Artificial Intelligence (AI), Breast Neoplasms, Deep Learning, Diffusion Magnetic Resonance Imaging, Magnetic Resonance Imaging (MRI)
Conditions
Keywords
Breast, Magnetic Resonance Imaging, Artificial Intelligence, Deep learning
Brief summary
This study is conducted under the ethics-approved project titled "Artificial Intelligence Solution for Simplifying the Diagnostic Workflow of Breast MRI''.The goal of this observational study is to develop an integrated breast MRI system that uses diffusion-weighted imaging (DWI) to create synthetic contrast-enhanced images. This system aims to diagnose and screen for breast cancer without the need for contrast agents, while using a generated risk score to perform imaging-based triage and risk stratification. Participants will include people aged 18 and older who require a breast MRI either for evaluation of a suspicious finding or for high-risk screening. This study seeks to answer two main questions: * Can synthetic contrast-enhanced images generated from DWI match real contrast-enhanced images in their ability to distinguish benign from malignant breast lesions? * Can the risk score derived from DWI-based synthetic images enable imaging-level risk stratification, allowing people at lower risk to avoid contrast agent injection? Researchers will compare the quality of synthetic images against real contrast-enhanced images and will recruit radiologists to assess how well these images perform for diagnostic and screening tasks. MRI data from participants undergoing breast MRI will be used to train, validate, and test this integrated system.
Detailed description
We selected "other" in Time Perspective. This study will retrospectively collect MRI data from patients who underwent breast MRI at multiple centers between 2014 and 2024. We will also prospectively enroll MRI data from multiple centers for testing to assess the model's robustness.
Interventions
DIAGNOSTIC_TESTNon-contrast breast MRI diagnostic model
An integrated AI model capable of generating synthetic contrast-enhanced images and distinguishing between benign and malignant lesions, as well as performing risk stratification
Sponsors
Peking University People's Hospital
Study design
Observational model
COHORT
Time perspective
OTHER
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
Yes
Inclusion criteria
1. Complete breast MRI data; 2. Negative pathology biopsy results or negative follow-up examinations for at least 12 months for non-cancer cases; 3. Positive biopsy results that meet the requirements for the pathological subtype of cancer for cancer cases; 4. Original data that can be used to verify clinical status, including radiological and pathological reports;
Exclusion criteria
1. Partial mastectomy or puncture biopsy on the diseased side of the breast prior to breast MRI examination; 2. Poor image quality; 3. Implants in the affected breast;
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| MRI examination | Baseline | A multi-parameter contrast-enhanced breast MRI examination was performed, including fat-suppressed T2-weighted imaging, diffusion-weighted imaging, dynamic contrast-enhanced sequences, and fat-suppressed T1-weighted imaging. |
Contacts
CONTACTHAOQUAN CHEN, MD
Outcome results
None listed