CT-based clinical-radiomics model to predict progression and drive clinical applicability in locally advanced head and neck cancer - Takeaways - MDSpire
Coming Soon: Introducing MDSpire News. Learn more
Conexiant’s news site is now MDSpire News. Learn more

Radiomics Model Utilizing CT Imaging to Forecast Disease Progression and Enhance Clinical Relevance in Locally Advanced Head and Neck Cancer

  • By

  • Gema Bruixola

  • Delfina Dualde-Beltrán

  • Ana Jimenez-Pastor

  • Anna Nogué

  • Fuensanta Bellvís

  • Almudena Fuster-Matanzo

  • Clara Alfaro-Cervelló

  • Nuria Grimalt

  • Nader Salhab-Ibáñez

  • Vicente Escorihuela

  • María Eugenia Iglesias

  • María Maroñas

  • Ángel Alberich-Bayarri

  • Andrés Cervantes

  • Noelia Tarazona

  • December 20, 2024

Share

  • 1

    Head and neck squamous cell carcinoma (HNSCC) is the seventh most prevalent cancer globally, with significant risk factors including tobacco and HPV infection.

  • 2

    Over 60% of HNSCC cases are locally advanced, and standard treatment involves high-dose cisplatin with concurrent radiotherapy.

  • 3

    Current prognostic models for HNSCC, including the TNM8 staging system, are suboptimal and lack external validation for clinical use.

  • 4

    A CT-based radiomics model integrating clinical and biological data aims to improve progression-free survival predictions in locally advanced HNSCC.

  • 5

    The Shapley additive explanations (SHAP) method enhances model interpretability by assigning values to features based on their influence on predictions.

Original Source(s)

CT-based clinical-radiomics model to predict progression and drive clinical applicability in locally advanced head and neck cancer

  • by Gema Bruixola, Delfina Dualde-Beltrán, Ana Jimenez-Pastor, Anna Nogué, Fuensanta Bellvís, Almudena Fuster-Matanzo, Clara Alfaro-Cervelló, Nuria Grimalt, Nader Salhab-Ibáñez, Vicente Escorihuela, María Eugenia Iglesias, María Maroñas, Ángel Alberich-Bayarri, Andrés Cervantes, Noelia Tarazona

  • December 20, 2024

Related Content

Deep learning-based malignancy probability estimation of pulmonary nodules in PET/CT imaging

Calibrated ensemble deep learning for four-class lung CT image classification and uncertainty-based referral

A Multi-Model, Pixel-Native Framework for Automated Computed Tomography Series Labeling and Characterization: Proof-of-Concept Study