HOU Hui, ZHU Yinxing, WANG Taiyu, ZHANG Yi, LIU Zhipeng. Efficacy of support vector machine model constructed based on dual-parameter MRI radiomics in predicting the expression of human epidermal growth factor receptor-2 and hormone receptor in breast cancer patients[J]. Journal of Clinical Medicine in Practice, 2024, 28(4): 7-13. DOI: 10.7619/jcmp.20233503
Citation: HOU Hui, ZHU Yinxing, WANG Taiyu, ZHANG Yi, LIU Zhipeng. Efficacy of support vector machine model constructed based on dual-parameter MRI radiomics in predicting the expression of human epidermal growth factor receptor-2 and hormone receptor in breast cancer patients[J]. Journal of Clinical Medicine in Practice, 2024, 28(4): 7-13. DOI: 10.7619/jcmp.20233503

Efficacy of support vector machine model constructed based on dual-parameter MRI radiomics in predicting the expression of human epidermal growth factor receptor-2 and hormone receptor in breast cancer patients

More Information
  • Received Date: November 01, 2023
  • Revised Date: January 02, 2024
  • Available Online: March 05, 2024
  • Objective 

    To construct a support vector machine (SVM) model based on magnetic resonance imaging (MRI) T2WI turbo inversion recovery magnitude (TIRM) and diffusion-weighted imaging (DWI) sequences, and evaluate its predictive performance for expression levels of human epidermal growth factor receptor-2 (HER-2) and hormone receptor (HR) in breast cancer.

    Methods 

    A total of 128 breast cancer lesions underwent breast MRI before surgery or treatment were collected, and were grouped according to immunohistochemical (IHC) method or in situ fluorescence hybridization (FISH) results. ITK-SNAP software was used to outline the three-dimensional volume region of interest (VOI) on magnetic resonance TIRM and DWI sequence images, and Pyradiomics program was introduced to extract the image omics features. After normalization of the data, a recursive feature elimination method based on support vector machine-recursive feature elimination (SVM-RFE) was used to filter the features. A total of 108 cases were divided into training group and verification group according to 8∶2 ratio by random stratified sampling method, and the other 20 cases were used as external test group. SVM machine learning classifier was used to construct the image omics model. Receiver operating characteristic (ROC) curve was used to evaluate the prediction efficiency of the model. DeLong test was used to evaluate the area under the curve (AUC) of each image omics model. SHAP algorithm was used for visual analysis, and the most contributing prediction features were screened.

    Results 

    The prediction efficiency of the combined model (training group AUC=0.94, verification group AUC=0.90) for HER-2 was higher than that of TIRM model(training group AUC=0.85, verification group AUC=0.80) and single DWI model(training group AUC=0.88, verification group AUC=0.66). The AUC of combined model in the external test group was 0.89. The feature contribution of DWI sequence obtained by SHAP algorithm was great. The image omics model based on the combination of TIRM and DWI sequence features (training group AUC=0.96, verification group AUC=0.88) and the single DWI sequence features (training group AUC=0.92, verification group AUC=0.86) was better than the model based on the single TIRM sequence features (training group AUC=0.84, verification group AUC=0.68) in HR prediction. The external test group proved that the combined model had good predictive efficiency, with an AUC of 0.90. The feature contribution of TIRM sequence obtained by SHAP algorithm was great.

    Conclusion 

    The imaging omics model constructed based on the combined features of TIRM and DWI sequences in magnetic resonance imaging has good predictive efficacy for HER-2 level, and has great potential in predicting HR expression, which can provide a basis for the formulation of personalized treatment for breast cancer patients.

