AI-Enhanced Analysis of Breast Density and Background Parenchymal Enhancement (BPE)

This study expands upon previous research investigating the correlation between breast density, Background Parenchymal Enhancement (BPE), and age in contrast-enhanced mammography (CEM). By integrating Artificial Intelligence (AI) methodologies, including Artificial Neural Networks (ANNs) and deep learning models, the study aims to optimize the accuracy of predictions and validate prior findings obtained through multiple linear regression.

Study Overview

• Status: Enrolling by invitation
• Conditions: Artificial Intelligence (AI); Breast Parenchimal Enhancement

• Study Type: Observational
• Enrollment (Estimated): 213

Contacts and Locations

Study Locations

• Italy
  • Naples, Italy, 80138
    • University of Campania Luigi Vanvitelli

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Women aged 18 years and older who underwent CEM for diagnostic or surveillance purposes.

Patients with recorded BPE levels and BI-RADS breast density classification.

Relational database containing structured data for correlation matrix analysis and AI model training.

Description

Patients who underwent CEM, mammography, and ultrasound between May 2022 and June 2023.

Availability of BPE assessment, BI-RADS density classification, and age data.

Complete dataset available for statistical and AI-based analysis.

Exclusion Criteria:

Patients with prior breast cancer treatment that could alter BPE.

Incomplete imaging or missing classification data.

Contraindications to contrast-enhanced imaging.

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort
patiens underwent CEM

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Correlation between breast density, BPE, and age using AI-driven analysis.	Evaluating whether AI models, including neural networks, can enhance prediction accuracy for BPE assessment compared to conventional multiple linear regression.	Data analysis within 12 months of study completion.

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
AI-based optimization of breast density and BPE classification	Evaluating the performance of neural networks in predicting BPE levels across different breast density categories.	Within 12 months of study completion
Comparative performance of multiple linear regression vs. AI models.	Assessing the accuracy of traditional statistical methods versus ANN-based predictions in explaining variance in BPE values.	Within 12 months of study completion.
Mean Squared Error (MSE) and explained variance in predictive models	Analyzing the error rates and variance explained by different AI models compared to multiple linear regression.	Within 12 months of study completion

Collaborators and Investigators

• Sponsor: Link Campus University
• Collaborators: University of Campania Luigi Vanvitelli

Study record dates

Study Major Dates

• Study Start (Actual): May 1, 2022
• Primary Completion (Actual): June 30, 2023
• Study Completion (Estimated): February 1, 2025

Study Registration Dates

• First Submitted: February 15, 2025
• First Submitted That Met QC Criteria: February 15, 2025
• First Posted (Actual): March 25, 2025

Study Record Updates

• Last Update Posted (Actual): March 25, 2025
• Last Update Submitted That Met QC Criteria: February 15, 2025
• Last Verified: February 1, 2025

More Information

Terms related to this study

• Other Study ID Numbers: T_6_2025

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No