1. Study Design Overview Study Type: Single-center, prospective, observational, diagnostic study. Primary Objective: To validate whether Super-Resolution Ultrasound Imaging (SRUS) can accurately predict pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) in breast cancer at an early stage (after the first cycle of chemotherapy).

   Sample Size: A total of 150 patients are planned to be enrolled. Study Period: March 2026 - March 2028.

2. Core Methodology: Cohort Allocation This study employs a classic "Model Development-Validation" cohort design to construct a predictive model and verify its generalizability.

   Allocation Method: Systematic random allocation. Allocation Ratio: 7:3. Randomization: Patients will be assigned based on the sequence of enrollment using a computer-generated random sequence.

   Blinding Principle: Allocation information will be concealed (blinded) from patients and the clinical treatment team. Only the research coordinators and statisticians will have access to the grouping data to prevent information leakage.

   Validation Set (Independent Validation Cohort): Comprising 30% of the sample (45 cases). The data will remain "sealed" until model construction is finalized. It will be used for unbiased, objective performance evaluation of the final model (e.g., calculating AUC, sensitivity).

3. Study Procedures and Visits

   The study workflow strictly adheres to the chemotherapy timeline, with core data collection points focused on the early phase of treatment:

   V0 (Screening): Confirmation of eligibility criteria. V1 (Baseline, Pre-chemotherapy): Initial SRUS examination to acquire baseline tumor data.

   V2 (Early Visit, 48-72 hours after the 1st cycle): The critical data point for the predictive model; the first follow-up examination.

   V3 (Mid-term Visit, Pre-4th cycle): The second follow-up examination. V4 (Surgery, 3-4 weeks after the last cycle): Radical surgery is performed. V5 (Endpoint Assessment, 2-4 weeks post-surgery): Acquisition of pathological results to confirm pCR status (the gold standard).

4. Key Technology and Statistics Key Technology: The Mindray Resona A20 ultrasound system will be used in conjunction with Sulfur Hexafluoride (SF6) microbubble contrast agents to extract quantitative parameters such as tumor microvascular density and blood volume.

   Statistical Analysis:

   In the Training Set: LASSO regression will be used for feature selection to construct a logistic regression predictive model.

   In the Validation Set: The formula derived from the training set will be directly applied to calculate the Area Under the ROC Curve (AUC), calibration curves, and other metrics to evaluate model performance.

5. Eligibility Criteria Inclusion Criteria: Females aged 18-75, histologically confirmed invasive breast cancer, scheduled for standard neoadjuvant chemotherapy, with lesions clearly visible on baseline ultrasound.

Exclusion Criteria: History of prior breast cancer treatment (surgery, radiotherapy, chemotherapy), presence of other active malignancies, pregnancy or lactation, severe organ dysfunction, or poor image quality.

Background and Rationale Breast cancer is the most common malignancy among women worldwide. Neoadjuvant chemotherapy (NAC) is standard for locally advanced breast cancer, aiming to downstage tumors and increase surgical options. Conventional imaging modalities (ultrasound, MRI) have limitations in detecting early microvascular changes and residual disease. Super-resolution ultrasound imaging (SRUS) is an emerging technique based on ultrasound localization microscopy, enabling visualization of microvasculature at micron-scale resolution. It provides quantitative parameters including vessel density, blood volume, vascular complexity, perfusion index, and intensity analysis. Preliminary evidence suggests SRUS can detect early microvascular alterations before morphological changes become apparent, but prospective data in breast cancer NAC response prediction are lacking.

Study Design Single-center, prospective, observational, diagnostic study. Patients receive standard NAC per clinical guidelines; no treatment intervention is imposed. The study involves additional SRUS examinations at predefined time points.

Model Development and Validation

Consecutive eligible patients are enrolled and randomly assigned (7:3 ratio using computer-generated sequence) to:

Training set (70%, n=105): for model development, feature selection, and internal optimization.

Validation set (30%, n=45): for independent, unbiased performance validation.

Allocation is concealed from patients and clinical care team. Analysis of SRUS images and pathological assessment are blinded to clinical data and group assignment.

Technical Procedures

Equipment: Mindray Resona A20 ultrasound system, probe frequency 5-18 MHz.

