Diffusion-Based Tumor Inpainting for Renal Segmentation under Clinical Data Scarcity

2026-09-18

AI Summary

为解决临床数据稀缺问题，提出基于扩散的肿瘤填充框架合成CT图像中的肾肿瘤，并对比2D、2.5D和3D合成策略，发现2.5D方法在保持精度的同时显著降低假阳性。

Abstract

Deep learning segmentation of renal tumors requires large annotated datasets, yet clinical deployments typically offer only a handful of tumor-positive cases from the target site. We propose a diffusion-based inpainting framework that synthesizes anatomically plausible renal tumors within healthy CT scans, requiring no additional annotation, and provide the first systematic comparison of 2D, 2.5D, and full 3D (MAISI) synthesis strategies for this task. Training the diffusion model on public data (KiTS23, KIRC) and evaluating nnU-Net segmentation on a internal cohort across three low-data regimes, we find that 2.5D and 3D augmentation substantially reduce false positives (from $\sim$18--20\% to $\sim$3--6\%) while maintaining Dice, whereas 2D provides no consistent benefit. Crucially, the proposed 2.5D method matches full 3D synthesis on every metric at substantially lower computational cost, indicating that local volumetric consistency alone is sufficient for effective augmentation in data- and resource-scarce clinical settings.

Problem

• renal tumor segmentation
• clinical data scarcity
• deep learning

Innovation

• diffusion-based inpainting
• data augmentation
• 2.5D synthesis
• false positives reduction
• computational cost