自适应后处理驱动卒中病灶分割中的实例级检测

中文摘要 AI 辅助

除了更标准的体素级重叠度外，实例级病灶检测已成为医学图像分割中日益重要的焦点。不过，大多数流程的训练和后处理仅针对体素重叠度优化。这种不匹配在小病灶上最为明显，其中接近命中的预测（即存在大量重叠但仅差一点达到实例匹配阈值）与完全未命中的得分相同。在我们的ISLES'26参赛方案中，我们发现缩小这一差距在后处理中比在架构设计中重要得多。我们的体积条件自适应后处理（VCAP）方案会根据每个病例预测的病灶负荷调整组分大小阈值，使病灶F1得分提高了0.032（无偏交叉折估计）——约为我们测试的任何架构改进效果的6倍。专为小病灶分割设计的感知分辨率注意力架构Viola2Plus表明了这种区分的重要性：它使小病灶Dice得分保持不变，但小病灶检测率提高了3.7%，这是仅靠体素重叠度指标会遗漏的真实效果。在包含1453个病例的训练集上进行5折交叉验证后，我们经后处理的双架构集成模型取得了Dice得分0.651、病灶F1得分0.614，而未后处理的单模型基线的对应得分分别为0.644和0.573。

英文摘要

Instance-level lesion detection has been an increasingly larger focal point in medical image segmentation besides the more standard voxel-level overlap. Still, most pipelines are trained and post-processed for voxel overlap alone. In particular, the mismatch is most pronounced for small lesions, where a near-miss prediction---substantial overlap that falls just short of the instance-matching threshold---scores the same as a complete miss. In our ISLES'26 submission, we found that closing this gap mattered far more in post-processing than in architecture design. Our Volume-Conditioned Adaptive Post-Processing (VCAP) scheme adjusts component-size thresholds to each case's predicted lesion burden, improving Lesion-F1 by 0.032 (unbiased cross-fold estimate)---approximately 6 times larger than any architectural change we tested. A resolution-aware attention architecture (Viola2Plus), designed for small-lesion segmentation, shows why the distinction matters: it left small-lesion Dice unchanged but raised small-lesion detection rate by 3.7\%, a real effect voxel-overlap metrics alone would have missed. Under 5-fold cross-validation on the 1,453-case training set, our post-processed two-architecture ensemble achieves Dice 0.651 and Lesion-F1 0.614, versus 0.644 and 0.573 for the unprocessed single-model baseline.

发表机构

• Oslo University Hospital（奥斯陆大学医院）

机构由 AI 辅助整理，请以论文原文为准。

补充信息

备注

8 papges, 4 figs, 2 tables, MICCAI ISLES'26