Background <p>Ultrasound (US) can be used as a reliable and early predictor of pathological response to neoadjuvant chemotherapy (NAC) in breast cancer (BC). However, existing studies have reported inconsistent results, which highlights the need for a thorough evaluation of evidence.</p> Methods <p>PubMed, Web of Science, Cochrane Library, Embase, and ClinicalTrials.gov databases were searched to screen relevant studies on the use of US in predicting pathological response to NAC in patients with BC from inception to October 2025. The pooled area under the curve (AUC), sensitivity, and specificity were calculated through Stata 14.0.</p> Results <p>This meta-analysis enrolled 72 studies involving 8439 patients with BC who underwent NAC. Pooled analysis indicated that contrast-enhanced US exhibited the highest performance, with an AUC of 0.90 (95% confidence interval [CI]: 0.87–0.93), sensitivity of 87%, and specificity of 79%. Color Doppler US, automated breast volume scanner, and shear-wave elastography achieved AUCs of 0.86 (95% CI: 0.83–0.89), 0.86 (95% CI: 0.83–0.89), and 0.86 (95% CI: 0.82–0.89), respectively. In addition, strain elastography and grayscale US attained AUCs of 0.85 (95% CI: 0.82–0.88) and 0.77 (95% CI: 0.73–0.81), respectively.</p> Conclusion <p>US, especially contrast-enhanced US, is helpful in predicting pathological response to NAC in patients with BC.</p>