  • [1]
    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 Cancer J Clin, 2021, 71(3): 209-249. doi: 10.3322/caac.21660
    [2]
    王海丽. 多参数MRI影像组学融合模型在预测HER-2 2+乳腺癌及不同激素受体状态下HER-2阳性乳腺癌中的应用价值[D]. 济南: 山东大学, 2021.
    [3]
    REINERT T, GONÇALVES R, BINES J. Implications of ESR1 mutations in hormone receptor-positive breast cancer[J]. Curr Treat Options Oncol, 2018, 19(5): 24. doi: 10.1007/s11864-018-0542-0
    [4]
    叶欣华, 熊戴群, 李金高. 西达本胺联合长春瑞滨软胶囊治疗HR阳性、HER-2阴性晚期乳腺癌的临床研究[J]. 实用癌症杂志, 2022, 37(12): 2070-2073. doi: 10.3969/j.issn.1001-5930.2022.12.041
    [5]
    CANTINI L, PISTELLI M, MERLONI F, et al. Body mass index and hormone receptor status influence recurrence risk in HER2-positive early breast cancer patients[J]. Clin Breast Cancer, 2020, 20(1): e89-e98. doi: 10.1016/j.clbc.2019.06.008
    [6]
    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. https://www.cnki.com.cn/Article/CJFDTOTAL-CGZC202304011.htm
    [7]
    LIANG X H, YU X Y, GAO T H. Machine learning with magnetic resonance imaging for prediction of response to neoadjuvant chemotherapy in breast cancer: a systematic review and meta-analysis[J]. Eur J Radiol, 2022, 150: 110247. doi: 10.1016/j.ejrad.2022.110247
    [8]
    陈文静, 牟伟, 张文馨, 等. 平扫T2脂肪抑制序列图像纹理可提高诊断乳腺良恶性结节的准确率[J]. 分子影像学杂志, 2019, 42(4): 453-456. https://www.cnki.com.cn/Article/CJFDTOTAL-FZYX201904007.htm
    [9]
    王振东, 李悦, 申炳俊, 等. 基于迁移学习的乳腺肿瘤组织病理图像分类研究[J]. 长春理工大学学报: 自然科学版, 2023, 46(5): 130-136. https://www.cnki.com.cn/Article/CJFDTOTAL-CGJM202305018.htm
    [10]
    张斌伟, 苟思琪, 程钲益, 等. 乳腺癌患者血清PCSK9、Tracp5b及MUC1表达水平及其与肿瘤病理特征的相关性分析[J]. 检验医学与临床, 2023, 20(9): 1235-1239. https://www.cnki.com.cn/Article/CJFDTOTAL-JYYL202309013.htm
    [11]
    郑洁, 开震天, 夏超然, 等. 基于GEO及TCGA数据库建立乳腺癌他莫昔芬耐药相关预后模型[J]. 检验医学与临床, 2022, 19(23): 3227-3230. doi: 10.3969/j.issn.1672-9455.2022.23.016
    [12]
    张维, 龙松权, 唐瑞骏. 不同分子分型乳腺癌血清CYFRA21-1、HCY和CA15-3的表达差异及与术后复发、转移的关系[J]. 检验医学与临床, 2023, 20(12): 1686-1689. doi: 10.3969/j.issn.1672-9455.2023.12.005
    [13]
    BALTZER P, MANN R M, ⅡMA M, et al. Diffusion-weighted imaging of the breast-a consensus and mission statement from the EUSOBI International Breast Diffusion-Weighted Imaging working group[J]. Eur Radiol, 2020, 30(3): 1436-1450. doi: 10.1007/s00330-019-06510-3
    [14]
    FAN M, LIU Z H, XU M S, et al. Generative adversarial network-based super-resolution of diffusion-weighted imaging: application to tumour radiomics in breast cancer[J]. NMR Biomed, 2020, 33(8): e4345. doi: 10.1002/nbm.4345
    [15]
    NEMETH A, CHAUDET P, LEPORQ B, et al. Multicontrast MRI-based radiomics for the prediction of pathological complete response to neoadjuvant chemotherapy in patients with early triple negative breast cancer[J]. MAGMA, 2021, 34(6): 833-844. doi: 10.1007/s10334-021-00941-0
    [16]
    徐丽娜, 唐竹晓, 李双标, 等. 基于DWI和DCE-MRI的影像特征对四种不同分子亚型乳腺癌的诊断价值探讨[J]. 现代肿瘤医学, 2021, 29(1): 116-120. https://www.cnki.com.cn/Article/CJFDTOTAL-SXZL202101026.htm
    [17]
    ZHANG S H, WANG X L, YANG Z, et al. Intra- and peritumoral radiomics model based on early DCE-MRI for preoperative prediction of molecular subtypes in invasive ductal breast carcinoma: a multitask machine learning study[J]. Front Oncol, 2022, 12: 905551. doi: 10.3389/fonc.2022.905551
    [18]
    HUANG Y H, WEI L H, HU Y L, et al. Multi-parametric MRI-based radiomics models for predicting molecular subtype and androgen receptor expression in breast cancer[J]. Front Oncol, 2021, 11: 706733. doi: 10.3389/fonc.2021.706733
    [19]
    LA FORGIA D, FANIZZI A, CAMPOBASSO F, et al. Radiomic analysis in contrast-enhanced spectral mammography for predicting breast cancer histological outcome[J]. Diagnostics, 2020, 10(9): 708. doi: 10.3390/diagnostics10090708
    [20]
    WU Q X, WANG S, CHEN X, et al. Radiomics analysis of magnetic resonance imaging improves diagnostic performance of lymph node metastasis in patients with cervical cancer[J]. Radiother Oncol, 2019, 138: 141-148. doi: 10.1016/j.radonc.2019.04.035
    [21]
    CHADDAD A, DANIEL P, NIAZI T. Radiomics evaluation of histological heterogeneity using multiscale textures derived from 3D wavelet transformation of multispectral images[J]. Front Oncol, 2018, 8: 96. doi: 10.3389/fonc.2018.00096
  • Related Articles

