Abstract:Objective To construct a prediction model of type 4 benign and malignant breast nodules by breast imaging reporting and data system (BI-RADS) based on multi-parameter magnetic resonance index. Methods A total of 135 lesions in 135 patients with type 4 breast nodules by BI-RADS treated in the 909th Hospital from January 2022 to January 2024 were retrospectively included, and they were divided into malignant group and benign group according to the nature of the lesions. Single-factor and multifactor methods were used to evaluate the independent predictors of type 4 benign and malignant breast nodules by BI-RADS. A prediction models of type 4 benign and malignant breast nodules by BI-RADS was constructed and the prediction efficiency was analyzed. Results There were 87 benign lesions and 48 malignant lesions in all 135 lesions of 135 patients. There were statistically significant differences in age (t=-5.485), lesion enhancement type (χ2=33.170), and average kurtosis value (t=-5.772) between the two groups (P<0.05). logistic multivariate analysis confirmed that age (OR=1.169), average kurtosis value (OR=483.393) and lesion enhancement type (OR=15.437) could be used as independent predictors of benign or malignant breast nodules of type 4 BI-RADS(P<0.05). Age, lesion enhancement type, mean kurtosis value and P-value prediction probability were used to predict the ROC curve of breast nodule, and the areas under the curve were 0.765, 0.720, 0.770 and 0.896, respectively. Conclusions Age, mean kurtosis value and lesion enhancement type are independent predictors of type 4 benign and malignant breast nodules by BI-RADS. The data model based on the above three factors has shown good efficiency in predicting the nature of breast nodules in patients.
林琼真, 陈佳韬, 方欣欣, 罗爱芳. 基于多参数磁共振指标的BI-RADS 4类乳腺结节良恶性预测模型构建[J]. 武警医学, 2025, 36(3): 200-204.
LIN Qiongzhen, CHEN Jiatao, FANG Xinxin, LUO Aifang. Construction of prediction model of type 4 benign and malignant breast nodules by BI-RADS based on multi-parameter magnetic resonance index. Med. J. Chin. Peop. Armed Poli. Forc., 2025, 36(3): 200-204.
Sung H, Ferlay J, Siegel R L, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries [J]. CA, 2021,71(3): 209-249.
Yin H L, Jiang Y, Xu Z, et al. Combined diagnosis of multiparametric MRI-based deep learning models facilitates differentiating triple-negative breast cancer from fibroadenoma magnetic resonance BI-RADS 4 lesions [J]. J Cancer Res Clin Oncol, 2023, 149(6): 2575-2584.
[4]
Marino M A, Avendano D, Sevilimedu V, et al. Limited value of multiparametric MRI with dynamic contrast-enhanced and diffusion-weighted imaging in non-mass enhancing breast tumors [J]. Eur J Radiol, 2022, 156(11): 110523-110530.
[5]
He H, Song M, Tian Z, et al. Multiparametric MRI model with synthetic MRI, DWI multi-quantitative parameters, and differential sub-sampling with cartesian ordering enables BI-RADS 4 lesions diagnosis with high accuracy [J]. Front Oncol, 2024, 13(1): 1180131-1180138.
[6]
Daimiel N I, Lo G R, Saccarelli C, et al. Diagnostic value of diffusion-weighted imaging with synthetic b-values in breast tumors: comparison with dynamic contrast-enhanced and multiparametric MRI [J]. Eur Radiol, 2021, 31(1): 356-367.
Park V Y, Shin H J, Kang B J, et al. Diffusion-weighted magnetic resonance imaging for preoperative evaluation of patients with breast cancer: protocol of a prospective, multicenter, observational cohort study [J]. J Breast Cancer, 2023, 26(3): 292-301.
[9]
Hegde S. Artifacts in magnetic resonance imaging caused by dental materials: a systematic review[J]. J Evid Based Dent Pract, 2022, 22(3): 101754-101760.
[10]
Zhu C R, Chen K Y, Li P, et al. Accuracy of multiparametric MRI in distinguishing the breast malignant lesions from benign lesions: a meta-analysis [J]. Acta Radiol, 2021, 62(10): 1290-1297.
[11]
Honda M, Le Bihan D, Kataoka M, et al. Diffusion kurtosis imaging as a biomarker of breast cancer [J]. BJR Open, 2023, 5(1): 2022-2030.
[12]
Romeo V, Clauser P, Rasul S, et al. AI-enhanced simultaneous multiparametric (18)F-FDG PET/MRI for accurate breast cancer diagnosis [J]. Eur J Nucl Med Mol Imaging, 2022, 49(2): 596-608.
[13]
Lin C X, Tian Y, Li J M, et al. Diagnostic value of multiple b-value diffusion-weighted imaging in discriminating the malignant from benign breast lesions [J]. BMC Med Imaging, 2023, 23(1): 10-16.
[14]
Meng L, Zhao X, Guo J, et al. Improved differential diagnosis based on BI-RADS descriptors and apparent diffusion coefficient for breast lesions: a multiparametric mri analysis as compared to kaiser score [J]. Acad Radiol, 2023, 30(Suppl 2): S93-S103.
[15]
Kazerouni A S, Rahbar H, Partridge S C. Is NME the enemy of breast DWI? [J]. Eur J Radiol, 2023, 159(11): 110648-110653.
Arian A, Seyed-Kolbadi F Z, Yaghoobpoor S, et al. Diagnostic accuracy of intravoxel incoherent motion (IVIM) and dynamic contrast-enhanced (DCE) MRI to differentiate benign from malignant breast lesions: A systematic review and meta-analysis [J]. Eur J Radiol, 2023, 167(10): 111051-111058.
[18]
Wang G, Guo Q, Shi D, et al. Clinical breast mri-based radiomics for distinguishing benign and malignant lesions: an analysis of sequences and enhanced phases [J]. J Magn Reson Imaging, 2023, 25(11): 819-825.
[19]
Istomin A, Masarwah A, Okuma H, et al. A multiparametric classification system for lesions detected by breast magnetic resonance imaging [J]. Eur J Radiol, 2020, 132(11): 109322-109329.
[20]
Lang M, Liang P, Shen H, et al. Head-to-head comparison of perfluorobutane contrast-enhanced US and multiparametric MRI for breast cancer: a prospective, multicenter study [J]. Breast Cancer Res, 2023, 25(1): 61-67.