Advertisement

Application of Deep Learning to Reduce the Rate of Malignancy Among BI-RADS 4A Breast Lesions Based on Ultrasonography

  • Author Footnotes
    1 These authors contributed equally.
    Zhijin Zhao
    Footnotes
    1 These authors contributed equally.
    Affiliations
    Department of Medical Ultrasound, Fudan University Shanghai Cancer Center, Shanghai, China

    Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, China
    Search for articles by this author
  • Author Footnotes
    1 These authors contributed equally.
    Size Hou
    Footnotes
    1 These authors contributed equally.
    Affiliations
    Department of Applied Mathematics, School of Science, Xi'an Jiaotong-Liverpool University, Suzhou, China
    Search for articles by this author
  • Shuang Li
    Affiliations
    International Business School Suzhou, Xi'an Jiaotong-Liverpool University, Suzhou, China
    Search for articles by this author
  • Danli Sheng
    Affiliations
    Department of Medical Ultrasound, Fudan University Shanghai Cancer Center, Shanghai, China

    Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, China
    Search for articles by this author
  • Qi Liu
    Affiliations
    Department of Medical Ultrasound, Fudan University Shanghai Cancer Center, Shanghai, China

    Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, China
    Search for articles by this author
  • Cai Chang
    Affiliations
    Department of Medical Ultrasound, Fudan University Shanghai Cancer Center, Shanghai, China

    Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, China
    Search for articles by this author
  • Jiangang Chen
    Correspondence
    Address correspondence to: Jiangang Chen, 500 Dongchuan Road, Shanghai, China.
    Affiliations
    Shanghai Key Laboratory of Multidimensional Information Processing, School of Communication & Electronic Engineering, East China Normal University, Shanghai, China

    Engineering Research Center of Traditional Chinese Medicine Intelligent Rehabilitation, Ministry of Education, Shanghai, China
    Search for articles by this author
  • Jiawei Li
    Correspondence
    Address correspondence to: Jiawei Li, 270 Dongan Road, Shanghai, China.
    Affiliations
    Department of Medical Ultrasound, Fudan University Shanghai Cancer Center, Shanghai, China

    Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, China
    Search for articles by this author
  • Author Footnotes
    1 These authors contributed equally.

      Abstract

      The aim of the work described here was to develop an ultrasound (US) image–based deep learning model to reduce the rate of malignancy among breast lesions diagnosed as category 4A of the Breast Imaging-Reporting and Data System (BI-RADS) during the pre-operative US examination. A total of 479 breast lesions diagnosed as BI-RADS 4A in pre-operative US examination were enrolled. There were 362 benign lesions and 117 malignant lesions confirmed by postoperative pathology with a malignancy rate of 24.4%. US images were collected from the database server. They were then randomly divided into training and testing cohorts at a ratio of 4:1. To correctly classify malignant and benign tumors diagnosed as BI-RADS 4A in US, four deep learning models, including MobileNet, DenseNet121, Xception and Inception V3, were developed. The performance of deep learning models was compared using the area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV). Meanwhile, the robustness of the models was evaluated by five-fold cross-validation. Among the four models, the MobileNet model turned to be the optimal model with the best performance in classifying benign and malignant lesions among BI-RADS 4A breast lesions. The AUROC, accuracy, sensitivity, specificity, PPV and NPV of the optimal model in the testing cohort were 0.897, 0.913, 0.926, 0.899, 0.958 and 0.784, respectively. About 14.4% of patients were expected to be upgraded to BI-RADS 4B in US with the assistance of the MobileNet model. The deep learning model MobileNet can help to reduce the rate of malignancy among BI-RADS 4A breast lesions in pre-operative US examinations, which is valuable to clinicians in tailoring treatment for suspicious breast lesions identified on US.

