含瘤周组织的超声影像组学在鉴别乳腺结节良恶性中的价值

doi:10.6040/j.issn.1671-7554.0.2024.1064

摘要/Abstract

摘要： 目的基于超声瘤内及含瘤周2 mm、4 mm区域构建影像组学模型,预测其在鉴别乳腺结节良恶性中的临床诊断价值。方法回顾性收集220例超声诊断为乳腺结节且在河北北方学院附属第一医院进行手术的女性患者的超声图像,按照7∶3的比例将乳腺结节图像随机分为训练集(n=154)和测试集(n=66),在乳腺结节最大切面图像勾画感兴趣区(region of interest, ROI),即瘤内组,并且分别自动适形外扩2 mm、4 mm,得到含瘤周2 mm组、含瘤周4 mm组;通过LASSO回归筛选出最优影像组学特征,建立逻辑回归模型,用AUC、敏感度、特异度及约登指数比较影像组学模型在训练集和测试集的诊断价值,采用Delong检验比较各影像组学模型之间的统计学差异,采用校准曲线和决策曲线评估影像组学模型的预测效能。结果含瘤周4 mm组的影像组学模型较另外两种模型效能更佳。在训练集中,瘤内组、含瘤周2 mm组及含瘤周4 mm组的AUC分别为0.886、0.902、0.945;在测试集中,瘤内组、含瘤周2 mm组及含瘤周4 mm组的AUC分别为0.793、0.757、0.901。在训练集中,瘤内组、含瘤周2 mm组模型分别与含瘤周4 mm组模型之间AUC对比,Delong检验P均<0.05。在训练集中,含瘤周4 mm组的敏感度、特异度及约登指数分别为0.927、0.833、0.760,在测试集中含瘤周4 mm组的敏感度、特异度及约登指数分别为0.879、0.818、0.697。结论与瘤内组模型和含瘤周2 mm组模型相比,基于超声含瘤周4 mm组的影像组学模型鉴别乳腺结节良恶性有更好的预测价值。

关键词: 超声, 影像组学, 乳腺结节, 瘤内区域, 瘤周区域

Abstract: Objective To construct the radiomics model of ultrasound based on intratumoral and peritumoral 2 mm and 4 mm regions and to predict the clinical diagnostic value of these models in identifying benign and malignant breast nodules. Methods Retrospective collection of the ultrasound images of 220 female patients diagnosed as breast nodules by ultrasound were performed. The patients underwent surgery at the Frist Affiliated Hospital of Hebei North University. The breast nodule ultrasound images were randomly divided into a training set(n=154)and a test set(n=66)in a ratio of 7∶3. The region of interest(ROI)was outlined as the intratumoral group on the maximal section image of the breast nodule and automatically conformed to the outward extension of 2 mm and 4 mm, respectively, to obtain the peritumoral 2 mm group and peritumoral 4 mm group. The optimal imaging histological features of the intratumoral group, peritumoral 2 mm group and peritumoral 4 mm group were screened by LASSO regression to construct a Logistic regression models. The diagnostic efficacy of the models in the training set and test set were evaluated using AUC, sensitivity, specificity and Jordon index, and the statistical difference among the models were verified using Delong test. The predictive efficacy of radiomics models were assessed using calibration and decision curves. Results Among the three groups, the radiomics model of the peritumoral 4mm group had the best efficacy. The values of AUC in the intratumoral group, peritumoral 2 mm group and peritumoral 4 mm group in the training set were 0.886, 0.902, and 0.945, while those in the testing set were 0.793, 0.757, 0.901, respectively. In the training set, the values of AUC in the intratumoral group and the peritumoral 2 mm group were statistical different with that in the peritumoral 4 mm group(both P<0.05). The sensitivity, specificity and Yoden index of the peritumoral 4 mm group in the training set and test set were 0.927, 0.833, 0.760, and 0.879, 0.818, 0.697, respectively. Conclusion The ultrasound-based radiomics model of the peritumoral 4 mm group has better predictive value in identifying benign and malignant breast nodules compared to the intratumoral group and the peritumoral 2 mm group.

