Value of Multimodal Magnetic Resonance Imaging Based on Artificial Intelligence in Differentiating Benign and Malignant Breast Lesions
Objective To explore the diagnostic value of multimodal magnetic resonance imaging based on artificial intelligence in benign and malignant breast lesions.Methods From May 2021 to July 2023,120 patients with benign and malignant breast lesions who underwent surgical treatment in Fuzhou Jianqiang Fifth Hospital were selected as the research objects.The patients were divided into benign lesion group(n=72)and malignant lesion group(n=48).All patients completed multimodal magnetic resonance imaging and high-frequency color Doppler ultrasound examination based on artificial intelligence in our hospital.The accuracy,sensitivity and specificity of different examination methods,as well as sADC,ADC and f indexes of the two groups were compared.Results The sensitivity,specificity,accuracy,positive predictive value and negative predictive value of multimodal magnetic resonance imaging based on artificial intelligence in the diagnosis of benign and malignant breast lesions were 95.83%,98.61%,97.50%,93.88%and 95.95%,respectively,which were higher than 83.33%,80.56%,81.67%,64.52%and 72.50%of high frequency color Doppler ultrasound(P<0.05).The sADC in malignant group was lower than that in benign group(P<0.05).The ADC and f in the malignant lesion group were higher than those in the benign lesion group(P<0.05).Conclusion Multimodal magnetic resonance imaging based on artificial intelligence has high sensitivity in the diagnosis of benign and malignant breast lesions,which is helpful to improve the accuracy of breast mass diagnosis and provide more accurate examination results.
Artificial intelligenceMultimodal magnetic resonance imagingHigh frequency color Doppler ultrasoundBenign and malignant breast lesions
国家科技期刊平台
NSTL
万方数据
