Overview

This study is a multicenter, prospective, observational cohort study to evaluate the predictive performance of pre-treatment DCE-MRI-based artificial intelligence (AI) models for neoadjuvant chemotherapy benefit in locally advanced triple-negative breast cancer. The study plans to enroll eligible locally advanced triple-negative breast cancer patients receiving routine standard neoadjuvant chemotherapy and stratify participants into high-benefit and low-benefit subgroups via the established AI model based on baseline breast DCE-MRI images.

All enrolled patients will undergo systematic collection of baseline clinical-pathological data, pre-treatment DCE-MRI scans, neoadjuvant chemotherapy regimens, pathological complete response (pCR) status, objective response rate (ORR), and long-term survival endpoints including disease-free survival (DFS) and overall survival (OS). The primary objective compares the pCR rate between AI-defined high-benefit patients and published historical control data; secondary analyses compare ORR, pCR proportion, DFS and OS between AI-stratified high-benefit and low-benefit subgroups to comprehensively verify the clinical value of this imaging AI model for individualized neoadjuvant chemotherapy selection.

Eligibility

Inclusion Criteria:

1. Female patients aged ≥ 18 years.
2. Histologically confirmed invasive triple-negative breast cancer; patients with ER/PR 1%-10% positive and HER2-negative status are also eligible given their biological features resembling triple-negative breast cancer.
3. Clinical stage T2-3N0-3M0 or T1N1-3M0 according to AJCC 8th edition, with potential indication for neoadjuvant chemotherapy.
4. Availability of both MRI and pathological biopsy materials; standardized breast DCE-MRI examination and pathological biopsy completed prior to neoadjuvant chemotherapy, with image quality satisfying requirements for model analysis.
5. Patients planned to receive standard neoadjuvant chemotherapy followed by surgical treatment. Patients who are undergoing standard neoadjuvant chemotherapy or have completed neoadjuvant chemotherapy awaiting surgery are also eligible.
6. Post-operative pathology available to assess neoadjuvant chemotherapy response (pCR or non-pCR).
7. Eastern Cooperative Oncology Group (ECOG) performance status 0-1; adequate function of major organs to tolerate planned therapy.
8. Voluntary participation and provision of written informed consent.

Exclusion Criteria:

1. Prior systemic anti-tumor therapy for breast cancer other than neoadjuvant chemotherapy.
2. Inflammatory breast cancer or distant metastatic disease (M1).
3. Concurrent active malignancy during neoadjuvant chemotherapy or surgical period.
4. History of autoimmune diseases, such as systemic lupus erythematosus, acanthosis and other related disorders.
5. Documented history of neurological or psychiatric disorders, including epilepsy, dementia, etc.
6. Contraindications to MRI or unacceptable image quality for analysis.
7. No definitive surgery performed or incomplete postoperative pathological reports.
8. Severe comorbidities that preclude chemotherapy or surgical intervention.
9. Missing required clinical information, MRI images, or pathological biopsy specimens for analysis.
10. Other conditions rendering the subject inappropriate for enrollment, in the investigator's judgment.