Using Deep Learning and Radiomics to Diagnose Benign and Malignant Breast Lesions Based on Ultrasound

Ultrasound-based Deep Learning Signature and Radiomics Signature Nomogram for Diagnosis of Benign and Malignant Breast Lesions of BI-RADS Category 4 Using Intratumoral and Peritumoral Regions

Status

Completed

Phases

Unknown

Study type

Observational

Source

ClinicalTrials.gov

Registry ID

NCT06069921

Enrollment

400

Registered

2023-10-06

Start date

2015-01-01

Completion date

2022-12-30

Last updated

2024-06-25

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Breast Diseases

Brief summary

This retrospective study aimed to create a prediction model using deep learning and radiomics features extracted from intratumoral and peritumoral regions of breast lesions in ultrasound images, to diagnose benign and malignant breast lesions with BI-RADS 4 classification. Materials and methods: Patients who visited in The First Affiliated Hospital of Shandong First Medical University ＆ Shandong Provincial Qianfoshan Hospital were collected. Their general clinical features, information on preoperative ultrasound diagnosis, and postoperative pathologic data were reviewed.

Interventions

None listed

Study design

Observational model

COHORT

Time perspective

RETROSPECTIVE

Eligibility

Sex/Gender

FEMALE

Age

15 Years to 80 Years

Healthy volunteers

Inclusion criteria

* female patients with US-visible solid breast masses who underwent biopsy and/or surgical resection, and were classified as having BI-RADS 4 lesions in medical US reports.

Exclusion criteria

* preoperative endocrine therapy, chemotherapy, or radiotherapy, preoperative invasive breast operation, insufficient image quality, and no pathological results.

Design outcomes

Primary

Measure	Time frame	Description
radiomcis prediction model and the model evaluation	Immediately evaluated after the radiomcis prediction model was built	three radiomics models were established using the support vector machines algorithm based on features extracted from the intratumoral, peritumoral, and combined regions of the breast lesions.The models were evaluated using various metrics, including AUC, accuracy, sensitivity, specificity, PPV, and NPV

Secondary

Measure	Time frame	Description
deep learning prediction model and the model evaluation	Immediately evaluated after the deep learning prediction model was built	three deep learning models were established using the support vector machines algorithm based on features extracted from the intratumoral, peritumoral, and combined regions of the breast lesions.The models were evaluated using various metrics, including AUC, accuracy, sensitivity, specificity, PPV, and NPV

Other

Measure	Time frame	Description
the combination prediction model and the model evaluation	Immediately evaluated after the combination prediction model was built	the combination model was established using clinical features , deep learning score and radiomics score.The models were evaluated using various metrics, including AUC, accuracy, sensitivity, specificity, PPV, and NPV

Countries

China

Outcome results