CATCH：基于条件哈尔扩散的反事实解剖组织修复
CATCH: Counterfactual Anatomical Tissue Inpainting with Conditional Haar Diffusion
浏览论文内容
中文总结 AI 辅助
CATCH提出条件哈尔扩散模型，在可逆小波域中实现脑MRI掩膜区域的合理无肿瘤组织修复，通过加权混合掩膜策略在BraTS 2026验证集上取得最优性能。
中文摘要 AI 辅助
BraTS局部合成任务将T1加权脑MRI中的掩膜区域替换为合理的无肿瘤组织，同时保留观察到的解剖结构。我们提出CATCH，一种在可逆哈尔小波域中的条件三维扩散模型。其去噪器接收带噪声的目标系数、空洞图像系数和带符号掩膜；肿瘤排除的小波重建和空洞聚焦损失引导训练，硬合成保留观察到的体素。我们比较了固定掩膜、肿瘤成分增强以及由肿瘤衍生、不规则斑块和椭球形掩膜组成的加权混合。在25个开发病例中，五个预指定病例选择每个分支的检查点及其全部25个轨迹聚合；一个独立的75例内部集比较冻结流程，并选择加权混合用于组织者评估。五次轨迹平均在内部获得SSIM/PSNR/MSE（均值±标准差）为0.80±0.13、19.18±1.80dB和0.010±0.005。作为唯一官方评估的流程，加权混合在219例BraTS 2026验证集上获得0.772±0.119、20.89±3.27dB和0.0098±0.0054。与计算匹配的随机增强内部比较，它提高了SSIM 0.019（95%自助法置信区间：0.013-0.025）、PSNR 0.95dB和MSE 0.003；所有三个配对比较在Holm校正后仍显著。结果支持CATCH内完整的加权混合策略；缺乏官方固定和随机流程得分以及直接可比的外部基线限制了更广泛的结论。
英文摘要
BraTS local synthesis replaces masked regions in T1-weighted brain MRI with plausible tumor-free tissue while preserving observed anatomy. We present CATCH, conditional 3D diffusion in an invertible Haar-wavelet domain. Its denoiser receives noisy target coefficients, voided-image coefficients, and a signed mask; tumor-excluded wavelet reconstruction and a hole-focused loss guide training, and hard compositing preserves observed voxels. We compare fixed masks, tumor-component augmentation, and a weighted mixture of tumor-derived, irregular-blob, and ellipsoidal masks. Of 25 development cases, five prespecified cases select each arm's checkpoint and all 25 of their trajectory aggregations; a separate 75-case internal set compares the frozen pipelines and selects a weighted mixture for organizer evaluation. Five-trajectory averaging yielded internal SSIM/PSNR/MSE (mean$\pm$SD) of $0.80\pm0.13$, $19.18\pm1.80$dB, and $0.010\pm0.005$. As the sole officially evaluated pipeline, weighted mixture yielded $0.772\pm0.119$, $20.89\pm3.27$dB, and $0.0098\pm0.0054$ on the 219-case BraTS 2026 validation set. Against compute-matched random augmentation internally, it improved SSIM by 0.019 (95% bootstrap CI: 0.013-0.025), PSNR by 0.95dB, and MSE by 0.003; all three paired comparisons remained significant after Holm correction. Results favor the complete weighted-mixture policy within CATCH; absent official fixed- and random-pipeline scores and a directly comparable external baseline limit broader conclusions.
发表机构
- Pioneer Centre for AI, University of Copenhagen（哥本哈根大学先锋人工智能中心）
机构由 AI 辅助整理，请以论文原文为准。
