Data Sheet 1: Radiomic Features Associated with MRD-Negative Surveillance in NSCLC

A 2026 dataset from a single-center translational cohort of 71 patients with completely resected stage IB–IIIA non-small cell lung cancer (NSCLC). It contains a Rad-Score derived from 1,432 pre-operative CT radiomic features, associated with molecular residual disease (MRD) negativity and molecular correlates from sequencing and spatial transcriptomics. The dataset was authored by Zehao Huang and is hosted on figshare.

Use Cases

• Predicting molecular residual disease (MRD) conversion risk based on pre-operative radiomic features.
• Correlating non-invasive imaging signatures with ferroptotic tumor microenvironment niches.
• Validating radiogenomic models for metastasis-free survival (MFS) in independent cohorts like TCIA NSCLC-Radiogenomics.
• Investigating the association between radiomic scores and immune cell infiltration (e.g., CD8+ T cells, M1 macrophages).
• Benchmarking radiomic prognostic performance against established comparators like the Kratz 14-gene signature.

Strengths

• Includes data from 71 patients in a prospective clinical trial (CTONG 2201) with longitudinal MRD surveillance.
• Rad-Score derived from 1,432 pre-operative CT radiomic features and validated in two external cohorts totaling 267 patients.
• Multimodal validation includes whole-exome sequencing, bulk RNA-seq, spatial transcriptomics (36,318 spots), and functional cell assays.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

Single-center translational cohort nested within the prospective CTONG 2201 trial.

Collection Method

Derived from pre-operative contrast-enhanced CT scans, sequencing, and immunofluorescence assays.

Freshness

Last updated 2026-05-25 06:03:38; freshness should be verified.