Improved Sub-Visible Particle Classification in Flow Imaging Microscopy via Generative AI-Based Image Synthesis

• URL: http://arxiv.org/abs/2508.06021v1
• Date: Fri, 08 Aug 2025 05:15:02 GMT
• Title: Improved Sub-Visible Particle Classification in Flow Imaging Microscopy via Generative AI-Based Image Synthesis
• Authors: Utku Ozbulak, Michaela Cohrs, Hristo L. Svilenov, Joris Vankerschaver, Wesley De Neve,
• Abstract summary: Sub-visible particle analysis using flow imaging microscopy combined with deep learning has proven effective in identifying particle types.<n>However, the scarcity of available data and severe imbalance between particle types within datasets remain substantial hurdles.<n>We develop a state-of-the-art diffusion model to address data imbalance by generating high-fidelity images that can augment training datasets.
• Score: 1.172405562070645
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Sub-visible particle analysis using flow imaging microscopy combined with deep learning has proven effective in identifying particle types, enabling the distinction of harmless components such as silicone oil from protein particles. However, the scarcity of available data and severe imbalance between particle types within datasets remain substantial hurdles when applying multi-class classifiers to such problems, often forcing researchers to rely on less effective methods. The aforementioned issue is particularly challenging for particle types that appear unintentionally and in lower numbers, such as silicone oil and air bubbles, as opposed to protein particles, where obtaining large numbers of images through controlled settings is comparatively straightforward. In this work, we develop a state-of-the-art diffusion model to address data imbalance by generating high-fidelity images that can augment training datasets, enabling the effective training of multi-class deep neural networks. We validate this approach by demonstrating that the generated samples closely resemble real particle images in terms of visual quality and structure. To assess the effectiveness of using diffusion-generated images in training datasets, we conduct large-scale experiments on a validation dataset comprising 500,000 protein particle images and demonstrate that this approach improves classification performance with no negligible downside. Finally, to promote open research and reproducibility, we publicly release both our diffusion models and the trained multi-class deep neural network classifiers, along with a straightforward interface for easy integration into future studies, at https://github.com/utkuozbulak/svp-generative-ai.

