Ultrasound Radiomics for Breast Cancer Differentiation, 237 Patients

237 patients with granulomatous lobular mastitis or breast cancer underwent preoperative ultrasound examinations at Quzhou People's Hospital between April 2013 and April 2023. Radiomic features were extracted from the images to build interpretable machine learning models for preoperative differentiation. The dataset likely contains the extracted radiomic features and clinical predictors used in the study.

Use Cases

• Building interpretable classification models for granulomatous lobular mastitis and breast cancer based on ultrasound radiomic features.
• Evaluating the performance of combined clinical and radiomics signatures for diagnostic tasks.
• Analyzing the correlation of specific imaging biomarker features (e.g., lbp_3D_k_glszm_SmallAreaLowGrayLevelEmphasis) with disease prediction.
• Applying feature selection techniques (ICC, Pearson correlation, LASSO) to high-dimensional radiomic data.
• Conducting decision curve analysis to assess the clinical utility of a diagnostic model.

Strengths

• Includes data from 237 patients with pathological diagnoses.
• Extracted 1,161 radiomic features per ultrasound image, providing a high-dimensional feature space.
• Model performance is reported with specific AUC metrics (0.935 in training, 0.833 in validation).

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 a 407.5 KB DOCX file, suggesting it may be a research paper or summary rather than raw data tables.

Provenance

Source

Quzhou People's Hospital

Collection Method

Retrospective study of patient ultrasound images and pathological diagnoses.

Time Range

April 2013 to April 2023

Freshness

Last updated 2026-04-24 04:22:35; freshness should be verified.

Geography

Likely Quzhou, China (inferred from hospital name).