mlsanityData to 14 Oct 2026

DiffMix: Diffusion Model-based Data Synthesis for Nuclei Segmentation and Classification in Imbalanced Pathology Image Datasets

arXiv 2306.14132 ↗First posted 25 Jun 2023cs.CVcited by 28

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Nuclei segmentation and classification is a significant process in pathology image analysis. Deep learning-based approaches have greatly contributed to the higher accuracy of this task. However, those approaches suffer from the imbalanced nuclei data composition, which shows lower classification performance on the rare nuclei class. In this paper, we propose a realistic data synthesis method using a diffusion model. We generate two types of virtual patches to enlarge the training data distribution, which is for balancing the nuclei class variance and for enlarging the chance to look at various nuclei. After that, we use a semantic-label-conditioned diffusion model to generate realistic and high-quality image samples. We demonstrate the efficacy of our method by experiment results on two imbalanced nuclei datasets, improving the state-of-the-art networks. The experimental results suggest that the proposed method improves the classification performance of the rare type nuclei classification, while showing superior segmentation and classification performance in imbalanced pathology nuclei datasets.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 16 of its 24 references that are in the map. First posted on arXiv 25 Jun 2023.

Builds on

16 of 24 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Diffusion Models for Medical Anomaly Detection8 Mar

Other references · 15

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  5. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  6. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  7. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  8. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  9. 2018HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Imagescited by 388
  10. 2022Semantic Image Synthesis via Diffusion Modelscited by 132
  11. 2018Micro-Net: A unified model for segmentation of various objects in microscopy imagescited by 56
  12. 2021A Comprehensive Review of Computer-aided Whole-slide Image Analysis: from Datasets to Feature Extraction, Segmentation, Classification, and Detection Approachescited by 44
3 more
  1. 2022InsMix: Towards Realistic Generative Data Augmentation for Nuclei Instance Segmentationcited by 19
  2. 2022GradMix for nuclei segmentation and classification in imbalanced pathology image datasetscited by 6
  3. 2022SIAN: Style-Guided Instance-Adaptive Normalization for Multi-Organ Histopathology Image Synthesiscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 11; 2025: 11; 2026: 4.

28 papers.

Sort:

By area:

  1. 2024TopoCellGen: Generating Histopathology Cell Topology with a Diffusion Modelcited by 16
  2. 2023AI-Generated Images as Data Source: The Dawn of Synthetic Eracited by 13
  3. 2025A Comprehensive Survey on Imbalanced Data Learningcited by 10
  4. 2025PathDiff: Histopathology Image Synthesis with Unpaired Text and Mask Conditionscited by 9
  5. 2024Controllable and Efficient Multi-Class Pathology Nuclei Data Augmentation using Text-Conditioned Diffusion Modelscited by 8
  6. 2024Co-synthesis of Histopathology Nuclei Image-Label Pairs using a Context-Conditioned Joint Diffusion Modelcited by 8
  7. 2025TRACE: Temporally Reliable Anatomically-Conditioned 3D CT Generation with Enhanced Efficiencycited by 8
  8. 2025GAITGen: Disentangled Motion-Pathology Impaired Gait Generative Model -- Bringing Motion Generation to the Clinical Domaincited by 7
  9. 2025Content Generation Models in Computational Pathology: A Comprehensive Survey on Methods, Applications, and Challengescited by 5
  10. 2024An Organism Starts with a Single Pix-Cell: A Neural Cellular Diffusion for High-Resolution Image Synthesiscited by 4
  11. 2024Histo-Diffusion: A Diffusion Super-Resolution Method for Digital Pathology with Comprehensive Quality Assessmentcited by 4
  12. 2025DAViD: Modeling Dynamic Affordance of 3D Objects Using Pre-trained Video Diffusion Modelscited by 4
16 more
  1. 2025Synthetic Data Augmentation using Pre-trained Diffusion Models for Long-tailed Food Image Classificationcited by 3
  2. 2024An Ordinal Diffusion Model for Generating Medical Images with Different Severity Levelscited by 2
  3. 2024Mask-guided cross-image attention for zero-shot in-silico histopathologic image generation with a diffusion modelcited by 2
  4. 2024HisynSeg: Weakly-Supervised Histopathological Image Segmentation via Image-Mixing Synthesis and Consistency Regularizationcited by 2
  5. 2023Combining Datasets with Different Label Sets for Improved Nucleus Segmentation and Classificationcited by 1
  6. 2024AdaptDiff: Cross-Modality Domain Adaptation via Weak Conditional Semantic Diffusion for Retinal Vessel Segmentationcited by 1
  7. 2024Comparative Analysis of Diffusion Generative Models in Computational Pathologycited by 1
  8. 2025Computationally Efficient Diffusion Models in Medical Imaging: A Comprehensive Reviewcited by 1
  9. 2025Zero-shot CT Super-Resolution using Diffusion-based 2D Projection Priors and Signed 3D Gaussianscited by 1
  10. 2026Geometrically Constrained Stenosis Editing in Coronary Angiography via Entropic Optimal Transportcited by 1
  11. 2024Contrastive-Adversarial and Diffusion: Exploring pre-training and fine-tuning strategies for sulcal identificationcited by 0
  12. 2025Instance Migration Diffusion for Nuclear Instance Segmentation in Pathologycited by 0
  13. 2025MSDM: Generating Task-Specific Pathology Images with a Multimodal Conditioned Diffusion Model for Cell and Nuclei Segmentationcited by 0
  14. 2026Layout-Guided Controllable Pathology Image Generation with In-Context Diffusion Transformerscited by 0
  15. 2026Central-to-Local Adaptive Generative Diffusion Framework for Improving Gene Expression Prediction in Data-Limited Spatial Transcriptomicscited by 0
  16. 2026Compositional Reward Models for Conditional Medical Image Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Diffusion-based Data Augmentation for Nuclei Image Segmentation
  2. 2024NucleiMix: Realistic Data Augmentation for Nuclei Instance Segmentation
  3. 2023NASDM: Nuclei-Aware Semantic Histopathology Image Generation Using Diffusion Models
  4. 2025PathSegDiff: Pathology Segmentation using Diffusion model representations
  5. 2023DiffBoost: Enhancing Medical Image Segmentation via Text-Guided Diffusion Model
  6. 2023Semi-Supervised Semantic Segmentation of Cell Nuclei via Diffusion-based Large-Scale Pre-Training and Collaborative Learning
  7. 2026From UNI2-h to ConvNeXt-T: Lightweight Nuclei Instance Segmentation via Knowledge Distillation
  8. 2023Latent Diffusion Models with Image-Derived Annotations for Enhanced AI-Assisted Cancer Diagnosis in Histopathology