|Table of Contents|

Nomogram based on conventional ultrasound,ultrasound-based radiomics and HER-2 to predict breast cancer neoadjuvant chemotherapy response

Journal Of Modern Oncology[ISSN:1672-4992/CN:61-1415/R]

Issue:
2024 08
Page:
1486-1491
Research Field:
Publishing date:

Info

Title:
Nomogram based on conventional ultrasound,ultrasound-based radiomics and HER-2 to predict breast cancer neoadjuvant chemotherapy response
Author(s):
LI Xinyan; CUI Guanghe; LIU Feifei; ZHANG Wenxin; WANG Xiaonan; XU Yongbo; SUN Fang
Department of Ultrasound，Binzhou Medical University Hospital，Shandong Binzhou 256603，China.
Keywords:
ultrasonography; radiomics; breast cancer; neoadjuvant chemotherapy
PACS:
R737.9
DOI:
10.3969/j.issn.1672-4992.2024.08.021
Abstract:
Objective:To investigate the value of a nomogram based on conventional ultrasound (CUS),ultrasound-based radiomics and HER-2 in predicting the efficacy of neoadjuvant chemotherapy (NAC) in breast cancer.Methods：Retrospective analysis of 95 patients undergoing NAC at our hospital from September 2018 to March 2023.Patients were divided into effective and ineffective groups according to postoperative pathological results.Radiomics features were extracted from the ultrasound images,and the Least Absolute Shrinkage and Selection Operator were used to create the Radiomics score.The random forest Recursive Feature Elimination (RFE) was applied to screen conventionalultrasound features.Logistic regression was used to construct several nomogram models,including CUS-radiomics (CUS-Rad),radiomics-HER-2 (Rad-HER-2),CUS-HER-2 (CUS-HER-2) and CUS-radiomics-HER-2 (CUS-Rad-HER-2).The performance of the models was compared using the area under the receiver operating characteristic curve (AUC) and the clinical decision curve (DCA),and the improvement of the model by HER-2 was quantified using the integrated discrimination improvement (IDI).The 1 000-fold bootstrap method was used for internal verification and the mean AUC was calculated.Results：A total of 1 084 radiomics features were extracted from the ultrasound images,and 17 radiomics features were selected to build the Radiomics score.The RFE results showed that among the conventional ultrasound features,the model based on the size and the lateral shadow had the highest accuracy,with an accuracy of 0.662.When comparing the nomograms,the CUS-Rad-HER-2 showed the best performance with an AUC of 0.933.The DCA curve showed the greatest clinical benefit across a wide range of thresholds.IDI showed that the performance of the CUS-Rad model improved by 15.98% when HER-2 was added.The mean AUC of the CUS-Rad-HER-2 model was 0.913 when internally validated using the bootstrap method.Conclusion：Conventional ultrasound combined with radiomics and HER-2 may improve the accuracy of predicting NAC response.

References:

