发表机构
Memorial Sloan Kettering Cancer Center（纪念斯隆-凯特琳癌症中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出参数高效的SWIFT系列模型，通过四种配置实现直肠癌分割，在247例测试集上验证性能，明确检测-边界一致性、效率-校准等权衡，为临床部署提供方案。
AI 中文摘要
从磁共振成像（MRI）中准确分割直肠癌对自适应放疗和肿瘤反应评估至关重要，但部署还需计算效率及信息丰富、校准良好的不确定性估计。因此，我们提出SWIFT——一种具备参数高效性和肿瘤感知微调的Swin预训练模型，用于直肠癌分割。采用类似DINOv2的目标函数在10444个公开3D CT体积上预训练的Swin V2编码器，通过四种累积配置适配T2加权MRI：全微调（SWIFT）、解码器压缩（SWIFTe）、低秩适配（SWIFTe-LoRA）及四成员LoRA解码器集成（SWIFTe-LDE4）。在来自同一机构队列的247例保留测试集上评估几何精度、肿瘤检测、放射组学一致性及概率校准，该测试集采用1.5或3特斯拉GE扫描仪采集。与SWIFT相比，SWIFTe总参数减少70.1%（从72.8M降至21.8M），肿瘤检测率从89.9%升至93.9%，同时达到略低的中位表面DSC（0.61 vs 0.62）及更优的放射组学一致性。在另一项SWIFTe消融实验中，移除肿瘤感知增强使检测率从93.9%降至89.9%，但表面DSC从0.61升至0.64，证明存在检测-边界一致性权衡。SWIFTe-LoRA使用SWIFTe可训练参数的14.6%，同时保留相似分割性能。SWIFTe-LDE4在温度缩放后四种配置中实现最低校准误差（预期校准误差0.217，Brier分数0.222），尽管绝对预期校准误差表明存在残留校准偏差。使用公开VoCo检查点观察到相似的效率-校准模式，支持其在不同预训练初始化间的鲁棒性，而非外部临床泛化性。
英文摘要
Accurate rectal cancer segmentation from magnetic resonance imaging (MRI) is essential for adaptive radiotherapy and tumor response assessment, but deployment also requires computational efficiency and informative, calibrated uncertainty estimates. We therefore introduce SWIFT, a SWin pretrained model wIth parameter-eFficient and Tumor-aware fine-tuning for rectal cancer segmentation. A Swin V2 encoder pretrained on 10,444 public 3D CT volumes using a DINOv2-style objective was adapted to T2-weighted MRI through four cumulative configurations: full fine-tuning (SWIFT), decoder compression (SWIFTe), low-rank adaptation (SWIFTe-LoRA), and a four-member LoRA-decoder ensemble (SWIFTe-LDE4). Geometric accuracy, tumor detection, radiomic agreement, and probability calibration were evaluated on a held-out 247-case test set from a single-institution cohort acquired using 1.5 or 3 Tesla GE scanners. Compared with SWIFT, SWIFTe reduced total parameters by 70.1% (from 72.8M to 21.8M) and increased tumor detection rate from 89.9% to 93.9%, while achieving a slightly lower median surface DSC (0.61 versus 0.62) and improved radiomic agreement. In a separate SWIFTe ablation, removing tumor-aware augmentation reduced detection from 93.9% to 89.9% but increased surface DSC from 0.61 to 0.64, demonstrating a detection-boundary-agreement trade-off. SWIFTe-LoRA used 14.6% of SWIFTe's trainable parameters while retaining similar segmentation performance. SWIFTe-LDE4 achieved the lowest calibration errors among the four configurations after temperature scaling (expected calibration error, 0.217; Brier score, 0.222), although the absolute expected calibration error indicates residual miscalibration. Similar efficiency-calibration patterns were observed using the public VoCo checkpoint, supporting robustness across pretrained initializations rather than external clinical generalizability.
CommentsAccepted to the Medical Image AI in Radiation Therapy (MIART) Workshop at MICCAI 2026
