mlsanityData to 7 Oct 2026

Mitigating 3D Prostate Biparametric MRI Data Scarcity through Domain Adaptation using Locally-Trained Latent Diffusion Models for Prostate Cancer Detection

arXiv 2507.06384 ↗First posted 8 Jul 2025eess.IV cs.CVcited by 0

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Objective: Latent diffusion models (LDMs) could mitigate data scarcity challenges affecting machine learning development for medical image interpretation. The recent CCELLA LDM improved prostate cancer detection performance using synthetic MRI for classifier training but was limited to the axial T2-weighted (AxT2) sequence, did not investigate inter-institutional domain shift, and prioritized PI-RADS over histopathology outcomes. Methods: We propose CCELLA++, a novel LDM pipeline for simultaneous 3D biparametric prostate MRI (bpMRI) generation, including the AxT2, high b-value diffusion series (HighB) and apparent diffusion coefficient map (ADC), to overcome these limitations. We investigated source-free domain adaptation with classifiers pretrained on single institution real or LDM-generated synthetic data prior to fine-tuning on fractions of an out-of-distribution, external dataset. Results: CCELLA++ achieved comparable AxT2 Kernel Inception Distance to CCELLA (0.0128, 0.0131 respectively). CCELLA++ synthetic bpMRI pretraining outperformed real bpMRI in AP and AUC up to 12.5% (n<=166) external dataset volume (p<0.01 all), no pretraining in AUC up to 25% external volume (n=332, p<0.05 all), and CCELLA AxT2-only pretraining in both data-scarce (n=83, p<0.001 AP and AUC) and full data (n=1329, p<0.05 AP and AUC) scenarios. Conclusion: CCELLA++ synthetic bpMRI can improve downstream classifier generalization and performance beyond real bpMRI or CCELLA-generated AxT2-only images. Future work should quantify medical image quality, balance bpMRI LDM training, and condition the LDM with additional information. Significance: CCELLA++ can generate synthetic bpMRI that outperforms real data for domain adaptation with data-scarce external institutions, advancing machine learning development for medical imaging. Our code is available at https://github.com/grabkeem/CCELLA-plus-plus

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 21 of its 38 references that are in the map. First posted on arXiv 8 Jul 2025.

Builds on

21 of 38 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025Leveraging Clinical Text and Class Conditioning for 3D Prostate MRI Generation11 Jun
  2. 2024Physics-Informed Latent Diffusion for Multimodal Brain MRI Synthesis20 Sep
  3. 2024MAISI: Medical AI for Synthetic Imaging13 Sep
  4. 2024Cross-conditioned Diffusion Model for Medical Image to Image Translation13 Sep
  5. 2023A Survey of Emerging Applications of Diffusion Probabilistic Models in MRI19 Nov
  6. 2023CoLa-Diff: Conditional Latent Diffusion Model for Multi-Modal MRI Synthesis24 Mar
  7. 2023Medical diffusion on a budget: Textual Inversion for medical image generation23 Mar
  8. 2023Bi-parametric prostate MR image synthesis using pathology and sequence-conditioned stable diffusion3 Mar
  9. 2022Diffusion Models for Medical Image Analysis: A Comprehensive Survey14 Nov

Other references · 12

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  4. 2018Demystifying MMD GANscited by 1,268
  5. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,182
  6. 2019A Closer Look at Few-shot Classificationcited by 679
  7. 2021Domain Adaptation for Medical Image Analysis: A Surveycited by 351
  8. 2019A Baseline for Few-Shot Image Classificationcited by 298
  9. 2019Med3D: Transfer Learning for 3D Medical Image Analysiscited by 282
  10. 2018Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysiscited by 178
  11. 2021Annotation-efficient cancer detection with report-guided lesion annotation for deep learning-based prostate cancer detection in bpMRIcited by 11
  12. 2019A Transfer Learning Approach for Automated Segmentation of Prostate Whole Gland and Transition Zone in Diffusion Weighted MRIcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Cancer-Net PCa-Gen: Synthesis of Realistic Prostate Diffusion Weighted Imaging Data via Anatomic-Conditional Controlled Latent Diffusion
  2. 2024DISC: Latent Diffusion Models with Self-Distillation from Separated Conditions for Prostate Cancer Grading
  3. 2026Semi-Supervised Domain Adaptation with Latent Diffusion for Pathology Image Classification
  4. 2026PCaPaint: Prostate Cancer Inpainting by Mitigating Shortcut Learning
  5. 2026Maximizing T2-Only Prostate Cancer Localization from Expected Diffusion Weighted Imaging
  6. 2025Conditional Diffusion Models are Medical Image Classifiers that Provide Explainability and Uncertainty for Free
  7. 2025Can Diffusion Models Bridge the Domain Gap in Cardiac MR Imaging?
  8. 2023Adaptive Latent Diffusion Model for 3D Medical Image to Image Translation: Multi-modal Magnetic Resonance Imaging Study