Contrast agent: 4.8 mL sulfur hexafluoride microbubbles (SonoVue) injected intravenously, followed by 5 mL saline flush.

Acquisition: Dynamic image sequences (6 seconds each) are acquired during early arterial phase (10-30 s) and late arterial phase (20-45 s) with breath-holding.

Post-processing: SRIPlatform software extracts quantitative parameters: vessel density, blood volume, vascular complexity, perfusion index, intensity, and velocity. Changes from baseline (Δ%) are calculated.

Study Timeline

V1 (Baseline, within 1 week before NAC): Baseline SRUS.

V2 (Early response, 48-72 hours after cycle 1): First follow-up SRUS (key predictive time point).

V3 (Mid-treatment, before cycle 4): Second follow-up SRUS.

V4 (Surgery, 3-4 weeks after last NAC): Radical breast surgery.

V5 (Pathology, 2-4 weeks post-surgery): Pathological complete response (pCR) determination (reference standard).

Sample Size Based on an assumed pCR rate of 30%, a two-sided 95% confidence interval width of 0.15 for sensitivity (expected 80%), 10% dropout, and 30% allocation to validation set, total enrollment is 150 patients. The training set provides ~32 pCR events, supporting evaluation of 3-5 candidate predictors (event-per-variable rule: 10:1).

Statistical Analysis

Software: R 4.3.0 (glmnet, rms, pROC, rmda).

Variable screening: Univariate analysis (p<0.10), then LASSO regression with 10-fold cross-validation (λ.1se) for dimension reduction.

Model building: Multivariate logistic regression; coefficients, OR, 95% CI.

Internal validation: Bootstrap optimism-corrected AUC.

External validation: Apply final model to validation set; assess discrimination, calibration, and clinical utility (decision curve analysis).

Reporting: Adherence to TRIPOD statement.

Safety and Risk Mitigation SRUS is non-invasive with output within safe limits, equivalent to conventional ultrasound. Risks are minimal (mild discomfort, potential privacy breach). Data are anonymized and stored on encrypted hospital servers.

Quality Control

Standardized operating procedures for image acquisition and post-processing.

Operator training and inter-operator consistency testing.

Image quality review by core laboratory (signal-to-noise ratio, tracking stability, coverage of inflow-washout phases).

100% source data verification for key variables.

Quarterly internal audits.

Ethics and Dissemination Approved by the Institutional Ethics Committee of the First Affiliated Hospital of USTC (West District, Anhui Provincial Cancer Hospital). Conducted in accordance with the Declaration of Helsinki. Written informed consent obtained from all participants. Results will be submitted for publication in peer-reviewed journals regardless of outcome.

Study Period March 2026 - March 2028.

Inclusion Criteria

1. Age and Gender: Female patients aged 18 to 75 years.
2. Diagnosis: Histologically confirmed invasive breast cancer via core needle biopsy.
3. Treatment Plan: Scheduled to receive standard neoadjuvant chemotherapy at our institution.
4. Imaging: The lesion is clearly visible on baseline ultrasound. Consent: Willing to participate in the study and sign the written informed consent form.

Exclusion Criteria

1. Prior Treatment: History of any prior treatment for ipsilateral breast cancer (e.g., surgery, radiotherapy, chemotherapy, or targeted therapy).
2. Other Malignancies: Presence of other active malignancies.
3. Pregnancy/Lactation: Pregnant or breastfeeding women.
4. Health Status: Severe cardiac, hepatic, or renal insufficiency, or psychiatric disorders that preclude cooperation with the examination.
5. Image Quality: Poor ultrasound image quality that prevents SR-US analysis.

This study will enroll female patients aged 18 to 75 years with histologically confirmed invasive breast cancer who are scheduled to receive neoadjuvant chemotherapy (NAC) prior to surgery.

Participants must have at least one measurable tumor lesion suitable for super-resolution ultrasound imaging. Patients with evidence of distant metastasis (Stage IV) or those who have received prior systemic therapy for the current cancer diagnosis will be excluded.

The study aims to recruit approximately 150 participants from the Anhui Provincial Cancer Hospital. This population represents a typical cohort of locally advanced breast cancer patients undergoing standard NAC protocols.