Dose-Volume Histogram Parameters for 108 Head and Neck Cancer Patients

Multimodal data from 108 patients were collected for a study on predicting radiation-induced oral mucositis. The dataset, authored by Ling Li and last updated in April 2026, includes CT imaging, dose distribution, and clinical features. It is stored in an XLSX file with a size of 53.9 KB.

Use Cases

• Comparing traditional ML and deep learning model performance for multi-class prediction based on multimodal clinical data.
• Training models to predict radiation-induced oral mucositis grades based on dose-volume histogram parameters.
• Analyzing the susceptibility of high-dimensional 3D-CNN architectures to overfitting in small-cohort settings.
• Evaluating the effectiveness of ensemble learning algorithms like Extra Trees for small-cohort radiomics analysis.

Strengths

• Data from 108 patients provides a basis for small-cohort analysis.
• Multimodal data includes CT imaging, dose distribution, and clinical features.
• Model performance was evaluated using a robust stratified 5-fold cross-validation framework.

Limitations

• Row count and specific column definitions are unknown, limiting suitability assessment.
• The dataset is small at 53.9 KB, indicating limited scope.
• Column-level documentation is absent; field semantics must be inferred after download.

Provenance

Source

figshare

Collection Method

Collected as part of a study to evaluate predictive models for radiation-induced oral mucositis.

Time Range

null

Freshness

Last updated 2026-04-09 17:29:00

Geography

null