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

NCT06069921 | Completed

• 1 other identifier: YXLL-KY-2023(045)
• Study Type: observational
• Target: 400
• Locations: 1 country
• Sites: 1

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.

Conditions

Breast Diseases

Outcome Measures

Primary Outcomes (1)

• radiomcis prediction model and the model evaluation

  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

  Immediately evaluated after the radiomcis prediction model was built

Secondary Outcomes (1)

• deep learning prediction model and the model evaluation

  Immediately evaluated after the deep learning prediction model was built

Other Outcomes (1)

• the combination prediction model and the model evaluation

  Immediately evaluated after the combination prediction model was built

Study Arms (2)

maligant

female patients with US-visible solid maligant breast masses who underwent biopsy and/or surgical resection.

benign

female patients with US-visible solid benign breast masses who underwent biopsy and/or surgical resection.

Eligibility Criteria

• Age: 15 Years - 80 Years
• Sex: female
• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Patients with breast lesions attending the First Affiliated Hospital of Shandong First Medical University were selected.

You may qualify if:

• 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.

You may not qualify if:

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

Sponsors & Collaborators

• Ma Zhe: lead

Study Sites (1)

QianfoshanH

Jinan, Shandong, 250014, China

Location

MeSH Terms

Conditions

Breast Diseases

Condition Hierarchy (Ancestors)

Skin Diseases; Skin and Connective Tissue Diseases

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR INVESTIGATOR
• PI Title: Director of Ultrasound

Study Record Dates

• First Submitted: September 29, 2023
• First Posted: October 6, 2023
• Study Start: January 1, 2015
• Primary Completion: December 30, 2022
• Study Completion: December 30, 2022
• Last Updated: June 25, 2024

Record last verified: 2024-06

Data Sharing

• IPD Sharing: Will not share

Locations

CN (1)