Key words: Ultrasound, Radiomics, Breast nodules, Intratumoural region, Peritumoral region

中图分类号:

R445.1

卢晓颂,杨瑞敏,王义成,周海丰,罗兵,李晓宇,李娜娜. 含瘤周组织的超声影像组学在鉴别乳腺结节良恶性中的价值[J]. 山东大学学报 (医学版), 2025, 63(1): 90-98.

LU Xiaosong, YANG Ruimin, WANG Yicheng, ZHOU Haifeng, LUO Bing, LI Xiaoyu, LI Nana. Clinical value of ultrasound radiomics based on peritumour-containing tissues in identifying benign and malignant breast nodules[J]. Journal of Shandong University (Health Sciences), 2025, 63(1): 90-98.

参考文献

[1] Sung H, Ferlay J, Siegel RL, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2021, 71(3): 209-249.
[2] Ginsburg O, Bray F, Coleman MP, et al. The global burden of womens cancers: a grand challenge in global health[J]. Lancet, 2017, 389(10071): 847-860.
[3] Conti A, Duggento A, Indovina I, et al. Radiomics in breast cancer classification and prediction[J]. Semin Cancer Biol, 2021, 72: 238-250. doi:10.1016/j.semcancer.2020.04.002.
[4] Li X, Fu P, Jiang M, et al. The diagnostic performance of dynamic contrast-enhanced MRI and its correlation with subtypes of breast cancer[J]. Medicine, 2021, 100(51): e28109. doi:10.1097/MD.0000000000028109.
[5] Rahbar H, Partridge SC. Multiparametric MR imaging of breast cancer[J]. Magn Reson Imaging Clin N Am, 2016, 24(1): 223-238.
[6] 刘聿辉, 除亮, 李姗姗, 等. 3.0TMRI联合计算机辅助系统在乳腺肿瘤诊断中的价值[J]. 山东大学学报(医学版), 2011, 49(12): 118-122. LIU Yuhui, CHU Liang, LI Shanshan, et al. Clinical value of 3.0T MRI combined with computer aided diagnosis in breast tumors[J]. Journal of Shandong University(Health Sciences), 2011, 49(12): 118-122.
[7] 李欣欣, 陈修婷, 李杰, 等. 乳腺影像报告和数据系统分类联合乳腺X线摄影影像组学鉴别诊断乳腺良、恶性无定形钙化灶[J]. 中国医学影像技术, 2024, 40(10): 1519-1523. LI Xinxin, CHEN Xiuting, LI Jie, et al. Breast imaging reporting and data system classification combined with mammography radiomics for differentiating breast benign and malignant amorphous calcification lesions[J]. Chinese Journal of Medical Imaging Technology, 2024, 40(10): 1519-1523.
[8] 张紫燕, 李海歌, 朱建国, 等. 基于对比增强能谱乳腺X线摄影对乳腺良恶性病灶鉴别的定量及定性分析[J]. 临床放射学杂志, 2023, 42(1): 46-50. ZHANG Ziyan, LI Haige, ZHU Jianguo, et al. Comparison of quantitative and qualitative analysis of contrast-enhanced spectral mammography between benign and malignant lesions of breast[J]. Journal of Clinical Radiology, 2023, 42(1): 46-50.
[9] Kim MY, Kim SY, Kim YS, et al. Added value of deep learning-based computer-aided diagnosis and shear wave elastography to b-mode ultrasound for evaluation of breast masses detected by screening ultrasound[J]. Medicine, 2021, 100(31): e26823. doi:10.1097/MD.0000000000026823.
[10] Yıldız MS, Goya C, Adin ME. Contribution of sonoelastography to diagnosis in distinguishing benign and malignant breast masses[J]. J Ultrasound Med, 2020, 39(7): 1395-1403.
[11] Huang JX, Wu L, Wang XY, et al. Delta radiomics based on longitudinal dual-modal ultrasound can early predict response to neoadjuvant chemotherapy in breast cancer patients[J]. Acad Radiol. 2024, 31(5): 1738-1747.
[12] Sun QC, Lin XN, Zhao YS, et al. Deep learning vs. radiomics for predicting axillary lymph node metastasis of breast cancer using ultrasound images: dont forget the peritumoral region[J]. Front Oncol, 2020, 10: 53. doi:10.3389/fonc.2020.00053.
