文献速递肿瘤 PET/CT

基于PET/CT影像与深度学习模型的高代谢肺部病灶检测与诊断

Hypermetabolic pulmonary lesions detection and diagnosis based on PET/CT imaging and deep learning models.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2025-04-04

本研究开发并评估深度学习模型,用于检测高代谢肺部病灶并将其分类为良性、肺癌、肺淋巴瘤和转移四类。研究回顾性纳入5家中心647例病例,内部数据集426例,外部测试集I 151例,外部测试集II 70例;定位模型检出率分别为81.19%、75.48%、77.59%,分类模型曲线下面积分别为88.4%、80.7%、66.6%,表现优于影像组学方法。

要点

  • 定位模型在内部数据集、外部测试集I和外部测试集II的检出率分别为81.19%、75.48%、77.59%。
  • 分类模型曲线下面积分别为88.4%、80.7%、66.6%,优于影像组学方法。
  • 多数假阳性分割在临床上可接受,对应邻近区域可疑病灶,尤其是淋巴结。

核心结论

  • 基于PET/CT影像的深度学习模型可有效检测、分割和分类高代谢肺部病灶,并识别邻近可疑病灶。
  • 结果凸显人工智能在临床决策和肺部疾病诊断中的潜力。

研究设计与样本

  • 回顾性纳入5家中心647例病例(男409例/女238例),时间跨度超过8年。
  • 内部数据集426例来自上海瑞金医院,外部测试集I 151例来自另外4家机构,外部测试集II 70例来自新成像设备。
  • 先使用手动标注的PET/CT图像开发病灶定位模型;分类采用多维联合网络,结合图像块和二维投影。
  • 分类性能以准确率等指标量化,并与影像组学模型比较。
  • 对假阳性分割进行人工复核和临床评估分析。

主要发现

  • 定位模型在内部数据集、外部测试集I和外部测试集II的检出率分别为81.19%、75.48%、77.59%。
  • 分类模型在内部数据集、外部测试集I和外部测试集II的曲线下面积分别为88.4%、80.7%、66.6%,优于影像组学方法。
  • 多数假阳性分割在临床上可接受,对应邻近区域可疑病灶,尤其是淋巴结。

关键数值与推荐

  • 分类类别为四类:良性、肺癌、肺淋巴瘤和转移,依据病理起源、临床相关性和治疗意义定义。
  • 定位模型检出率在内部数据集为81.19%,外部测试集I为75.48%,外部测试集II为77.59%。
  • 分类模型曲线下面积在内部数据集为88.4%,外部测试集I为80.7%,外部测试集II为66.6%。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

PURPOSE: This study aims to develop and evaluate deep learning models for the detection and classification of hypermetabolic lung lesions into four categories: benign, lung cancer, pulmonary lymphoma, and metastasis. These categories are defined by their pathological origin, clinical relevance, and therapeutic implications. METHODS: A lesion localisation model was first developed using manually annotated PET/CT images. For classification, a multi-dimensional joint network was employed, incorporating both image patches and two-dimensional projections. Classification performance was quantified by metrics like accuracy, and compared to that of a radiomics model. Additionally, false-positive segmentations were manually reviewed and analysed for clinical evaluation. RESULTS: The study retrospectively included 647 cases (409 males/238 females) over more than 8 years from five centres, divided into an internal dataset (426 cases from Shanghai Ruijin Hospital), an external test set I (151 cases from four other institutions), and an external test set II (70 cases from a new imaging device). The localisation model achieved detection rates of 81.19%, 75.48%, and 77.59% on the internal, external test set I, and external test set II, respectively. The classification model outperformed the radiomics approach, with area-under-curves of 88.4%, 80.7%, and 66.6%, respectively. Most false-positive segmentations were clinically acceptable, corresponding to suspicious lesions in adjacent regions, particularly lymph nodes. CONCLUSION: Deep learning models based on PET/CT imaging can effectively detect, segment, and classify hypermetabolic lung lesions, and identify suspicious adjacent lesions. These results highlight the potential of artificial intelligence in clinical decision-making and lung disease diagnosis.

来源:Eur J Nucl Med Mol Imaging,查看原文。版权归原作者所有。

引用

  1. Hu J, Cheng R, Quan M, et al. Hypermetabolic pulmonary lesions detection and diagnosis based on PET/CT imaging and deep learning models. Eur J Nucl Med Mol Imaging. 2025. PMID: 40183951. doi:10.1007/s00259-025-07215-0

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。