Prediction of Neoadjuvant Therapy Efficacy and Prognosis for Breast Cancer Based on Multimodal Data

NCT07671690 | Not Yet Recruiting

• 1 other identifier: KYLX2026-205
• Study Type: interventional
• Target: 1,800
• Locations: 0 countries
• Sites: N/A

Brief Summary

This study aims to develop a multimodal deep learning model integrating MRI, ultrasound, digital pathology and clinical information based on multicenter retrospective data. To externally validate the model in an independent prospective cohort, and evaluate its accuracy in predicting pathological complete response (pCR), 3-year and 5-year disease-free survival (DFS). To establish visual tools such as nomograms, assisting clinicians in identifying patients with chemoresistance and facilitating individualized de-escalation or escalation treatment strategies.

Conditions

Breast Carcinoma

Outcome Measures

Primary Outcomes (1)

• Predictive value of multimodal data for neoadjuvant therapy efficacy in breast cancer

  Combined with preoperative multimodal MRI and ultrasound imaging parameters, pathological baseline data and clinical data, a prediction model for neoadjuvant therapy efficacy in breast cancer is constructed. Taking postoperative pathological response results as the evaluation basis, the predictive efficacy of multimodal data for neoadjuvant therapy complete response and non-complete response is evaluated.

  From enrollment to the end of surgery

Secondary Outcomes (1)

• Prognostic predictive value of multimodal data for breast cancer

  From enrollment to the end of surgery

Study Arms (1)

Prediction of Neoadjuvant Therapy Efficacy and Prognosis for Breast Cancer Based on Multimodal Data

EXPERIMENTAL

To develop a multimodal deep learning model integrating MRI, ultrasound, digital pathology and clinical information based on multicenter retrospective data.

Diagnostic Test: To explore the value of a multimodal deep learning model integrating MRI, ultrasound, digital pathology and clinical information in predicting pCR and long-term prognosis.

Interventions

To explore the value of a multimodal deep learning model integrating MRI, ultrasound, digital pathology and clinical information in predicting pCR and long-term prognosis. DIAGNOSTIC_TEST

MRI and ultrasound were performed in addition to conventional treatment regimens

Prediction of Neoadjuvant Therapy Efficacy and Prognosis for Breast Cancer Based on Multimodal Data

Eligibility Criteria

• Age: 18 Years - 80 Years
• Sex: female
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Histopathologically confirmed invasive breast cancer;
• Planned to receive a full course of neoadjuvant therapy;
• Complete baseline imaging data (MRI/ultrasound/mammography) and core needle pathology results available.

You may not qualify if:

• Previous history of ipsilateral breast cancer or chest radiotherapy;
• Distant metastasis (Stage IV);
• Poor image quality or missing clinical data exceeding 20%.

Sponsors & Collaborators

• Yunnan Cancer Hospital: lead

MeSH Terms

Conditions

Breast Neoplasms

Interventions

Ultrasonography

Condition Hierarchy (Ancestors)

Neoplasms by Site; Neoplasms; Breast Diseases; Skin Diseases; Skin and Connective Tissue Diseases

Intervention Hierarchy (Ancestors)

Diagnostic Imaging; Diagnostic Techniques and Procedures; Diagnosis

Study Officials

• Lianhua Ye

  Ethics Committee of Yunnan Provincial Cancer Hospital

  STUDY DIRECTOR

Central Study Contacts

Yu Xie

CONTACT

13708445492; xieyu@kmmu.edu.cn

Zhenhui LI

CONTACT

13698736132; lizhenhui@kmmu.edu.cn

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: NA
• Masking: NONE
• Purpose: DIAGNOSTIC
• Intervention Model: SINGLE GROUP
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: May 19, 2026
• First Posted: June 26, 2026
• Study Start: June 1, 2026
• Primary Completion (Estimated): December 31, 2026
• Study Completion (Estimated): June 30, 2029
• Last Updated: June 26, 2026

Record last verified: 2026-05

Data Sharing

• IPD Sharing: Will not share