|Table of Contents|

Building a machine learning model based on SHAP interpretable analysis and MRI imageology to predict the efficacy of neoadjuvant chemotherapy for breast cancer

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

Issue:
2024 15
Page:
2839-2844
Research Field:
Publishing date:

Info

Title:
Building a machine learning model based on SHAP interpretable analysis and MRI imageology to predict the efficacy of neoadjuvant chemotherapy for breast cancer
Author(s):
ZHAO Ling1; CHEN Zhengguo1; LUO Rui1; YIN Longzhou1; ZHOU Li1; HUANG Yao2
1.Mianyang Hospital Affiliated to Medical School of University of Electronic Science and Technology，Mianyang Central Hospital，Sichuan Mianyang 621000，China;2.School of Medicine,Chongqing University,Chongqing 400030，China.
Keywords:
breast cancer; therapeutic effect prediction; neoadjuvant chemotherapy; machine learning
PACS:
R737.9
DOI:
10.3969/j.issn.1672-4992.2024.15.023
Abstract:
Objective:To explore the integration of SHAP interpretability analysis with MRI radiomics machine learning models to provide accurate and interpretable predictions for the efficacy of neoadjuvant chemotherapy in breast cancer patients.Methods:This study enrolled 60 breast cancer patients and analyzed their ER,PR,HER-2,and Ki-67 status.Key radiomic features were further selected,and an integrated clinical and radiomics model was constructed using XGBoost.The interpretability of the model was evaluated using SHAP analysis.Results:Significant differences were observed in ER,PR,and HER-2 status between pCR and Non-pCR patients,while no significant difference was noted for Ki-67.The integrated model achieved an AUC of 0.972 and an accuracy of 90.0%.SHAP analysis revealed that the importance of two radiomic features significantly surpassed that of HER-2 status.Conclusion:This study successfully established a highly accurate and interpretable predictive model for neoadjuvant chemotherapy by integrating SHAP with MRI radiomics,offering valuable insights for the clinical assessment of neoadjuvant chemotherapy in breast cancer patients.

References:

