Literature DB >> 34647174

Predicting the molecular subtype of breast cancer and identifying interpretable imaging features using machine learning algorithms.

Mengwei Ma1, Renyi Liu1, Chanjuan Wen1, Weimin Xu1, Zeyuan Xu1, Sina Wang1, Jiefang Wu1, Derun Pan1, Bowen Zheng1, Genggeng Qin2, Weiguo Chen3.   

Abstract

OBJECTIVES: To evaluate the performance of interpretable machine learning models in predicting breast cancer molecular subtypes.
METHODS: We retrospectively enrolled 600 patients with invasive breast carcinoma between 2012 and 2019. The patients were randomly divided into a training (n = 450) and a testing (n = 150) set. The five constructed models were trained based on clinical characteristics and imaging features (mammography and ultrasonography). The model classification performances were evaluated using the area under the receiver operating characteristic (ROC) curve (AUC), accuracy, sensitivity, and specificity. Shapley additive explanation (SHAP) technique was used to interpret the optimal model output. Then we choose the optimal model as the assisted model to evaluate the performance of another four radiologists in predicting the molecular subtype of breast cancer with or without model assistance, according to mammography and ultrasound images.
RESULTS: The decision tree (DT) model performed the best in distinguishing triple-negative breast cancer (TNBC) from other breast cancer subtypes, yielding an AUC of 0.971; accuracy, 0.947; sensitivity, 0.905; and specificity, 0.941. The accuracy, sensitivity, and specificity of all radiologists in distinguishing TNBC from other molecular subtypes and Luminal breast cancer from other molecular subtypes have significantly improved with the assistance of DT model. In the diagnosis of TNBC versus other subtypes, the average sensitivity, average specificity, and average accuracy of less experienced and more experienced radiologists increased by 0.090, 0.125, 0.114, and 0.060, 0.090, 0.083, respectively. In the diagnosis of Luminal versus other subtypes, the average sensitivity, average specificity, and average accuracy of less experienced and more experienced radiologists increased by 0.084, 0.152, 0.159, and 0.020, 0.100, 0.048.
CONCLUSIONS: This study established an interpretable machine learning model to differentiate between breast cancer molecular subtypes, providing additional values for radiologists. KEY POINTS: • Interpretable machine learning model (MLM) could help clinicians and radiologists differentiate between breast cancer molecular subtypes. • The Shapley additive explanations (SHAP) technique can select important features for predicting the molecular subtypes of breast cancer from a large number of imaging signs. • Machine learning model can assist radiologists to evaluate the molecular subtype of breast cancer to some extent.
© 2021. European Society of Radiology.

Entities:  

Keywords:  BI-RADS; Computer-aided diagnosis; Interpretable machine learning; Mammography and ultrasonography; Molecular subtype breast cancer

Mesh:

Year:  2021        PMID: 34647174     DOI: 10.1007/s00330-021-08271-4

Source DB:  PubMed          Journal:  Eur Radiol        ISSN: 0938-7994            Impact factor:   7.034


  35 in total

Review 1.  Clinical management of breast cancer heterogeneity.

Authors:  Dimitrios Zardavas; Alexandre Irrthum; Charles Swanton; Martine Piccart
Journal:  Nat Rev Clin Oncol       Date:  2015-04-21       Impact factor: 66.675

Review 2.  Screening for breast cancer in 2018-what should we be doing today?

Authors:  J M Seely; T Alhassan
Journal:  Curr Oncol       Date:  2018-06-13       Impact factor: 3.677

Review 3.  Breast cancer.

Authors:  Nadia Harbeck; Michael Gnant
Journal:  Lancet       Date:  2016-11-17       Impact factor: 79.321

4.  The mammographic correlations of a new immunohistochemical classification of invasive breast cancer.

Authors:  S Taneja; A J Evans; E A Rakha; A R Green; G Ball; I O Ellis
Journal:  Clin Radiol       Date:  2008-08-21       Impact factor: 2.350

Review 5.  Breast cancer molecular subtypes in patients with locally advanced disease: impact on prognosis, patterns of recurrence, and response to therapy.

Authors:  Kathryn E Huber; Lisa A Carey; David E Wazer
Journal:  Semin Radiat Oncol       Date:  2009-10       Impact factor: 5.934

Review 6.  Screening for Breast Cancer.

Authors:  Bethany L Niell; Phoebe E Freer; Robert Jared Weinfurtner; Elizabeth Kagan Arleo; Jennifer S Drukteinis
Journal:  Radiol Clin North Am       Date:  2017-11       Impact factor: 2.303

Review 7.  Clinical Diagnosis and Management of Breast Cancer.

Authors:  Elizabeth S McDonald; Amy S Clark; Julia Tchou; Paul Zhang; Gary M Freedman
Journal:  J Nucl Med       Date:  2016-02       Impact factor: 10.057

8.  Strategies for subtypes--dealing with the diversity of breast cancer: highlights of the St. Gallen International Expert Consensus on the Primary Therapy of Early Breast Cancer 2011.

Authors:  A Goldhirsch; W C Wood; A S Coates; R D Gelber; B Thürlimann; H-J Senn
Journal:  Ann Oncol       Date:  2011-06-27       Impact factor: 32.976

Review 9.  Molecular characterization and targeted therapeutic approaches in breast cancer.

Authors:  Angela Toss; Massimo Cristofanilli
Journal:  Breast Cancer Res       Date:  2015-04-23       Impact factor: 6.466

10.  Predicting the molecular subtype of breast cancer based on mammography and ultrasound findings.

Authors:  S Rashmi; S Kamala; S Sudha Murthy; Swapna Kotha; Y Suhas Rao; K Veeraiah Chaudhary
Journal:  Indian J Radiol Imaging       Date:  2018 Jul-Sep
View more
  1 in total

1.  Artificial intelligence in oncologic imaging.

Authors:  Melissa M Chen; Admir Terzic; Anton S Becker; Jason M Johnson; Carol C Wu; Max Wintermark; Christoph Wald; Jia Wu
Journal:  Eur J Radiol Open       Date:  2022-09-29
  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.