mlsanityData to 14 Oct 2026

CenSynCMB: Centre Maps and Physics-Guided Synthesis for Microbleed Detection

arXiv 2607.05325 ↗First posted 6 Jul 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Cerebral microbleeds (CMBs) are MRI markers of small vessel disease and the microbleed component of amyloid related imaging abnormalities (ARIA-H), but their small size, sparsity, and similarity to vessels, calcification-like foci, and artefacts make automated detection difficult. We propose CenSynCMB, a centre-guided and mimic-aware framework combining a 3D Attention U-Net, auxiliary centre-map supervision, false-negative-driven reweighting, and fold-wise physics-guided synthesis of positive CMBs and labelled hard negatives. Synthetic data expose the detector to compact lesions and common mimics without validation or test leakage. On VALDO Task 2, CenSynCMB achieved the best local-comparison lesion-level F1 (74.3%, p = 0.020); on external AIBL SWI, it achieved the highest local-comparison recall (88.5%, p = 0.0058) and F1 (65.0%, p = 0.0016). Together, these results support scalable CMB candidate extraction in large, unlabelled MRI cohorts, while highlighting cohort-specific calibration as the next step toward reliable burden estimation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 74 of its 92 references that are in the map. First posted on arXiv 6 Jul 2026.

Builds on

74 of 92 references.

References · 74

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  6. 2022Scalable Diffusion Models with Transformerscited by 6,054
  7. 2022Flow Matching for Generative Modelingcited by 5,702
  8. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  9. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  10. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  11. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  12. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
38 more
  1. 2019Generating Long Sequences with Sparse Transformerscited by 1,546
  2. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  3. 2021Variational Diffusion Modelscited by 1,153
  4. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 941
  5. 2020Object-Centric Learning with Slot Attentioncited by 876
  6. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 860
  7. 2021Going deeper with Image Transformerscited by 764
  8. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 737
  9. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 703
  10. 2023Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Modelscited by 702
  11. 2018Disentangling by Factorisingcited by 616
  12. 2017Opening the Black Box of Deep Neural Networks via Informationcited by 503
  13. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representationcited by 449
  14. 2023Simple diffusion: End-to-end diffusion for high resolution imagescited by 422
  15. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 392
  16. 2019Multi-Object Representation Learning with Iterative Variational Inferencecited by 360
  17. 2018Understanding disentangling in β-VAEcited by 335
  18. 2023Understanding Diffusion Objectives as the ELBO with Simple Data Augmentationcited by 304
  19. 2022Perception Prioritized Training of Diffusion Modelscited by 303
  20. 2020ReZero is All You Need: Fast Convergence at Large Depthcited by 264
  21. 2023Efficient Diffusion Training via Min-SNR Weighting Strategycited by 246
  22. 2022What the DAAM: Interpreting Stable Diffusion Using Cross Attentioncited by 236
  23. 2019GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representationscited by 227
  24. 2025REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformerscited by 225
  25. 2022Bridging the Gap to Real-World Object-Centric Learningcited by 220
  26. 2019Fixup Initialization: Residual Learning Without Normalizationcited by 198
  27. 2023On the Importance of Noise Scheduling for Diffusion Modelscited by 194
  28. 2021Illiterate DALL-E Learns to Composecited by 147
  29. 2023DiffusionSat: A Generative Foundation Model for Satellite Imagerycited by 131
  30. 2019On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Datasetcited by 100
  31. 2021ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentationcited by 93
  32. 2023Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Taskcited by 93
  33. 2023Object-Centric Slot Diffusioncited by 90
  34. 2022RoentGen: Vision-Language Foundation Model for Chest X-ray Generationcited by 89
  35. 2023SlotDiffusion: Object-Centric Generative Modeling with Diffusion Modelscited by 85
  36. 2023SODA: Bottleneck Diffusion Models for Representation Learningcited by 77
  37. 2024Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusioncited by 75
  38. 2024Building Machines that Learn and Think with Peoplecited by 73

50 most cited of 74 All 74 (JSON)

Built on by

Not cited yet.