[13] Li CL, Song LR, Yin JD. Intratumoral and peritumoral radiomics based on functional parametric maps from breast DCE-MRI for prediction of HER-2 and ki-67 status[J]. J Magn Reson Imaging, 2021, 54(3): 703-714.
[14] Wang SM, Sun YQ, Li RM, et al. Diagnostic performance of perilesional radiomics analysis of contrast-enhanced mammography for the differentiation of benign and malignant breast lesions[J]. Eur Radiol, 2022, 32(1): 639-649.
[15] 徐帅娅, 罗芳琼, 巴晨曦, 等. 多模态超声对70例BI-RADS 4类乳腺病变的诊断价值[J].山东大学学报(医学版), 2023, 61(2): 95-101. XU Shuaiya, LUO Fangqiong, BA Chenxi, et al. Diagnostic value of multi-modal ultrasound in 70 cases of BI-RADS category 4 breast lesions[J]. Journal of Shandong University(Health Sciences), 2023, 61(2): 95-101.
[16] Su GH, Xiao Y, You C, et al. Radiogenomic-based multiomic analysis reveals imaging intratumor heterogeneity phenotypes and therapeutic targets[J]. Sci Adv, 2023, 9(40): eadf0837. doi:10.1126/sciadv.adf0837.
[17] 代婷, 苏桐, 王锐, 等. DCE-MRI影像特征对乳腺癌激素受体、HER-2及三阴性乳腺癌的预测价值[J]. 磁共振成像, 2023, 14(4): 57-67. DAI Ting, SU Tong, WANG Rui, et al. Predictive value of DCE-MRI features of breast cancer on hormone receptor, HER-2 and triple negative breast cancer[J]. Chinese Journal of Magnetic Resonance Imaging, 2023, 14(4): 57-67.
[18] Shi ZW, Huang XM, Cheng ZL, et al. MRI-based quantification of intratumoral heterogeneity for predicting treatment response to neoadjuvant chemotherapy in breast cancer[J]. Radiology, 2023, 308(1): e222830. doi:10.1148/radiol.222830.
[19] Braman N, Prasanna P, Whitney J, et al. Association of peritumoral radiomics with tumor biology and pathologic response to preoperative targeted therapy for HER2(ERBB2)-positive breast cancer[J]. JAMA Netw Open, 2019, 2(4): e192561. doi:10.1001/jamanetworkopen.2019.2561.
[20] Wu YM, Ma QQ, Fan LF, et al. An automated breast volume scanner-based intra- and peritumoral radiomics nomogram for the preoperative prediction of expression of ki-67 in breast malignancy[J]. Acad Radiol, 2024, 31(1): 93-103.
[21] Braman N, Prasanna P, Whitney J, et al. Association of peritumoral radiomics with tumor biology and pathologic response to preoperative targeted therapy for HER2(ERBB2)-positive breast cancer[J]. JAMA Netw Open, 2019, 2(4): e192561. doi:10.1001/jamanetworkopen.2019.2561.
[22] Zhang WY, Wang SY, Wang YC, et al. Ultrasound-based radiomics nomogram for predicting axillary lymph node metastasis in early-stage breast cancer[J]. Radiol Med, 2024, 129(2): 211-221.
[23] Zhou J, Yu X, Wu QX, et al. Radiomics analysis of intratumoral and different peritumoral regions from multiparametric MRI for evaluating HER2 status of breast cancer: a comparative study[J]. Heliyon, 2024, 10(7): e28722. doi:10.1016/j.heliyon.2024.e28722.
[24] Zhong LC, Shi L, Zhou L, et al. Development of a nomogram-based model combining intra- and peritumoral ultrasound radiomics with clinical features for differentiating benign from malignant in Breast Imaging Reporting and Data System category 3-5 nodules[J]. Quant Imaging Med Surg, 2023, 13(10): 6899-6910.
[25] Gong XT, Li QF, Gu LS, et al. Conventional ultrasound and contrast-enhanced ultrasound radiomics in breast cancer and molecular subtype diagnosis[J]. Front Oncol, 2023, 13: 1158736. doi:10.3389/fonc.2023.1158736.
