Controllable Lung Nodule Synthesis via Histogram-Regularized Latent Diffusion Models
Quick Take
The proposed controllable latent diffusion model synthesizes diverse pulmonary nodules in 3D CT volumes by incorporating histogram-based regularization, enhancing lesion-level intensity distributions. This approach improves visual realism and subtype consistency, leading to better performance in clinical tasks, particularly for underrepresented nodule types.
Key Points
- Introduces a histogram-based regularization term for better intensity distribution modeling.
- Synthesizes solid, part-solid, and ground-glass nodules in full 3D CT volumes.
- Achieves strong visual realism validated by quantitative metrics and Turing tests.
- Improves performance in clinical tasks through effective data augmentation.
- Addresses limitations of existing models that produce over-smoothed textures.
Article Content
From source RSS / original summaryarXiv:2605. 30631v1 Announce Type: new Abstract: While automated diagnosis systems have achieved remarkable success in computed tomography (CT)-based lung cancer screening, their development remains limited by the scarcity of diverse, annotated pulmonary nodule datasets.
Diffusion-based generative models offer a promising strategy for data synthesis; however, many existing conditional approaches primarily optimize spatial reconstruction losses, which encourage voxel-wise similarity but may inadequately constrain lesion-level intensity distributions. As a result, these methods may produce over-smoothed texture profiles and underrepresent the distinct attenuation characteristics of different nodule subtypes, including solid, part-solid, and ground-glass nodules.
To address this challenge, we propose a controllable latent diffusion model that synthesizes pulmonary nodules within full 3D CT volumes while accurately modeling nodule-specific intensity distributions. Specifically, rather than relying solely on spatial losses, we introduce a histogram-based regularization term that constrains voxel intensity distributions during the generative process.
The model combines subtype, spatial mask, and Hounsfield unit (HU) histogram conditioning with the differentiable feature-space histogram regularization term to better align lesion-level intensity distributions, improving the visual plausibility and subtype consistency of synthesized nodules. Extensive experiments on lung CT data demonstrate that our framework achieves strong visual realism, validated through both quantitative metrics and a visual Turing test.
Furthermore, when used for data augmentation, the generated nodules improve performance in downstream clinical tasks, particularly for underrepresented nodule subtypes, and show a potential benefit for subtype-informed malignancy classification.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →Evi-Steer: Learning to Steer Biomedical Vision-Language Models through Efficient and Generalizable Evidential Tuning
Evi-Steer introduces a novel evidential tuning framework for BiomedCLIP, enabling efficient fine-tuning with only 0.11% parameter updates. It significantly enhances performance in few-shot learning and domain shifts across 15 biomedical imaging datasets, demonstrating robustness for clinical applications.
