Logistic回归模型在乳腺小结节超声鉴别诊断中的应用
|
摘要
目的筛选出乳腺小结节(直径≤1 cm)良、恶性鉴别诊断的超声征象,建立Logistic预报回归模型。方法回顾性分析215例女性乳腺小结节患者的临床资料,以病理结果为因变量,超声征象及年龄作为自变量,建立二分类Logistic回归模型,绘制ROC曲线,评价回归模型的预测能力。结果经Logistic回归分析内部回声均匀性、形态、边缘特征、纵横比、血流分级、血流阻力指数、高回声声晕、微钙化、同侧腋窝淋巴结肿大及年龄进入回归方程。不同超声特征经Logistic回归分析中最大似然比分析,差异有统计学意义(P <0.05)。Logistic回归模型与术前超声诊断正确率分别为94.2%和87.2%。Logistic回归模型的曲线下面积为0.918(95%CI:0.873,0.963)。结论基于超声征象建立的Logistic回归模型有较高的预报准确率和临床实用性。
Objective To screen the ultrasound features of benign and malignant small breast nodules(diameter≤1 cm) and to establish a logistic prediction regression model. Methods The clinical data of 215 female patients with small breast nodules were retrospectively analyzed. Pathological results were used as dependent variables, while ultrasound signs and age were used as independent variables. Binary Logistic regression based on maximum likelihood estimation in partial forward step-wise was used to establish regression model. The receiver operating characteristic curve(ROC) is used to evaluate the diagnostic efficacy of regression model. Results The internal echo uniformity, shape, margin, aspect ratio, flow grade, flow resistance index, hyperechoic halo,microcalcification, ipsilateral axillary lymphadenectasis and age were entered the Logistic equation. The different ultrasound features independently predicting diagnostic efficacy of malignant nodules in breast, which was statistically significant(P < 0.05). The correct rates of Logistic regression model and preoperative ultrasound diagnosis were94.2% and 87.2%, respectively. The area under the curve(AUC) of logistic regression model was 0.918(95% CI:0.873, 0.963). Conclusions The Logistic regression model based on ultrasound signs had high prediction accuracy and high clinical applicability.
Objective To screen the ultrasound features of benign and malignant small breast nodules(diameter≤1 cm) and to establish a logistic prediction regression model. Methods The clinical data of 215 female patients with small breast nodules were retrospectively analyzed. Pathological results were used as dependent variables, while ultrasound signs and age were used as independent variables. Binary Logistic regression based on maximum likelihood estimation in partial forward step-wise was used to establish regression model. The receiver operating characteristic curve(ROC) is used to evaluate the diagnostic efficacy of regression model. Results The internal echo uniformity, shape, margin, aspect ratio, flow grade, flow resistance index, hyperechoic halo,microcalcification, ipsilateral axillary lymphadenectasis and age were entered the Logistic equation. The different ultrasound features independently predicting diagnostic efficacy of malignant nodules in breast, which was statistically significant(P < 0.05). The correct rates of Logistic regression model and preoperative ultrasound diagnosis were94.2% and 87.2%, respectively. The area under the curve(AUC) of logistic regression model was 0.918(95% CI:0.873, 0.963). Conclusions The Logistic regression model based on ultrasound signs had high prediction accuracy and high clinical applicability.
引文
[1]IZUMORI A,TAKEBE K,SATO A.Ultrasound findings and histological features of ductal carcinoma in situ detected by ultrasound examination alone[J].Breast Cancer,2010,17(2):136-141.
[2]ADLER D D,CARSON P L,RUBIN J M,et al.Doppler ultrasound color flow imaging in the study of breast cancer:preliminary findings[J].Ultrasound Med Biol,1990,16(6):553-559.
[3]HAFIZ A,ADENIJI-SOFOLUWE A T,ADEMOLA A F,et al.Sonographic evaluation of axillary lymph nodes in women with newly diagnosed breast cancer at the university college hospital Ibadan,Nigeria[J].Niger Postgrad Med J,2018,25(2):79-86.
[4]姜惠文,于晓丹.超声诊断乳腺癌腋窝淋巴结转移的影像学表现分析及研究[J].影像技术,2017,29(3):35-37.
[5]FAN L,STRASSER-WEIPPL K,LI J J,et al.Breast cancer in China[J].Lancet Oncol,2014,15(7):e279-e289.
[6]TASKIN F,KOSEOGLU K,OZBAS S,et al.Sonographic features of histopathologically benign solid breast lesions that have been classified as BI-RADS 4 on sonography[J].J Clin Ultrasound,2012,40(5):261-265.
