mlsanityData to 14 Oct 2026

HUydra: Full-Range Lung CT Synthesis via Multiple HU Interval Generative Modelling

arXiv 2603.23041 ↗First posted 24 Mar 2026cs.CV cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Currently, a central challenge and bottleneck in the deployment and validation of computer-aided diagnosis (CAD) models within the field of medical imaging is data scarcity. For lung cancer, one of the most prevalent types worldwide, limited datasets can delay diagnosis and have an impact on patient outcome. Generative AI offers a promising solution for this issue, but dealing with the complex distribution of full Hounsfield Unit (HU) range lung CT scans is challenging and remains as a highly computationally demanding task. This paper introduces a novel decomposition strategy that synthesizes CT images one HU interval at a time, rather than modelling the entire HU domain at once. This framework focuses on training generative architectures on individual tissue-focused HU windows, then merges their output into a full-range scan via a learned reconstruction network that effectively reverses the HU-windowing process. We further propose multi-head and multi-decoder models to better capture textures while preserving anatomical consistency, with a multi-head VQVAE achieving the best performance for the generative task. Quantitative evaluation shows this approach significantly outperforms conventional 2D full-range baselines, achieving a 6.2% improvement in FID and superior MMD, Precision, and Recall across all HU intervals. The best performance is achieved by a multi-head VQVAE variant, demonstrating that it is possible to enhance visual fidelity and variability while also reducing model complexity and computational cost. This work establishes a new paradigm for structure-aware medical image synthesis, aligning generative modelling with clinical interpretation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 81 references that are in the map. First posted on arXiv 24 Mar 2026.

Builds on

35 of 81 references.

References · 35

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  4. 2017Neural Discrete Representation Learningcited by 4,712
  5. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  6. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  7. 2017Improved Training of Wasserstein GANscited by 2,235
  8. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  9. 2021Variational Diffusion Modelscited by 1,153
  10. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
  11. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 672
  12. 2017Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Losscited by 162
23 more
  1. 2018Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networkscited by 147
  2. 2018GANs for Medical Image Analysiscited by 81
  3. 2019Unsupervised Anomaly Localization using Variational Auto-Encoderscited by 73
  4. 2020Unsupervised Lesion Detection via Image Restoration with a Normative Priorcited by 65
  5. 2021GANs for Medical Image Synthesis: An Empirical Studycited by 65
  6. 2014Multi-Atlas Segmentation of Biomedical Images: A Surveycited by 56
  7. 2017How to Fool Radiologists with Generative Adversarial Networks? A Visual Turing Test for Lung Cancer Diagnosiscited by 35
  8. 2018CT-Realistic Lung Nodule Simulation from 3D Conditional Generative Adversarial Networks for Robust Lung Segmentationcited by 34
  9. 2024Fast-DDPM: Fast Denoising Diffusion Probabilistic Models for Medical Image-to-Image Generationcited by 33
  10. 2019Synthesizing Diverse Lung Nodules Wherever Massively: 3D Multi-Conditional GAN-based CT Image Augmentation for Object Detectioncited by 29
  11. 2024Cross-conditioned Diffusion Model for Medical Image to Image Translationcited by 26
  12. 2023Beware of diffusion models for synthesizing medical images -- A comparison with GANs in terms of memorizing brain MRI and chest x-ray imagescited by 23
  13. 2025MedVAE: Efficient Automated Interpretation of Medical Images with Large-Scale Generalizable Autoencoderscited by 22
  14. 2018On Catastrophic Forgetting and Mode Collapse in Generative Adversarial Networkscited by 17
  15. 2022Attri-VAE: attribute-based interpretable representations of medical images with variational autoencoderscited by 17
  16. 2024Exploring Variational Autoencoders for Medical Image Generation: A Comprehensive Studycited by 9
  17. 2024On Differentially Private 3D Medical Image Synthesis with Controllable Latent Diffusion Modelscited by 7
  18. 2019LGAN: Lung Segmentation in CT Scans Using Generative Adversarial Networkcited by 5
  19. 2025Lung-DDPM+: Efficient Thoracic CT Image Synthesis using Diffusion Probabilistic Modelcited by 4
  20. 2025LAND: Lung and Nodule Diffusion for 3D Chest CT Synthesis with Anatomical Guidancecited by 4
  21. 2022Evaluation of 3D GANs for Lung Tissue Modelling in Pulmonary CTcited by 3
  22. 20254D VQ-GAN: Synthesising Medical Scans at Any Time Point for Personalised Disease Progression Modelling of Idiopathic Pulmonary Fibrosiscited by 2
  23. 2025ART-ASyn: Anatomy-aware Realistic Texture-based Anomaly Synthesis Framework for Chest X-Rayscited by 1

Built on by

Not cited yet.