Scholarlink

Objectives <p>To assess the impact of image post-processing steps on the generalisability of MRI-based radiogenomic models. Using a human papillomavirus (HPV) status in oropharyngeal squamous cell carcinoma (OPSCC) prediction model, this study examines the potential of different post-processing strategies to increase its generalisability across data from different centres and image acquisition protocols.</p> Materials and methods <p>Contrast-enhanced T1-weighted MR images of OPSCC patients of two cohorts from different centres, with confirmed HPV status, were manually segmented. After radiomic feature extraction, the HPV prediction model trained on a training set with 91 patients was subsequently tested on two independent cohorts: a test set with 62 patients and an externally derived cohort of 157 patients. The data processing options included: data harmonisation, a process to ensure consistency in data from different centres; exclusion of unstable features across different segmentations and scan protocols; and removal of highly correlated features to reduce redundancy.</p> Results <p>The predictive model, trained without post-processing, showed high performance on the test set, with an AUC of 0.79 (95% CI: 0.66–0.90, <i>p</i> &lt; 0.001). However, when tested on the external data, the model performed less well, resulting in an AUC of 0.52 (95% CI: 0.45–0.58, <i>p</i> = 0.334). The model’s generalisability substantially improved after performing post-processing steps. The AUC for the test set reached 0.76 (95% CI: 0.63–0.87, <i>p</i> &lt; 0.001), while for the external cohort, the predictive model achieved an AUC of 0.73 (95% CI: 0.64–0.81, <i>p</i> &lt; 0.001).</p> Conclusions <p>When applied before model development, post-processing steps can enhance the robustness and generalisability of predictive radiogenomics models.</p> Key Points <p><Emphasis Type="BoldItalic">Question</Emphasis> <i>How do post-processing steps impact the generalisability of MRI-based radiogenomic prediction models?</i></p> <p><Emphasis Type="BoldItalic">Findings</Emphasis> <i>Applying post-processing steps, i.e., data harmonisation, identification of stable radiomic features, and removal of correlated features, before model development can improve model robustness and generalisability.</i></p> <p><Emphasis Type="BoldItalic">Clinical relevance</Emphasis> <i>Post-processing steps in MRI radiogenomic model generation lead to reliable non-invasive diagnostic tools for personalised cancer treatment strategies.</i></p> Graphical Abstract <p></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

Post-processing steps improve generalisability and robustness of an MRI-based radiogenomic model for human papillomavirus status prediction in oropharyngeal cancer

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年6月6日

查看全文
  • Milad Ahmadian,
  • Zuhir Bodalal,
  • Paula Bos,
  • Roland M. Martens,
  • Georgios Agrotis,
  • Hedda J. van der Hulst,
  • Conchita Vens,
  • Luc Karssemakers,
  • Abrahim Al-Mamgani,
  • Pim de Graaf,
  • Bas Jasperse,
  • Ruud H. Brakenhoff,
  • C. René Leemans,
  • Regina G. H. Beets-Tan,
  • Jonas A. Castelijns,
  • Michiel W. M. van den Brekel

摘要

Objectives

To assess the impact of image post-processing steps on the generalisability of MRI-based radiogenomic models. Using a human papillomavirus (HPV) status in oropharyngeal squamous cell carcinoma (OPSCC) prediction model, this study examines the potential of different post-processing strategies to increase its generalisability across data from different centres and image acquisition protocols.

Materials and methods

Contrast-enhanced T1-weighted MR images of OPSCC patients of two cohorts from different centres, with confirmed HPV status, were manually segmented. After radiomic feature extraction, the HPV prediction model trained on a training set with 91 patients was subsequently tested on two independent cohorts: a test set with 62 patients and an externally derived cohort of 157 patients. The data processing options included: data harmonisation, a process to ensure consistency in data from different centres; exclusion of unstable features across different segmentations and scan protocols; and removal of highly correlated features to reduce redundancy.

Results

The predictive model, trained without post-processing, showed high performance on the test set, with an AUC of 0.79 (95% CI: 0.66–0.90, p < 0.001). However, when tested on the external data, the model performed less well, resulting in an AUC of 0.52 (95% CI: 0.45–0.58, p = 0.334). The model’s generalisability substantially improved after performing post-processing steps. The AUC for the test set reached 0.76 (95% CI: 0.63–0.87, p < 0.001), while for the external cohort, the predictive model achieved an AUC of 0.73 (95% CI: 0.64–0.81, p < 0.001).

Conclusions

When applied before model development, post-processing steps can enhance the robustness and generalisability of predictive radiogenomics models.

Key Points

Question How do post-processing steps impact the generalisability of MRI-based radiogenomic prediction models?

Findings Applying post-processing steps, i.e., data harmonisation, identification of stable radiomic features, and removal of correlated features, before model development can improve model robustness and generalisability.

Clinical relevance Post-processing steps in MRI radiogenomic model generation lead to reliable non-invasive diagnostic tools for personalised cancer treatment strategies.

Graphical Abstract