发表机构
Brightskies（Brightskies）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出基于涂鸦条件残差编码U-Net的交互式多示踪剂PET/CT病灶分割方案，经五折交叉验证，交互修正可大幅提升分割性能，缩小模型间差异。
AI 中文摘要
全身PET/CT中的自动病灶分割因生理示踪剂摄取模式的多样性及不同示踪剂下病灶外观的差异而变得复杂。autoPET/CT V挑战赛通过将分割任务交互化来解决这一问题：图像旁会提供标记前景和背景的用户涂鸦，算法需利用这些涂鸦信息。本文介绍我们的参赛方案，即一种基于涂鸦条件的残差编码U-Net，它以四个输入通道运行：CT、PET，以及分别对应前景和背景的稀疏涂鸦图。该网络从autoPET-III的获胜权重初始化，并将输入通道从2个扩展至4个，其中两个涂鸦通道采用零初始化，以确保预训练表示在初始化时被精确保留。每个模型均从对应autoPET-III折的检查点按折进行微调，因此预训练过程中不会看到验证集样本。PET强度根据从CT分割得到的每例扫描主动脉血池参考进行归一化，这消除了示踪剂和中心特有的缩放问题，且无需病灶标签。推理时，通过按滑动窗口补丁对五个折模型的softmax输出取平均，再经高斯加权拼接来集成这些模型。在挑战赛的五折划分中，每折在其自身验证集上评估，无涂鸦时平均Dice系数为0.554，平均病灶级F1值为0.528；经过五次修正轮次后，这两个指标分别升至0.751和0.733。约85%的增益来自第一次涂鸦，且各折模型间的差距在相同轮次内缩小了五倍，因此交互在很大程度上弥补了给定模型自动分割效果的优劣差异。
英文摘要
Automated lesion segmentation in whole-body PET/CT is complicated by the variety of physiological tracer uptake patterns and by the differing appearance of lesions across tracers. The autoPET/CT V challenge addresses this by making segmentation interactive: user scribbles marking foreground and background are supplied alongside the image, and the algorithm is expected to exploit them. We present our submission, a scribble-conditioned residual encoder U-Net operating on four input channels: CT, PET, and a sparse scribble map for each of foreground and background. The network is initialised from the autoPET-III winning weights and extended from two to four input channels, with the two scribble channels zero-initialised so that the pretrained representation is preserved exactly at initialisation. Every model is fine-tuned per fold from the corresponding autoPET-III fold checkpoint, so that no validation case is seen during pretraining. PET intensities are normalised against a per-scan aorta blood-pool reference derived from a CT segmentation, which removes tracer- and centre-specific scaling without requiring lesion labels. At inference the five fold models are ensembled by averaging their softmax outputs per sliding-window patch, before Gaussian-weighted stitching. On the challenge's five-fold split, with each fold evaluated on its own validation cases, mean Dice is 0.554 and mean lesion-level F1 is 0.528 without scribbles, rising to 0.751 and 0.733 after five correction rounds. About 85% of that gain follows the first scribble, and the spread between fold models narrows five-fold over the same rounds, so interaction largely compensates for how well or badly a given model segments unaided.
