ABSTRACT
Objective:To evaluate the differential diagnostic efficacy of a predictive model of breast imaging reporting and data system (BI-RADS) classification combined with mammography radiomics classifier for various X-ray phenotype of breast lesions.Methods:A retrospective analysis was performed on 2 055 female patients who underwent mammography examination and were confirmed by pathology from May 2013 to August 2020 in Zhongda Hospital, Southeast University. Breast lesion was classified into mass or non-mass according to the fifth edition of BI-RADS. The mass was further divided into small mass (maximum diameter ≤ 2 cm) and large mass (maximum diameter>2 cm), the non-mass was further divided into asymmetric, calcification and structural distortions. By manually segmenting the region of interest of the lesion, the radiomics features were extracted and the model was constructed. Receiver operating characteristic curve and area under the curve (AUC) were used to assess the diagnostic efficacy of the BI-RADS classification, the radiomics model and the combined model for various phenotypes of breast lesions. Differences among the AUC were analyzed by the DeLong test.Results:The AUCs based on the BI-RADS classification, the radiomics model and the combined model were 0.924±0.006, 0.827±0.009 and 0.947±0.005 respectively. Compared with BI-RADS classification and the radiomics model, AUC of the combined model was the highest, and the differences were statistically significant ( Z=9.29, 14.94, P<0.001). For large mass, small mass and non-mass, combined model (AUC=0.958±0.007, 0.933±0.013, 0.939±0.008) showed the best performance when compared to the BI-RADS classification (AUC=0.937±0.010, 0.896±0.020, 0.916±0.011; Z=5.32, 3.90, 5.08, P<0.001) or the radiomics model (AUC=0.872±0.012, 0.851±0.021, 0.758±0.016; Z=7.86, 4.53, 12.13, P<0.001). The AUC of the combined model for benign and malignant asymmetric breast lesions (0.897±0.017) was higher than that of the BI-RADS classification (AUC=0.866±0.020, Z=4.27, P<0.001) and the radiomics model (AUC=0.633±0.029, Z=7.44, P<0.001); however, the AUC of the combined model for benign and malignant calcification and structural distortion of breast lesions (0.971±0.010, 0.811±0.057, respectively) was only higher than that of the radiomics model (AUC=0.827±0.021, 0.586±0.075, Z=7.40, 3.15, P<0.001), and there was no significant difference with the BI-RADS classification (AUC=0.959±0.012, 0.800±0.061, Z=1.87, 0.39, P>0.05). Conclusion:The combined model shows better differential diagnostic performance, which is valued in the clinical application.
ABSTRACT
Objective To investigate the signal intensity ratio and signal-to-noise ratio of breast lesions in 3.0 T MR diffusion weighted imaging with different b values.Methods Ninety seven patients with 106 solid breast lesions (44 malignant,62 benign) confirmed by pathology were retrospectively analyzed.The patients were examined by 3.0 T MR DWI with different b values (b =0,400,800,1 000 s/mm2) before surgery.The signal-to-noise ratio (SNR) and signal intensity ratio (SIR) of benign and malignant lesions were observed and measured under different b values.One-way ANOVA and t test were used to analyze quantitative data.ROC curve was used to analyze the diagnostic efficiency of SIR under different b values.Results Under different b values,class A image was found in 92 cases,class B images was found in 5 cases.While b value were 0,400,800,1 000 s/mm2,SIR of benign lesions were 2.33 ± 1.36,2.25 ± 1.13,2.06 ± 0.84,2.02 ± 0.79 respectively,SIR of malignant lesions were 2.02 ± 0.79,2.27 ± 0.85,2.61±0.78,2.82 ± 1.01 respectively.While b value was 0 or 400 s/mm2,there was no significant differences for SIR between benign and malignant lesions (t value were 1.58,1.26 respectively; P value were 0.12,0.90 respectively),but there were statistically significances between benign and malignant lesions under b value 800 s/mm2 or 1 000 s/mm2 (t value were 3.41,4.29 respectively ;P ＜0.01).There was no differences in SIR for benign and malignant lesions under different b values respectively (F value is 1.21,2.22 respectively; P ＞0.05).While b value were 0,400,800,1 000 s/mm2,the diagnostic sensitivity and specificity of SIR for breast benign and malignant lesions were 56.8％ (25/44),56.8％ (25/44),75.0％ (33/44),77.3％ (34/44) and 51.6％ (32/62),54.8％ (34/62),66.1％ (41/62),66.1％ (41/62) respectively.While b value were 0,400,800,1 000 s/mm2,SNR were 170 ±93,145 ±72,84 ±41,70 ± 39 respectively.Different b values,there was statistically significant difference between groups (F =55.89,P ＜ 0.01) ; and there were significant differences between every two b values (P ＜ 0.05).Conclusion The higher b values (800 s/mm2 and 1 000 s/mm2) are superior to lower b values in the differential diagnosis of benign and malignant breast lesions using 3.0 T MR scanner.