MRI Radiomics and Clinical Data for 290 Locally Advanced Rectal Cancer Patients

290 patient records from a multicenter retrospective study on locally advanced rectal cancer (LARC). The data includes MRI-derived radiomic features from intratumoral and peritumoral regions, habitat heterogeneity metrics, and clinical variables used to build a predictive nomogram. The dataset was uploaded by Liang Zhang to figshare in April 2026 under a CC-BY-4.0 license.

Use Cases

• Training machine learning classifiers for cancer risk prediction based on MRI radiomic features.
• Developing integrated nomograms for clinical decision support by combining imaging and clinical data.
• Analyzing tumor microenvironment heterogeneity using habitat clustering derived from radiomic features.
• Comparing model performance (e.g., logistic regression vs. SVM) for medical imaging classification tasks.

Strengths

• Data originates from a multicenter study involving 290 patients, which may improve generalizability.
• Model performance metrics are provided, including an AUC of 0.928 in the training cohort and 0.817 in the test cohort.
• The methodology is detailed, specifying the use of LASSO regression for feature selection and 3D Slicer for region delineation.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small at 18.2 KB, indicating limited scope, likely containing summary or model data rather than raw patient records.

Provenance

Source

figshare

Collection Method

Retrospective analysis of high-resolution MRI scans from a multicenter cohort.

Freshness

Last updated 2026-04-21 04:21:57; freshness should be verified.