Scholarlink

Objective <p>Gliomas are heterogeneous brain tumors with variable biology and treatment response. Accurate, non-invasive assessment of tumor aggressiveness is essential for prognosis and treatment planning. Conventional machine learning (ML) approaches typically frame glioma grading as a discrete classification task, which may overlook substantial intra-grade heterogeneity. This pilot study explores a regression-based framework to derive a continuous imaging-derived severity score, providing a relative assessment of tumor aggressiveness anchored to, but not redefining, established WHO grades.</p> Materials and methods <p>36 glioma patients (low-grade glioma; LGG: 58.33%, high-grade glioma; HGG: 41.67%) underwent 3D T1-weighted and DTI MRI on a 1.5&#xa0;T scanner. Diffusivity maps were derived from DTI, and radiomic features were extracted. Sequential Feature Selection with a Random Forest regressor identified the most informative features. Fifteen ML regression models estimated the relative severity score, evaluated using MSE, MAE, and <i>R</i><sup>2</sup>, with fivefold nested cross-validation repeated 10 times. Model interpretability was examined using SHAP analysis.</p> Results <p>The random forest model yielded the best performance (MSE = 0.066 ± 0.044, MAE = 0.182 ± 0.069, <i>R</i><sup>2</sup> = 0.307 ± 0.432). T1-weighted features predominated, while DTI-derived measures, notably the robust mean absolute deviation of axial diffusivity, enhanced performance.</p> Conclusion <p>Regression-based modeling of radiomic features from T1-weighted and diffusion MRI enables the estimation of a relative, imaging-derived glioma severity score that captures intra-grade heterogeneity beyond categorical classification. While this model provides a continuous scale of radiological severity, it is intended as a complementary tool for assessing intra-grade heterogeneity and is not a replacement for the definitive WHO 2021 clinical grading.</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

Beyond binary classification: a pilot study of imaging-derived glioma severity modeling using T1-weighted and diffusion MRI radiomics

  • 期刊论文

  • 发表日期：

    2026年4月28日

查看全文
  • Pamela Franco,
  • Cristian Montalba,
  • Raúl Caulier-Cisterna,
  • Ignacio Espinoza,
  • MDaniela Cornejo,
  • Francisco Torres,
  • Carlos Bennett,
  • Steren Chabert,
  • Rodrigo Salas

摘要

Objective

Gliomas are heterogeneous brain tumors with variable biology and treatment response. Accurate, non-invasive assessment of tumor aggressiveness is essential for prognosis and treatment planning. Conventional machine learning (ML) approaches typically frame glioma grading as a discrete classification task, which may overlook substantial intra-grade heterogeneity. This pilot study explores a regression-based framework to derive a continuous imaging-derived severity score, providing a relative assessment of tumor aggressiveness anchored to, but not redefining, established WHO grades.

Materials and methods

36 glioma patients (low-grade glioma; LGG: 58.33%, high-grade glioma; HGG: 41.67%) underwent 3D T1-weighted and DTI MRI on a 1.5 T scanner. Diffusivity maps were derived from DTI, and radiomic features were extracted. Sequential Feature Selection with a Random Forest regressor identified the most informative features. Fifteen ML regression models estimated the relative severity score, evaluated using MSE, MAE, and R2, with fivefold nested cross-validation repeated 10 times. Model interpretability was examined using SHAP analysis.

Results

The random forest model yielded the best performance (MSE = 0.066 ± 0.044, MAE = 0.182 ± 0.069, R2 = 0.307 ± 0.432). T1-weighted features predominated, while DTI-derived measures, notably the robust mean absolute deviation of axial diffusivity, enhanced performance.

Conclusion

Regression-based modeling of radiomic features from T1-weighted and diffusion MRI enables the estimation of a relative, imaging-derived glioma severity score that captures intra-grade heterogeneity beyond categorical classification. While this model provides a continuous scale of radiological severity, it is intended as a complementary tool for assessing intra-grade heterogeneity and is not a replacement for the definitive WHO 2021 clinical grading.