3D医学图像分割需用保守正则化，否则会因2D训练策略迁移而性能下降。
Optimization in Sparse 2D to Dense 3D Weakly Supervised Learning: Application to Multi-Label Segmentation of Large ex vivo MRI Data
- 2D教师模型需强增强与软标签来弥补数据少
- 3D学生模型若用相同策略性能反而下降
- 人眼优化的对比增强会破坏机器学习效果
全监督3D高分辨率离体MRI分割受限于体积标注成本高昂，迫使采用稀疏2D切片。弱监督稀疏到稠密框架可缓解此问题，但关于人机视觉增强与跨维度优化策略迁移仍缺乏指导。本研究分析了高分辨率多发性硬化脊髓MRI多类别分割中不同正则化需求。使用9.4T MRI数据（>104,000切片，仅428个稀疏标注），以2D教师模型在稀疏切片上训练，生成稠密伪标签供3D学生模型学习。系统评估了人机友好预处理、空间增强和软标签正则化对两架构的影响。结果发现：2D教师需强空间增强与软标签，使白质病灶Dice提升超过11点；但将这些技术迁移到3D学生模型会导致性能下降。此外，人机预处理（如CLAHE）破坏全局统计特征，使灰质病灶Dice下降约25点。研究揭示了感知差异（人眼增强损害模型）与跨维度正则化冲突：3D模型在稠密伪标签上训练时，其优化路径与2D模型根本不同，需采用更保守的正则化策略。代码与模型见：https://github.com/ivadomed/model_seg_sc-gm-lesion_human_ms_exvivo_t2star。
原文摘要 · Abstract (English)
INTRODUCTION | Fully supervised 3D segmentation of high-resolution ex vivo MRI is limited by the prohibitive cost of volumetric annotation, forcing reliance on sparse 2D slices. Weakly supervised Sparse-to-Dense frameworks bridge this gap, but guidelines remain ambiguous regarding human-centric visual enhancements and transferring optimization strategies across dimensions. We analyze divergent regularization needs for multi-class segmentation of high-resolution ex vivo spinal cord MRI. METHODS | We used 9.4T MRI of multiple sclerosis spinal cords (>104,000 slices) with sparse annotations (428 slices). A 2D Teacher trained on sparse slices generated dense pseudo-labels to train a 3D Student. We systematically evaluated the impact of human-centric preprocessing, spatial augmentation, and soft-label regularization on both architectures. RESULTS | We identified a critical divergence in training dynamics. The 2D Teacher required strong spatial augmentation and soft-labeling to overcome data scarcity, improving White Matter Lesion Dice scores by >11 points. However, propagating these techniques to the 3D Student degraded its performance. Furthermore, human-centric preprocessing (e.g., CLAHE) disrupted global statistical cues, dropping Gray Matter Lesion Dice scores by ~25 points. DISCUSSION | Our study highlights a perception divergence (human-centric contrast enhancement harms machine models) and a regularization conflict across dimensions. 3D architectures trained on dense pseudo-labels exhibit fundamentally different optimization landscapes than 2D counterparts and require distinct, conservative regularization. Code and models: https://github.com/ivadomed/model_seg_sc-gm-lesion_human_ms_exvivo_t2star.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。