Integrated Intratumoral and Peritumoral Ultrasound Radiomics Models for Breast Nodule Diagnosis Using…

AI / informaticsBritish journal of hospital medicine (London, England : 2005)· Jul 2026

Integrated Intratumoral and Peritumoral Ultrasound Radiomics Models for Breast Nodule Diagnosis Using Machine Learning.

Xinru Yang, Jiaxin Zuo, Cuiping Liu … Ping Xiong

Read paper

Breast ImagingAI / informaticsDiagnosisQ3IF 1.3

Adding peritumoral ultrasound features raised AUC for detecting malignant breast nodules

Integrated Intratumoral and Peritumoral Ultrasound Radiomics Models for Breast Nodule Diagnosis Using Machine Learning.

Xinru Yang … Ping Xiong

British journal of hospital medicine (London, England · Jul 2026 · Q3 in General Medicine

Background

The differentiation of benign and malignant breast nodules, particularly those categorized as Breast Imaging Reporting and Data System (BI-RADS) 3-4, remains a clinical challenge due to the subjectivity and operator dependence of conventional ultrasound assessment.

Purpose

This study aimed to evaluate the diagnostic value of intratumoral and peritumoral ultrasound radiomics features in distinguishing benign from malignant BI-RADS 3-4 breast nodules and to construct interpretable machine learning models.

Methods

Ultrasound images and parameters (BI-RADS classification) of breast nodules were retrospectively collected from female patients at two institutions between January 2021 and June 2024: 571 patients (880 nodules) from Institution 1 (Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine) and 333 patients (351 nodules) from Institution 2 (Shanghai Second People's Hospital).

n = 571 patients

Results

AUC scale 0-1; 0.875 (with peritumoral data) beat 0.787 for tumor-only model

42.2%

Sensitivity

97%

Specificity

More results

Across the training, internal validation, and external test sets, support vector machine demonstrated the most stable and balanced performance.

Most models incorporating peritumoral features demonstrated AUCs that were higher than or comparable to those of the T model.

More results

SHAP analysis indicated that the high specificity was mainly driven by texture and shape features.

“

Conclusion · 1 of 2

Integrating intratumoral and peritumoral radiomics features significantly improves the diagnostic accuracy and objectivity for differentiating benign and malignant breast nodules.

Conclusion · 2 of 2

This approach may aid clinical decision-making, reduce unnecessary biopsies, and support early precision diagnosis of breast cancer.

Integrated Intratumoral and Peritumoral Ultrasound Radiomics Models for Breast Nodule Diagnosis Using Machine Learning.

Integrated Intratumoral and Peritumoral Ultrasound Radiomics Models for Breast Nodule Diagnosis Using Machine Learning.

Related papers