全身PET/CT中具有解剖学意识的淋巴瘤病变检测

摘要(中文译文)

早期癌症检测对于改善患者预后至关重要，18F-FDG PET/CT显像通过结合代谢与解剖信息发挥着核心作用。然而，由于存在大小和位置各异的多个病灶，准确的病灶检测仍具有挑战性。本研究探讨引入解剖先验信息能否提升基于深度学习的病灶检测性能。解剖先验的引入方式为：将TotalSegmentator生成的器官分割掩膜作为辅助输入通道，添加至两种病灶检测框架中——基于CNN的nnDetection和基于Transformer的Swin UNETR（在MONAI中实现）。Swin Transformer采用两阶段策略训练，先在autoPET数据集上进行自监督预训练，再在独立的Karolinska淋巴瘤数据集上对检测器模型进行监督微调。模型评估采用单次留出划分，性能以FROC和平均精度指标进行评估。实验在两个独立的PET/CT数据集上进行，涵盖不同的示踪剂和癌症亚型。autoPET数据集包括淋巴瘤、黑色素瘤和肺癌的18F-FDG PET/CT扫描，而Karolinska数据集则聚焦于淋巴瘤显像。在nnDetection框架内，引入解剖先验在两个数据集上均持续改善了病灶检测性能。具体而言，加入解剖掩膜的nnDetection在mAP@0.1-0.5上从0.288提升至0.335。相比之下，解剖先验对Swin Transformer的影响极小，后者未表现出相对于基于CNN的编码器的明显优势。解剖感知先验可显著增强基于CNN模型的病灶检测性能，凸显了显式解剖上下文对多病灶PET/CT分析的重要性。然而，这些获益并不能轻易迁移至基于Transformer的架构，表明需要改进策略以将解剖信息整合到视觉Transformer中用于医学图像分析。

Abstract

Early cancer detection is essential for improving patient outcomes, and 18F-FDG PET/CT imaging plays a central role by combining metabolic and anatomical information. However, accurate lesion detection remains challenging due to the presence of multiple lesions with varying sizes and locations. This study investigates whether incorporating anatomical prior information can improve deep learning-based lesion detection performance. Anatomical priors were incorporated by adding organ segmentation masks generated with TotalSegmentator as auxiliary input channels to two lesion detection frameworks: the CNN-based nnDetection and a transformer-based Swin UNETR implemented in MONAI. The Swin Transformer was trained using a two-stage strategy, with self-supervised pretraining performed on the autoPET dataset and supervised fine-tuning of the detector model conducted on the independent Karolinska lymphoma dataset. Model evaluation followed a single hold-out split, and performance was assessed using FROC and average precision metrics. Experiments were conducted on two independent PET/CT datasets covering different tracers and cancer subtypes. The autoPET dataset includes 18F-FDG PET/CT scans of lymphoma, melanoma, and lung cancer, while the Karolinska dataset focuses on lymphoma imaging. Incorporating anatomical priors consistently improved lesion detection performance within the nnDetection framework across both datasets. Specifically, nnDetection augmented with anatomical masks improved in mAP@0.1-0.5 from 0.288 to 0.335. In contrast, anatomical priors had minimal impact on the Swin Transformer, which did not demonstrate clear advantages over CNN-based encoders. Anatomy-aware priors substantially enhance lesion detection performance in CNN-based models, highlighting the importance of explicit anatomical context for multi-lesion PET/CT analysis. However, these benefits do not readily transfer to transformer-based architectures, indicating the need for improved strategies to integrate anatomical information into vision transformers for medical image analysis.

如何引用

Frontiers in oncology 的其他文献

• 大剂量化疗联合造血干细胞移植治疗晚期神经母细胞瘤的疗效
• 慢性心理社会压力：在乳腺癌症病因中的作用？
• 用类器官模拟胶质瘤：为转化神经肿瘤学重建人类神经微环境
• 结直肠癌发生的综合观点：分子发病机制、基因组改变、诊断范式、治疗干预和精准肿瘤学中的人工智能驱动方向
• 单孔腹腔镜在妇科恶性肿瘤腹膜后淋巴结切除术中的应用及研究进展
• 综合全身免疫炎症指数和预后营养指数的化疗前列线图的开发和验证，以预测结直肠癌癌症的严重佐剂毒性
• 雄激素受体表达在ER阳性/HER2阴性乳腺癌症中的预后价值：来自当代中国队列的证据
• ESCC术后患者5年生存预测模型的构建与验证
• 一种新的液-液cfDNA提取方法，用于大肠癌癌症患者样本的靶向测序：一项中试研究
• 瘤内和瘤周放射组学用于预测乳腺癌症对比增强乳房X光检查中的可疑HER2状态