    [1]LIU Guixiang, AN Jinmei, HOU Jichong, SONG Nuan, ZHAO Yuexia. Effects of painting combined with drug intervention on mental states, compliance and quality of life in patients with anxiety disorder[J]. Journal of Clinical Medicine in Practice, 2023, 27(22): 81-85. DOI: 10.7619/jcmp.20230109
    [2]DAI Xiaoyan, WANG Xinting, YUAN Xiaochen. Correlations of anxiety and depression with quality of life in patients with atrial fibrillation[J]. Journal of Clinical Medicine in Practice, 2022, 26(10): 54-57. DOI: 10.7619/jcmp.20214676
    [3]GAO Juan, DU Hong, LIU Han, LIU Menghui. Effect of information support on anxiety and depression of premature infants with maternal separation[J]. Journal of Clinical Medicine in Practice, 2017, (8): 142-144. DOI: 10.7619/jcmp.201708042
    [4]LI Qin, WANG Zhengbing. Analysis in status of anxiety and depression and social support in 82 patients with permanent colostomy[J]. Journal of Clinical Medicine in Practice, 2016, (8): 94-97. DOI: 10.7619/jcmp.201608029
    [5]ZHAO Yanhua. Influence of continuous nursing on postoperative negative emotions and quality of life in patients with bladder cancer after stoma of abdominal wall[J]. Journal of Clinical Medicine in Practice, 2016, (6): 64-66. DOI: 10.7619/jcmp.201606020
    [6]LI Jingjing, XU Jing, XU Yaping. Effect of comprehensive nursing intervention on relieving anxiety of hospitalized neonates' parents[J]. Journal of Clinical Medicine in Practice, 2016, (2): 112-114. DOI: 10.7619/jcmp.201602035
    [7]XIE Xiaohui. Influence of humane care nursing on anxiety and quality of sleep in female patients with menopause syndrome[J]. Journal of Clinical Medicine in Practice, 2015, (16): 92-95. DOI: 10.7619/jcmp.201516029
    [8]CHEN Mingzhu. Effect analysis of prenatal nursing intervention on anxiety and quality of life of patients with pregnancy induced hypertension[J]. Journal of Clinical Medicine in Practice, 2014, (12): 149-151. DOI: 10.7619/jcmp.201412054
    [9]CHENG Lin, LIN Ling, CHEN Aiping, XU Aimei. Influence of nursing intervention on anxiety mood of patients with acute attack of bronchial asthma[J]. Journal of Clinical Medicine in Practice, 2013, (10): 27-29. DOI: 10.7619/jcmp.201310011
    [10]SUN Ting. Application of Roy's adaptation mode in the mitigation of anxiety in patients with urinary stoma[J]. Journal of Clinical Medicine in Practice, 2013, (8): 23-25. DOI: 10.7619/jcmp.201308009
  • Cited by

    Periodical cited type(9)

    1. 王涛,张艳达,霍继珍,穆伟,王超,刘伟. 血清神经元特异性烯醇化酶和D-二聚体在高血压脑出血术后神经功能障碍患者中的表达水平及检测意义. 陕西医学杂志. 2024(05): 658-661 .
    2. 黄煌,文涛,陈兵,吴成坤. 高血压脑出血预后相关危险因素的Meta分析. 广东医科大学学报. 2023(01): 44-53 .
    3. 高振军,高丽凤. 微创小骨窗血肿清除术联合尿激酶溶解治疗高血压脑出血的价值探究. 中外医学研究. 2023(14): 20-23 .
    4. 邵小丽. 延续性护理在高血压脑出血患者中的实施及对生活能力的影响研究. 婚育与健康. 2023(18): 151-153 .
    5. 廖成伟,张登兴. 清震汤联合甘露醇在高血压脑出血术后患者中的应用. 中外医学研究. 2023(29): 29-32 .
    6. 郑海军,戴凯茜,娄晓辉,林逢春,曾上飞. 缺氧诱导因子-1α/血管内皮生长因子通路表达与高血压脑出血破入脑室患者颅内压及预后的相关性. 中华高血压杂志. 2022(03): 283-286 .
    7. 赵建华,朱骏,瞿准,王超. 术后早期颅内压参数预测高血压性脑出血手术患者预后的价值. 川北医学院学报. 2022(06): 701-703+707 .
    8. 侯德文,朱勇军,张东. 补阳还五汤联合超早期尿激酶给药对高血压脑出血微创术后患者的效果观察. 四川中医. 2022(09): 124-127 .
    9. 徐宣乐,李学超,王琼,赵悦,段飞,王宏利,赵虎威,王国飞. 单通道、软-硬通道结合微创血肿穿刺引流术与神经内镜下血肿清除术治疗高血压脑出血临床疗效研究. 陕西医学杂志. 2021(08): 977-982 .

    Other cited types(3)

Catalog

    Article views (123) PDF downloads (15) Cited by(12)

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return