CT Radiomics Model for Differentiating Lung Adenoma from Adenocarcinoma

362 patient records with pathologically confirmed bronchiolar adenoma or lung adenocarcinoma were analyzed. The dataset supports a fusion model combining clinical characteristics, CT morphological features, and tumor-peritumoral radiomics features, developed by Ziqian Zhao and last updated in April 2026. The model achieved AUCs up to 0.939 for differentiating the two conditions.

Use Cases

• Training a classifier to differentiate bronchiolar adenoma from lung adenocarcinoma based on clinical characteristics like lung lobe distribution and density.
• Building a radiomics model using tumor and peritumoral CT features for non-invasive diagnosis.
• Developing a clinical-radiomics fusion model to improve preoperative diagnostic accuracy.
• Comparing the performance of different machine learning algorithms (e.g., MLP) for medical imaging tasks.

Strengths

• Includes data from 362 patients across two medical centers, providing an external validation set.
• The described fusion model achieved high performance metrics, with AUCs up to 0.939 and accuracies up to 0.864.
• Released under a CC-BY-4.0 license, permitting broad reuse with attribution.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The primary file format is DOCX, which may require conversion for direct computational use.

Provenance

Source

figshare, authored by Ziqian Zhao.

Collection Method

Retrospective analysis of patient data from two medical centers.

Time Range

null

Freshness

Last updated 2026-04-15 04:37:03; freshness should be verified.

Geography

null