv  Detail & Related papers  (2025-04-16T08:29:46Z)
• Enhanced segmentation of femoral bone metastasis in CT scans of patients using synthetic data generation with 3D diffusion models [0.06700983301090582]
  We propose an automated data pipeline using 3D Denoising Diffusion Probabilistic Models (DDPM) to generalize on new images. We created 5675 new volumes, then trained 3D U-Net segmentation models on real and synthetic data to compare segmentation performance.
  arXiv  Detail & Related papers  (2024-09-17T09:21:19Z)
• ShapeMamba-EM: Fine-Tuning Foundation Model with Local Shape Descriptors and Mamba Blocks for 3D EM Image Segmentation [49.42525661521625]
  This paper presents ShapeMamba-EM, a specialized fine-tuning method for 3D EM segmentation. It is tested over a wide range of EM images, covering five segmentation tasks and 10 datasets.
  arXiv  Detail & Related papers  (2024-08-26T08:59:22Z)
• Dataset Distillation for Histopathology Image Classification [46.04496989951066]
  We introduce a novel dataset distillation algorithm tailored for histopathology image datasets (Histo-DD) We conduct a comprehensive evaluation of the effectiveness of the proposed algorithm and the generated histopathology samples in both patch-level and slide-level classification tasks.
  arXiv  Detail & Related papers  (2024-08-19T05:53:38Z)
• Leveraging Frequency Domain Learning in 3D Vessel Segmentation [50.54833091336862]
  In this study, we leverage Fourier domain learning as a substitute for multi-scale convolutional kernels in 3D hierarchical segmentation models. We show that our novel network achieves remarkable dice performance (84.37% on ASACA500 and 80.32% on ImageCAS) in tubular vessel segmentation tasks.
  arXiv  Detail & Related papers  (2024-01-11T19:07:58Z)
• Interpretable 2D Vision Models for 3D Medical Images [47.75089895500738]
  This study proposes a simple approach of adapting 2D networks with an intermediate feature representation for processing 3D images. We show on all 3D MedMNIST datasets as benchmark and two real-world datasets consisting of several hundred high-resolution CT or MRI scans that our approach performs on par with existing methods.
  arXiv  Detail & Related papers  (2023-07-13T08:27:09Z)
• 3D Mitochondria Instance Segmentation with Spatio-Temporal Transformers [101.44668514239959]
  We propose a hybrid encoder-decoder framework that efficiently computes spatial and temporal attentions in parallel. We also introduce a semantic clutter-background adversarial loss during training that aids in the region of mitochondria instances from the background.
  arXiv  Detail & Related papers  (2023-03-21T17:58:49Z)
• gACSON software for automated segmentation and morphology analyses of myelinated axons in 3D electron microscopy [55.78588835407174]
  We introduce a freely available gACSON software for visualization, segmentation, assessment, and morphology analysis of myelinated axons in 3D-EM volumes. gACSON automatically segments the intra-axonal space of myelinated axons and their corresponding myelin sheaths. It analyzes the morphology of myelinated axons, such as axonal diameter, axonal eccentricity, myelin thickness, or g-ratio.
  arXiv  Detail & Related papers  (2021-12-13T08:17:15Z)
• 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.