文献速递甲状腺核医学肿瘤 PET/CT

视野缩放与分割批次对甲状腺闪烁显像影像组学特征可重复性及机器学习性能的影响

Impact of Field-of-view Zooming and Segmentation Batches on Radiomics Features Reproducibility and Machine Learning Performance in Thyroid Scintigraphy.
PubMed 文献 · Clin Nucl Med · 2025-06-17

该回顾性研究基于3个中心872例甲状腺闪烁显像病例,评估视野缩放与分割对影像组学特征可重复性的影响,并比较4种机器学习训练场景。视野缩放显著降低特征可重复性(ICC≥0.80者仅49%),分割影响较小(ICC≥0.80者96%);使用互稳健特征训练的模型优于使用全部特征。

要点

  • 视野缩放显著降低影像组学特征可重复性,ICC≥0.80的特征仅占49%。
  • 分割对特征可重复性影响较小,ICC≥0.80的特征占96%。
  • 使用互稳健特征训练的模型优于使用全部特征,Boruta-MLP在缩放数据集准确率最高(0.71,P<0.001 vs 全部特征)。

核心结论

  • 利用稳健影像组学特征可显著提升机器学习模型在甲状腺疾病分类中的性能,在不同数据集间获得更准确且可泛化的诊断结果。

研究设计与样本

  • 回顾性分析3个中心共872例甲状腺闪烁显像病例。
  • 以组内相关系数(ICC)评估影像组学特征可重复性,在分割与缩放条件下识别稳健特征(ICC≥0.80)。
  • 在中心A数据上实施4种机器学习训练场景:全部特征、缩放稳健特征、分割稳健特征、互稳健特征,采用3种特征选择方法与7种分类器,并在中心B和C的外部数据集上验证。

主要发现

  • 视野缩放显著降低特征可重复性(ICC≥0.80:49%),分割影响较小(ICC≥0.80:96%)。
  • 使用互稳健特征训练的模型优于使用全部特征训练的模型。
  • Boruta-MLP在缩放数据集中准确率最高(0.71,P<0.001 vs 全部特征)。
  • RFE-MLP在基线数据集中表现最佳(0.69,P<0.001 vs 全部特征),灰度共生矩阵(GLCM)特征被频繁选择。

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

BACKGROUND: Thyroid diseases are the second most common hormonal disorders, necessitating accurate diagnostics. Advances in artificial intelligence and radiomics have enhanced diagnostic precision by analyzing quantitative imaging features. However, reproducibility challenges arising from factors such as the field-of-view (FOV) zooming and segmentation variability limit the clinical application of radiomic-based models. AIM: This study focuses on evaluating the impact of segmentation and FOV zooming on the reproducibility of radiomic features and improved performance of machine learning (ML) when using reproducible features for classification of thyroid scintigraphy images into normal, diffuse goiter (DG), multinodular goiter (MNG), and thyroiditis. PATIENTS AND METHODS: A retrospective analysis was conducted on 872 thyroid scintigraphy cases from 3 centers. Radiomic feature reproducibility was assessed using the intraclass correlation coefficient (ICC), with robust features (ICC≥0.80) identified under segmentation and zooming conditions. Four ML training scenarios were implemented to train models on Center A data, including (1) all, (2) zoom-robust, (3) segmentation-robust, and (4) mutually robust features, with 3 feature selection methods and 7 classifiers. Models were validated on external data sets (centers B and C). RESULTS: FOV zooming significantly reduced feature reproducibility (ICC≥0.80: 49%), while segmentation effects were minimal (ICC≥0.80: 96%). Models trained on mutually robust features outperformed those trained using all features. Boruta-MLP achieved the highest accuracy (0.71, P -value <0.001 vs. all features) in zoomed data sets, and RFE-MLP performed best (0.69, P -value <0.001 vs. all features) in the baseline data set, with Gray-Level Co-occurrence Matrix (GLCM) features frequently selected. CONCLUSIONS: Utilizing robust radiomic features significantly improved the performance of ML models in thyroid disease classification, enabling more accurate and generalizable diagnostic outcomes across diverse data sets.

来源:Clin Nucl Med,查看原文。版权归原作者所有。

引用

  1. Bagheri S, Hajianfar G, Sabouri M, et al. Impact of Field-of-view Zooming and Segmentation Batches on Radiomics Features Reproducibility and Machine Learning Performance in Thyroid Scintigraphy. Clin Nucl Med. 2025. PMID: 40524366. doi:10.1097/RLU.0000000000005995

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。