［1］PARK W,PARK S,SONG G,et al.Inhibitory effects of osthole on human breast cancer cell progression via induction of cell cycle arrest,mitochondrial dysfunction,and ER stress［J］.Nutrients,2019,11(11):2777.
［2］NAIR VA,VALO S,PELTOMAKI P,et al.Abdel-Rahman WM.Oncogenic potential of bisphenol A and common environmental contaminants in human mammary epithelial cells［J］.Int J Mol Sci,2020,21(10):3735.
［3］GRADISHAR WJ,ANDERSON BO,ABRAHAM J,et al.Breast cancer,version 3.2020,NCCN clinical practice guidelines in oncology［J］.J Natl Compr Canc Netw,2020,18(4):452-478.
［4］黄瑶,王晓霞,蒋富杰,等.基于纵向时间影像的深度学习在乳腺癌新辅助化疗疗效预测中的研究进展［J］.磁共振成像,2023,14(3):175-178,183. HUANG Y,WANG XX,JIANG FJ,et al.The research progress in predicting the efficacy of neoadjuvant chemotherapy for breast cancer according to longitudinal images-based deep learning［J］.Chinese Journal of Magnetic Resonance Imaging,2023,14(3):175-178,183.
［5］缑庆香,高晋南,王金桃.乳腺癌新辅助化疗病理完全缓解率及影响因素分析［J］.现代肿瘤医学,2024,32(3):472-476. GOU QX,GAO JN,WANG JT.Pathological complete response rate and influencing factors of neoadjuvant chemotherapy for breast cancer［J］.Modern Oncology,2024,32(3):472-476.
［6］CRIVELLI P,LEDDA RE,PARASCANDOLO N,et al.A new challenge for radiologists:Radiomics in breast cancer［J］.Biomed Res Int,2018,2018:6120703.
［7］LI H,MENDEL KR,LAN L,et al.Digital mammography in breast cancer:Additive value of radiomics of breast parenchyma［J］.Radiology,2019,291(1):15-20.
［8］杨蔚,张宁妹,张朝林,等.基于Shapley Additive Explanations(SHAP)分析乳腺X线检查假阴性乳腺癌的特征［J］.中国医学计算机成像杂志,2023,29(3):271-276. YANG W,ZHANG NM,ZHANG CL,et al.Study of features of false-negative mammography breast cancer based on the analysis of Shapley Additive Explanations(SHAP)［J］.Chinese Computed Medical Imaging,2023,29(3):271-276.
［9］LUNDBERG SM,NAIR B,VAVILALA MS,et al.Explainable machine-learning predictions for the prevention of hypoxaemia during surgery［J］.Nat Biomed Eng,2018,2(10):749-760.
［10］NAKAMURA K,KOJIMA R,UCHINO E,et al.Health improvement framework for actionable treatment planning using a surrogate Bayesian model［J］.Nat Commun,2021,12(1):3088.
［11］GU J,TONG T,HE C,et al.Deep learning radiomics of ultrasonography can predict response to neoadjuvant chemotherapy in breast cancer at an early stage of treatment:A prospective study［J］.Eur Radiol,2022,32(3):2099-2109.
［12］YUE H,LIU J,LI J,et al.MLDRL:Multi-loss disentangled representation learning for predicting esophageal cancer response to neoadjuvant chemoradiotherapy using longitudinal CT images［J］.Med Image Anal,2022,79:102423.
［13］ZWANENBURG A,VALLIERES M,ABDALAH MA,et al.The image biomarker standardization initiative:Standardized quantitative radiomics for high-throughput image-based phenotyping［J］.Radiology,2020,295(2):328-338.
［14］莫佳妮,赵慧.ER、PR、Her-2及Ki-67在乳腺癌患者新辅助化疗后表达情况及意义分析［J］.现代诊断与治疗,2023,34(1):8-10. MO JN,ZHAO H.Expression and significance of ER，PR，Her-2 and Ki-67 in breast cancer patients after neoadjuvant chemotherapy［J］.Modern Diagnosis and Treatment,2023,34(1):8-10.
［15］LI Z,WEI H,LI S,et al.The role of progesterone receptors in breast cancer［J］.Drug Des Devel Ther,2022,16:305-314.
［16］杨丽，何建信，张春霞，等.HER-2阳性型浸润性乳腺癌新辅助化疗后肿瘤退缩模式及影响因素［J］.现代肿瘤医学，2022，30(2):226-229. YANG L,HE JX,ZHANG CX,et al.The pattern of tumor regression after neoadjuvant chemotherapy for HER-2 positive invasive breast cancer and its influencing factors［J］.Modern Oncology，2022，30(2):226-229.
［17］党少华，徐敏，胡金月，等.HER-2阳性乳腺癌患者新辅助化疗联合曲妥珠单抗治疗的影响因素及预后分析［J］.现代肿瘤医学，2021，29(15):2620-2624. DANG SH,XU M,HU JY,et al.Prognosis and influencing factors of neoadjuvant chemotherapy combined with trastuzumab in breast cancer patients with positive HER-2［J］.Modern Oncology，2021，29(15):2620-2624.
［18］陈淑銮,车树楠,李静.MRI及影像组学评估不同分子亚型乳腺癌新辅助治疗疗效的研究进展［J］.磁共振成像,2023,14(6):156-160. CHEN SL,CHE SN,LI J.Progress of MRI and radiomics in predicting the response to neoadjuvant therapy for breast cancer in different molecular subtypes［J］.Chinese Journal of Magnetic Resonance Imaging,2023,14(6):156-160.

Memo

Memo:
2023年重庆市研究生科研创新项目（编号：CYB23070）
Last Update: 2024-06-28