[26] Shi SS, An X, Li YH. Ultrasound radiomics-based logistic regression model to differentiate between benign and malignant breast nodules[J]. J Ultrasound Med, 2023, 42(4): 869-879.
[27] Huang ZB, Mo SJ, Wu HY, et al. Optimizing breast cancer diagnosis with photoacoustic imaging: an analysis of intratumoral and peritumoral radiomics[J]. Photoacoustics, 2024, 38: 100606. doi:10.1016/j.pacs.2024.100606.
[28] 师琳, 钟李长, 马方, 等. 瘤周超声影像组学对乳腺结节良恶性的鉴别诊断价值[J].肿瘤影像学, 2023, 32(6): 485-491. SHI Lin, ZHONG Lichang, MA Fang, et al. The value of ultrasound-based peri-tumoral radiomics in differential diagnosis of benign and malignant breast nodules[J]. Oncoradiology, 2023, 32(6): 485-491.
[29] 刘艳, 冷珊珊, 夏晓娜, 等. 基于影像组学参数评估376例幕上自发性脑出血患者的功能状态[J]. 山东大学学报(医学版), 2023, 61(5): 59-67. LIU Yan, LENG Shanshan, XIA Xiaona, et al. Functional outcomes of 376 patients with supratentorial spontaneous intracerebral hemorrhage based on radiomic parameters[J]. Journal of Shandong University(Health Sciences), 2023, 61(5): 59-67.
[30] 赵新凯, 王茂林, 郑小敏. 构建磁共振影像组学模型鉴别诊断乳腺浸润性导管癌及乳腺硬化性腺病价值[J].中国计划生育学杂志, 2023, 31(10): 2348-2353. ZHAO Xinkai, WANG Maolin, ZHENG Xiaomin. Value of the model of magnetic resonance imaging omics for differential diagnosing breast infiltrating ductal carcinoma and breast sclerosing adenosis[J]. Chinese Journal of Family Planning, 2023, 31(10): 2348-2353.
[31] 焦光丽, 石子馨, 陈蓉, 等. 基于增强CT影像组学预测卵巢癌患者铂类药物敏感性[J]. 山东大学学报(医学版), 2023, 61(12): 62-69. JIAO Guangli, SHI Zixin, CHEN Rong, et al. Radiomics of enhanced CT in predicting the response to platinum-based chemotherapy for ovarian cancer[J]. Journal of Shandong University(Health Sciences), 2023, 61(12): 62-69.
[32] 李春萍, 杨瑞敏, 王义成, 等. 基于超声影像组学在预测BI-RADS 4类肿瘤良恶性中的价值[J]. 中国超声医学杂志, 2024, 40(3): 274-277. LI Chunping, YANG Ruimin, WANG Yicheng, et al. Value of ultrasound-based radiomics in differentiating benign and malignant BI-RADS category 4 tumors[J]. Chinese Journal of Ultrasound in Medicine, 2024, 40(3): 274-277.
[33] Bisaso KR, Karungi SA, Kiragga A, et al. A comparative study of logistic regression based machine learning techniques for prediction of early virological suppression in antiretroviral initiating HIV patients[J]. BMC Med Inform Decis Mak, 2018, 18(1): 77. doi:10.1186/s12911-018-0659-x.
[34] Erickson BJ, Korfiatis P, Akkus Z, et al. Machine learning for medical imaging[J]. Radiographics, 2017, 37(2): 505-515.
[35] Mao N, Yin P, Wang QL, et al. Added value of radiomics on mammography for breast cancer diagnosis: a feasibility study[J]. J Am Coll Radiol, 2019, 16(4): 485-491.
[36] Shi SS, An X, Li YH. Ultrasound radiomics-based logistic regression model to differentiate between benign and malignant breast nodules[J]. J Ultrasound Med, 2023, 42(4): 869-879.
[37] 陈剑琼, 肖榕, 周玮珺, 等. 灰阶超声影像组学在诊断乳腺结节良恶性中的应用价值[J].安徽医科大学学报, 2022, 57(2): 325-328.
[38] 苏蕾, 周牧野, 李阳, 等. 超声影像组学对乳腺BI-RADS 3类及以上结节良恶性鉴别诊断的应用价值[J].蚌埠医学院学报, 2023, 48(8): 1101-1104. SU Lei, ZHOU Muye, LI Yang, et al. Application value of ultrasound imaging in differential diagnosis of benign and malignant breast BI-RADS3 and above nodules[J]. Journal of Bengbu Medical College, 2023, 48(8): 1101-1104.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed