Scholarlink

Background <p>This study explored a machine learning approach using <sup>18</sup>F-FDG PET/CT as a non-invasive alternative to biopsy, incorporating tumor-to-liver ratio (TLR) PET radiomics, and performed survival analysis to improve lymphoma management.</p> Methods <p>In this cohort study, baseline <sup>18</sup>F-FDG PET/CT scans of newly diagnosed, histologically confirmed lymphoma patients were analyzed. Lesions were segmented using 3D Slicer, and radiomic features were extracted and normalized by tumor-to-liver ratios. Patient-level features were used to train three machine learning models (XGBoost, AdaBoost, Logistic Regression) using nested cross-validation with SMOTE for class balancing. A model based on SUV<sub>max</sub> metrics served as baseline. Radiomic features were also evaluated for correlation with 3- and 5-year survival using the Mann-Whitney U test.</p> Results <p>A total of 156 lymphoma patients were analyzed, with 2,076 lesions segmented and 200 radiomic features extracted. For subtype classification, AdaBoost achieved the highest AUC for Diffuse Large B-cell (DLBCL) (0.863, accuracy 0.742), while XGBoost performed best for High-Grade Non-Hodgkin lymphoma (NHL) (AUC 0.825, accuracy 0.735) and Nodular Sclerosis Hodgkin Lymphoma (NS-HL) (AUC 0.827, accuracy 0.832). Logistic regression showed the best results for Classical Hodgkin Lymphoma (C-HL) (AUC 0.849, accuracy 0.775). The SUV<sub>max</sub>-based model (LR-SUV_MAX) consistently underperformed (AUCs: C-HL 0.630, High-Grade NHL 0.700, NS-HL 0.638, DLBCL 0.664), with all differences being statistically significant (<i>p</i> &lt; 0.001). Radiomic and clinical features including SUV-GLSZM small area emphasis (<i>p</i> = 0.0019), age (<i>p</i> = 0.0002), and spleen involvement (<i>p</i> = 0.0014) were significantly associated with 3- and 5-year overall survival in 110 and 74 patients, respectively.</p> Conclusion <p>Radiomic features combined with machine learning significantly improve lymphoma subtype classification over SUV<sub>max</sub> alone and show potential for predicting patient survival.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Enhanced Lymphoma Subtype Classification and Prognosis Using Machine Learning with 18F-FDG PET/CT Radiomics: Beyond SUVmax

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月27日

查看全文
  • Setareh Hasanabadi,
  • Seyed Mahmud Reza Aghamiri,
  • Ahmad Ali Abin,
  • Habibeh Vosoughi,
  • Farshad Emami,
  • Mehrdad Bakhshayesh Karam,
  • Marzieh Nejabat,
  • Abtin Dorudinia,
  • Hossein Arabi,
  • Habib Zaidi

摘要

Background

This study explored a machine learning approach using 18F-FDG PET/CT as a non-invasive alternative to biopsy, incorporating tumor-to-liver ratio (TLR) PET radiomics, and performed survival analysis to improve lymphoma management.

Methods

In this cohort study, baseline 18F-FDG PET/CT scans of newly diagnosed, histologically confirmed lymphoma patients were analyzed. Lesions were segmented using 3D Slicer, and radiomic features were extracted and normalized by tumor-to-liver ratios. Patient-level features were used to train three machine learning models (XGBoost, AdaBoost, Logistic Regression) using nested cross-validation with SMOTE for class balancing. A model based on SUVmax metrics served as baseline. Radiomic features were also evaluated for correlation with 3- and 5-year survival using the Mann-Whitney U test.

Results

A total of 156 lymphoma patients were analyzed, with 2,076 lesions segmented and 200 radiomic features extracted. For subtype classification, AdaBoost achieved the highest AUC for Diffuse Large B-cell (DLBCL) (0.863, accuracy 0.742), while XGBoost performed best for High-Grade Non-Hodgkin lymphoma (NHL) (AUC 0.825, accuracy 0.735) and Nodular Sclerosis Hodgkin Lymphoma (NS-HL) (AUC 0.827, accuracy 0.832). Logistic regression showed the best results for Classical Hodgkin Lymphoma (C-HL) (AUC 0.849, accuracy 0.775). The SUVmax-based model (LR-SUV_MAX) consistently underperformed (AUCs: C-HL 0.630, High-Grade NHL 0.700, NS-HL 0.638, DLBCL 0.664), with all differences being statistically significant (p < 0.001). Radiomic and clinical features including SUV-GLSZM small area emphasis (p = 0.0019), age (p = 0.0002), and spleen involvement (p = 0.0014) were significantly associated with 3- and 5-year overall survival in 110 and 74 patients, respectively.

Conclusion

Radiomic features combined with machine learning significantly improve lymphoma subtype classification over SUVmax alone and show potential for predicting patient survival.