Related papers

• Quantification and Classification of Carbon Nanotubes in Electron Micrographs using Vision Foundation Models [1.8969168959157112]
  This work presents a unified framework leveraging vision foundation models to automate the quantification and classification of CNTs in electron microscopy images.<n>We introduce an interactive quantification tool built on the Segment Anything Model (SAM) that segments particles with near-perfect accuracy using minimal user input.<n>Second, we propose a novel classification pipeline that utilizes these segmentation masks to spatially constrain a DINOv2 vision transformer, extracting features exclusively from particle regions while suppressing background noise.<n> Evaluated on a dataset of 1,800 TEM images, this architecture achieves 95.5% accuracy in distinguishing between four different CNT morphologies, significantly outperforming the current baseline despite using a
  arXiv  Detail & Related papers  (2026-01-10T20:22:58Z)
• Diffusion-Based Synthetic Brightfield Microscopy Images for Enhanced Single Cell Detection [0.0]
  We investigate the use of unconditional models to generate synthetic brightfield microscopy images.<n>A U-Net based diffusion model was trained and used to create datasets with varying ratios of synthetic and real images.<n>Experiments with YOLOv8, YOLOv9 and RT-DETR reveal that training with synthetic data can achieve improved detection accuracies.
  arXiv  Detail & Related papers  (2025-11-25T08:57:23Z)
• Diffusion Prism: Enhancing Diversity and Morphology Consistency in Mask-to-Image Diffusion [4.0301593672451]
  Diffusion Prism is a training-free framework that transforms binary masks into realistic and diverse samples.<n>We explore that a small amount of artificial noise will significantly assist the image-denoising process.
  arXiv  Detail & Related papers  (2025-01-01T20:04:25Z)
• MaskTerial: A Foundation Model for Automated 2D Material Flake Detection [48.73213960205105]
  We present a deep learning model, called MaskTerial, that uses an instance segmentation network to reliably identify 2D material flakes.<n>The model is extensively pre-trained using a synthetic data generator, that generates realistic microscopy images from unlabeled data.<n>We demonstrate significant improvements over existing techniques in the detection of low-contrast materials such as hexagonal boron nitride.
  arXiv  Detail & Related papers  (2024-12-12T15:01:39Z)
• Understanding and Improving Training-Free AI-Generated Image Detections with Vision Foundation Models [68.90917438865078]
  Deepfake techniques for facial synthesis and editing pose serious risks for generative models.<n>In this paper, we investigate how detection performance varies across model backbones, types, and datasets.<n>We introduce Contrastive Blur, which enhances performance on facial images, and MINDER, which addresses noise type bias, balancing performance across domains.
  arXiv  Detail & Related papers  (2024-11-28T13:04:45Z)
• Self-Supervised and Few-Shot Learning for Robust Bioaerosol Monitoring [0.0]
  We show that self-supervised learning and few-shot learning can be combined to classify holographic images of bioaerosol particles. Our findings suggest that real-time bioaerosol monitoring can be substantially optimized.
  arXiv  Detail & Related papers  (2024-06-14T12:48:26Z)
• A Phase Transition in Diffusion Models Reveals the Hierarchical Nature of Data [51.03144354630136]
  Recent advancements show that diffusion models can generate high-quality images.<n>We study this phenomenon in a hierarchical generative model of data.<n>We find that the backward diffusion process acting after a time $t$ is governed by a phase transition.
  arXiv  Detail & Related papers  (2024-02-26T19:52:33Z)
• Feedback Efficient Online Fine-Tuning of Diffusion Models [52.170384048274364]
  We propose a novel reinforcement learning procedure that efficiently explores on the manifold of feasible samples. We present a theoretical analysis providing a regret guarantee, as well as empirical validation across three domains.
  arXiv  Detail & Related papers  (2024-02-26T07:24:32Z)
• Training Class-Imbalanced Diffusion Model Via Overlap Optimization [55.96820607533968]
  Diffusion models trained on real-world datasets often yield inferior fidelity for tail classes. Deep generative models, including diffusion models, are biased towards classes with abundant training images. We propose a method based on contrastive learning to minimize the overlap between distributions of synthetic images for different classes.
  arXiv  Detail & Related papers  (2024-02-16T16:47:21Z)
• DiffMix: Diffusion Model-based Data Synthesis for Nuclei Segmentation and Classification in Imbalanced Pathology Image Datasets [8.590026259176806]
  We propose a realistic data synthesis method using a diffusion model. We generate two types of virtual patches to enlarge the training data distribution. We use a semantic-label-conditioned diffusion model to generate realistic and high-quality image samples.
  arXiv  Detail & Related papers  (2023-06-25T05:31:08Z)
• Your Diffusion Model is Secretly a Zero-Shot Classifier [90.40799216880342]
  We show that density estimates from large-scale text-to-image diffusion models can be leveraged to perform zero-shot classification. Our generative approach to classification attains strong results on a variety of benchmarks. Our results are a step toward using generative over discriminative models for downstream tasks.
  arXiv  Detail & Related papers  (2023-03-28T17:59:56Z)
• Unpaired Image-to-Image Translation with Limited Data to Reveal Subtle Phenotypes [0.5076419064097732]
  We present an improved CycleGAN architecture that employs self-supervised discriminators to alleviate the need for numerous images. We also provide results obtained with small biological datasets on obvious and non-obvious cell phenotype variations.
  arXiv  Detail & Related papers  (2023-01-21T16:25:04Z)
• Synthetic Image Rendering Solves Annotation Problem in Deep Learning Nanoparticle Segmentation [5.927116192179681]
  We show that using a rendering software allows to generate realistic, synthetic training data to train a state-of-the art deep neural network. We derive a segmentation accuracy that is comparable to man-made annotations for toxicologically relevant metal-oxide nanoparticles ensembles.
  arXiv  Detail & Related papers  (2020-11-20T17:05:36Z)

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.