[7]TAMAKI K,SASANO H,ISHIDA T,et al.The correlation between ultrasonographic findings and pathologic features in breast disorders[J].Jpn J Clin Oncol,2010,40(10):905-912.
[8]冷晓玲,马富成.乳腺癌肿瘤微环境的超声研究进展[J].中国临床医学影像杂志,2015,26(11):823-826.
[9]XIAO M,YANG S,MENG F,et al.LAPTM4B predicts axillary lymph node metastasis in breast cancer and promotes breast cancer cell aggressiveness in vitro[J].Cell Physiol Biochem,2017,41(3):1072-1082.
[10]王一澎,张扬,王仲照,等.2108例T1~2期乳腺癌患者腋窝淋巴结转移的相关因素分析[J].癌症进展,2016,14(06):530-534.
[11]FENG Y,HUANG R,HE Y,et al.Efficacy of physical examination,ultrasound,and ultrasound combined with fineneedle aspiration for axilla staging of primary breast cancer[J].Breast Cancer Res Treat,2015,149(3):761-765.
[12]JACKSON R S,MYLANDER C,ROSMAN M,et al.Normal axillary ultrasound excludes heavy nodal disease burden in patients with breast cancer[J].Ann Surg Oncol,2015,22(10):3289-3295.
[13]李晓燕.乳腺肿块超声特征与乳腺癌诊断的准确性[J].分子影像学杂志,2017,40(4):409-412.
[14]李金娥,于国放,张志文,等.直接与间接超声征象对小乳腺癌诊断价值的分析[J].中国现代普通外科进展,2011(5):414-416.
[15]RAHBAR G,SIE A C,HANSEN G C,et al.Benign versus malignant solid breast masses:US differentiation[J].Radiology,1999,213(3):889-894.
[2]ADLER D D,CARSON P L,RUBIN J M,et al.Doppler ultrasound color flow imaging in the study of breast cancer:preliminary findings[J].Ultrasound Med Biol,1990,16(6):553-559.
[3]HAFIZ A,ADENIJI-SOFOLUWE A T,ADEMOLA A F,et al.Sonographic evaluation of axillary lymph nodes in women with newly diagnosed breast cancer at the university college hospital Ibadan,Nigeria[J].Niger Postgrad Med J,2018,25(2):79-86.
[4]姜惠文,于晓丹.超声诊断乳腺癌腋窝淋巴结转移的影像学表现分析及研究[J].影像技术,2017,29(3):35-37.
[5]FAN L,STRASSER-WEIPPL K,LI J J,et al.Breast cancer in China[J].Lancet Oncol,2014,15(7):e279-e289.
[6]TASKIN F,KOSEOGLU K,OZBAS S,et al.Sonographic features of histopathologically benign solid breast lesions that have been classified as BI-RADS 4 on sonography[J].J Clin Ultrasound,2012,40(5):261-265.
[7]TAMAKI K,SASANO H,ISHIDA T,et al.The correlation between ultrasonographic findings and pathologic features in breast disorders[J].Jpn J Clin Oncol,2010,40(10):905-912.
[8]冷晓玲,马富成.乳腺癌肿瘤微环境的超声研究进展[J].中国临床医学影像杂志,2015,26(11):823-826.
[9]XIAO M,YANG S,MENG F,et al.LAPTM4B predicts axillary lymph node metastasis in breast cancer and promotes breast cancer cell aggressiveness in vitro[J].Cell Physiol Biochem,2017,41(3):1072-1082.
[10]王一澎,张扬,王仲照,等.2108例T1~2期乳腺癌患者腋窝淋巴结转移的相关因素分析[J].癌症进展,2016,14(06):530-534.
[11]FENG Y,HUANG R,HE Y,et al.Efficacy of physical examination,ultrasound,and ultrasound combined with fineneedle aspiration for axilla staging of primary breast cancer[J].Breast Cancer Res Treat,2015,149(3):761-765.
[12]JACKSON R S,MYLANDER C,ROSMAN M,et al.Normal axillary ultrasound excludes heavy nodal disease burden in patients with breast cancer[J].Ann Surg Oncol,2015,22(10):3289-3295.
[13]李晓燕.乳腺肿块超声特征与乳腺癌诊断的准确性[J].分子影像学杂志,2017,40(4):409-412.
[14]李金娥,于国放,张志文,等.直接与间接超声征象对小乳腺癌诊断价值的分析[J].中国现代普通外科进展,2011(5):414-416.
[15]RAHBAR G,SIE A C,HANSEN G C,et al.Benign versus malignant solid breast masses:US differentiation[J].Radiology,1999,213(3):889-894.