［1］LIANG Y,ZHANG H,SONG X,et al.Metastatic heterogeneity of breast cancer:Molecular mechanism and potential therapeutic targets ［J］.Semin Cancer Biol,2020,60:14-27.
［2］LI F,YANG Y,WEI Y,et al.Predicting neoadjuvant chemotherapy benefit using deep learning from stromal histology in breast cancer ［J］.NPJ Breast Cancer,2022,8(1):124.
［3］LIU Q,TANG L,CHEN M.Ultrasound strain elastography and contrast-enhanced ultrasound in predicting the efficacy of neoadjuvant chemotherapy for breast cancer:a nomogram integrating Ki-67 and ultrasound features ［J］.J Ultrasound Med,2022,41(9):2191-2201.
［4］LUO WQ,HUANG QX,HUANG XW,et al.Predicting breast cancer in breast imaging reporting and data system (BI-RADS) ultrasound category 4 or 5 lesions:A nomogram combining radiomics and BI-RADS ［J］.Scientific Reports,2019,9(1):11921.
［5］SUN W,LIU S,GUO J,et al.A CT-based radiomics nomogram for distinguishing between benign and malignant bone tumours ［J］.Cancer Imaging,2021,21(1):20.
［6］BRAMAN NM,ETESAMI M,PRASANNA P,et al.Intratumoral and peritumoral radiomics for the pretreatment prediction of pathological complete response to neoadjuvant chemotherapy based on breast DCE-MRI ［J］.Breast Cancer Research,2017,19(1):57.
［7］LI J,YIN H,WANG Y,et al.Multiparametric MRI-based radiomics nomogram for early prediction of pathological response to neoadjuvant chemotherapy in locally advanced gastric cancer ［J］.European Radiology,2023,33(4):2746-2756.
［8］CAIN EH,SAHA A,HAROWICZ MR,et al.Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features:a study using an independent validation set ［J］.Breast Cancer Res Treat,2019,173(2):455-463.
［9］LA K,MR S,LA C,et al.Neoadjuvant chemotherapy,endocrine therapy,and targeted therapy for breast cancer:ASCO guideline ［J］.Journal of Clinical Oncology,2021,39(13):1485-1505.
［10］SPAK DA,PLAXCO JS,SANTIAGO L,et al.BI-RADS() fifth edition:A summary of changes ［J］.Diagn Interv Imaging,2017,98(3):179-190.
［11］孙家宝,张蕾,崔浩,等.超声评估乳腺癌新辅助化疗后病理完全缓解的临床应用价值 ［J］.中华超声影像学杂志,2021,30(5):420-425. SUN JB,ZHANG L,CUI H,et al.Clinical application of ultrasound in evaluating pathologically complete response after neoadjuvant chemotherapy for breast cancer［J］.Chin J Ultrasonogr,2021,30(5):420-425.
［12］XU A,CHU X,ZHANG S,et al.Development and validation of a clinicoradiomic nomogram to assess the HER2 status of patients with invasive ductal carcinoma ［J］.BMC Cancer,2022,22(1):872.
［13］黄丹凤,唐丽娜,沈友洪,等.剪切波弹性成像预测乳腺癌新辅助化疗病理反应性的效能分析 ［J］.中华超声影像学杂志,2021,30(8):715-720. HUANG DF,TANG LN,SHEN YH,et al.Effect of shear wave elastography in predicting pathological responses to neoadjuvant chemotherapy in patients with breast cancer［J］.Chin J Ultrasonogr,2021,30(8):715-720.
［14］李雅婷,王丹丹,徐超丽,等.超声预测乳腺癌新辅助化疗病理完全缓解的临床价值 ［J］.中华超声影像学杂志,2021,30(12):1071-1076. LI YT,WANG DD,XU CL,et al.Value of ultrasound in predicting pathological complete response of breast cancer after neoadjuvant chemotherapy［J］.Chin J Ultrasonogr,2021,30(12):1071-1076.
［15］TANG Y,CHE X,WANG W,et al.Radiomics model based on features of axillary lymphatic nodes to predict axillary lymphatic node metastasis in breast cancer ［J］.Med Phys,2022,49(12):7555-7566.
［16］WU J,GONG G,CUI Y,et al.Intratumor partitioning and texture analysis of dynamic contrast-enhanced (DCE)-MRI identifies relevant tumor subregions to predict pathological response of breast cancer to neoadjuvant chemotherapy ［J］.Journal of Magnetic Resonance Imaging,2016,44(5):1107-1115.
［17］LI Q,JIANG T,ZHANG C,et al.A nomogram based on clinical information,conventional ultrasound and radiomics improves prediction of malignant parotid gland lesions ［J］.Cancer Letters,2022,527:107-114.
［18］PIOTRZKOWSKA-WROBLEWSKA H,DOBRUCH-SOBCZAK K,KLIMONDA Z,et al.Monitoring breast cancer response to neoadjuvant chemotherapy with ultrasound signal statistics and integrated backscatter ［J］.PLoS One,2019,14(3):e0213749.
［19］曲天宇,葛一涵,赵毅.乳腺癌患者新辅助化疗后病理完全缓解的相关影响因素分析及列线图预测模型的构建 ［J］.现代肿瘤医学,2021,29(04):590-594. QU TY,GE YH,ZHAO Y.Related factors analysis on breast cancer patients pathologic complete response after neoadjuvant therapy and establishment of a nomogram prediction model［J］.Modern Oncology,2021,29(04):590-594.

Memo

Memo:
山东省医药卫生科技发展计划项目（编号：202009020663）；山东省自然科学基金（编号：ZR2023MH348，ZR2023QH231）
Last Update: 1900-01-01