Scholarlink

Objective <p>To assess whether the pCASL technique and its radiomics features can enhance the differentiation between tumor recurrence (TR) and pseudoprogression (PsP) in postoperative glioma patients.</p> Methods <p>A retrospective study of 120 postoperative glioma patients (WHO Grade 2–4) from Tongji Hospital, Wuhan, was conducted. MRI data, including T<sub>1</sub>WI, T<sub>2</sub>WI, T<sub>2</sub>FLAIR, contrast-enhanced T<sub>1</sub>WI, and pCASL, were analyzed. Final diagnoses of TR or PsP were confirmed through pathology or follow-up. Among the patients, 65 had recurrence, and 55 had PsP. Process the pCASL images to generate the CBF parameter map, then perform N4 bias correction and Z- score standardization to obtain the standardized CBF parameter map for group analysis. The lesion areas were outlined, and mean values for ROI were calculated. Statistical analysis included the Mann-Whitney U test and ROC curve analysis. Radiomics features were extracted from the CBF maps. These features were then further selected and divided into training and testing sets. Machine learning models, including Support Vector Machine (SVM), logistic regression, random forest, and Gaussian Naive Bayes, were developed and subsequently validated.</p> Results <p>The Mann-Whitney U test showed a significant difference in mean CBF values between TR and PsP groups (<i>p</i> &lt; 0.001). ROC analysis revealed an AUC of 0.879 (95% CI: 0.817–0.941), sensitivity of 0.846, specificity of 0.836, PPV of 0.859, and NPV of 0.821. After feature selection, seven radiomics features were retained. SVM yielded the best performance with an AUC of 0.971, sensitivity of 0.950, specificity of 0.813, PPV of 0.864, and NPV of 0.929.</p> Conclusion <p>The pCASL technique, combined with radiomics features, effectively differentiates TR from PsP in postoperative glioma patients. The pCASL provides reliable diagnostic information, with radiomics further improving classification accuracy. The SVM model demonstrated the best performance, highlighting the potential of combining pCASL and radiomics for accurate, non-invasive differentiation of TR and PsP. This approach could enhance clinical decision-making and patient management.</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

Differentiating tumor recurrence and pseudoprogression in postoperative gliomas using pseudo-continuous arterial spin labeling (pCASL) technique

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月19日

查看全文
  • Peiquan Liu,
  • Yujie Chen,
  • Xudong Ai,
  • Weiyin Vivian Liu,
  • Hongquan Zhu,
  • Yujie Ding,
  • Dong Liu,
  • Tengfei Chao,
  • Jiaxuan Zhang,
  • Wenzhen Zhu

摘要

Objective

To assess whether the pCASL technique and its radiomics features can enhance the differentiation between tumor recurrence (TR) and pseudoprogression (PsP) in postoperative glioma patients.

Methods

A retrospective study of 120 postoperative glioma patients (WHO Grade 2–4) from Tongji Hospital, Wuhan, was conducted. MRI data, including T1WI, T2WI, T2FLAIR, contrast-enhanced T1WI, and pCASL, were analyzed. Final diagnoses of TR or PsP were confirmed through pathology or follow-up. Among the patients, 65 had recurrence, and 55 had PsP. Process the pCASL images to generate the CBF parameter map, then perform N4 bias correction and Z- score standardization to obtain the standardized CBF parameter map for group analysis. The lesion areas were outlined, and mean values for ROI were calculated. Statistical analysis included the Mann-Whitney U test and ROC curve analysis. Radiomics features were extracted from the CBF maps. These features were then further selected and divided into training and testing sets. Machine learning models, including Support Vector Machine (SVM), logistic regression, random forest, and Gaussian Naive Bayes, were developed and subsequently validated.

Results

The Mann-Whitney U test showed a significant difference in mean CBF values between TR and PsP groups (p < 0.001). ROC analysis revealed an AUC of 0.879 (95% CI: 0.817–0.941), sensitivity of 0.846, specificity of 0.836, PPV of 0.859, and NPV of 0.821. After feature selection, seven radiomics features were retained. SVM yielded the best performance with an AUC of 0.971, sensitivity of 0.950, specificity of 0.813, PPV of 0.864, and NPV of 0.929.

Conclusion

The pCASL technique, combined with radiomics features, effectively differentiates TR from PsP in postoperative glioma patients. The pCASL provides reliable diagnostic information, with radiomics further improving classification accuracy. The SVM model demonstrated the best performance, highlighting the potential of combining pCASL and radiomics for accurate, non-invasive differentiation of TR and PsP. This approach could enhance clinical decision-making and patient management.