      Key Words

      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Ultrasound in Medicine and Biology
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Conti A
        • Duggento A
        • Indovina I
        • Guerrisi M
        • Toschi N.
        Radiomics in breast cancer classification and prediction.
        Semin Cancer Biol. 2021; 72: 238-250
        • Dogan BE
        • Gonzalez-Angulo AM
        • Gilcrease M
        • Dryden MJ
        • Yang WT.
        Multimodality imaging of triple receptor-negative tumors with mammography, ultrasound, and MRI.
        AJR Am J Roentgenol. 2010; 194: 1160-1166
        • Ferlay J
        • Colombet M
        • Soerjomataram I
        • Parkin DM
        • Pineros M
        • Znaor A
        • Bray F.
        Cancer statistics for the year 2020: An overview.
        Int J Cancer. 2021; (Published online April 5)https://doi.org/10.1002/ijc.33588
        • Fleury E
        • Marcomini K.
        Performance of machine learning software to classify breast lesions using BI-RADS radiomic features on ultrasound images.
        Eur Radiol Exp. 2019; 3: 34
        • Ha EJ
        • Baek JH.
        Applications of machine learning and deep learning to thyroid imaging: Where do we stand?.
        Ultrasonography. 2021; 40: 23-29
        • Hu XC
        • Loo WT
        • Chow LW.
        Surgery-related shedding of breast cancer cells as determined by RT-PCR assay.
        J Surg Oncol. 2003; 82 (discussion 233): 228-232
        • Isik A
        • Isik N
        • Kurnaz E.
        Complete breast autoamputation: Clinical image.
        Breast J. 2020; 26: 2265-2266
        • Ismail MS
        • Wynendaele W
        • Aerts JL
        • Paridaens R
        • Gaafar R
        • Shakankiry N
        • Khaled HM
        • Christiaens MR
        • Wildiers H
        • Omar S
        • Vandekerckhove P
        • Van Oosterom AT.
        Detection of micrometastatic disease and monitoring of perioperative tumor cell dissemination in primary operable breast cancer patients using real-time quantitative reverse transcription-PCR.
        Clinical Cancer Res. 2004; 10: 196-201
        • Koh J
        • Kim EK
        • Kim MJ
        • Yoon JH
        • Park VY
        • Moon HJ.
        Role of elastography for downgrading BI-RADS category 4a breast lesions according to risk factors.
        Acta Radiol. 2019; 60: 278-285
        • Lee SE
        • Han K
        • Kwak JY
        • Lee E
        • Kim EK.
        Radiomics of US texture features in differential diagnosis between triple-negative breast cancer and fibroadenoma.
        Sci Rep. 2018; 8: 13546
        • Li DD
        • Xu HX
        • Guo LH
        • Bo XW
        • Li XL
        • Wu R
        • Xu JM
        • Zhang YF
        • Zhang K.
        Combination of two-dimensional shear wave elastography with ultrasound breast imaging reporting and data system in the diagnosis of breast lesions: A new method to increase the diagnostic performance.
        Eur Radiol. 2016; 26: 3290-3300
        • Li S
        • Yan W
        • Yang X
        • Chen L
        • Fan L
        • Liu H
        • Liu K
        • Zhang Y
        • Jiang J.
        Less micrometastatic risk related to circulating tumor cells after endoscopic breast cancer surgery compared to open surgery.
        BMC Cancer. 2019; 19: 1070
        • Lian J
        • Li K.
        A review of breast density implications and breast cancer screening.
        Clin Breast Cancer. 2020; 20: 283-290
        • Mei H
        • Xu J
        • Yao G
        • Wang Y.
        The diagnostic value of MRI for architectural distortion categorized as BI-RADS category 3-4 by mammography.
        Gland Surg. 2020; 9: 1008-1018
        • Mendelson EB
        • Böhm-Vélez M
        • Berg WA
        • Whitman GJ
        • Feldman MI
        • Madjar H
        • Rizzatto G
        • Baker JA
        • Zuley M
        • Stavros AT
        • Comstock C
        • Van Duyn Wear V
        ACR BI-RADS Ultrasound. ACR BI-RADS Atlas, Breast Imaging Reporting and Data System.
        5th edition. American College of Radiology, Reston, VA2013
        • Mercado CL.
        BI-RADS update.
        Radiol Clin North Am. 2014; 52: 481-487
        • Munir K
        • Elahi H
        • Ayub A
        • Frezza F
        • Rizzi A.
        Cancer diagnosis using deep learning: A bibliographic review.
        Cancers (Basel). 2019; 11: 1235
        • Niu S
        • Huang J
        • Li J
        • Liu X
        • Wang D
        • Zhang R
        • Wang Y
        • Shen H
        • Qi M
        • Xiao Y
        • Guan M
        • Liu H
        • Li D
        • Liu F
        • Wang X
        • Xiong Y
        • Gao S
        • Wang X
        • Zhu J.
        Application of ultrasound artificial intelligence in the differential diagnosis between benign and malignant breast lesions of BI-RADS 4A.
        BMC Cancer. 2020; 20: 959
        • Qian L
        • Lv Z
        • Zhang K
        • Wang K
        • Zhu Q
        • Zhou S
        • Chang C
        • Tian J.
        Application of deep learning to predict underestimation in ductal carcinoma in situ of the breast with ultrasound.
        Ann Transl Med. 2021; 9: 295
        • Sandler M
        • Howard A
        • Zhu M
        • Zhmoginov A
        • Chen LC.
        MobileNetV2: Inverted residuals and linear bottlenecks.
        in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, Piscataway, NJ2018: 4510-4520
        • Shang J
        • Ruan LT
        • Wang YY
        • Zhang XJ
        • Dang Y
        • Liu B
        • Wang WL
        • Song Y
        • Chang SJ.
        Utilizing size-based thresholds of stiffness gradient to reclassify BI-RADS category 3-4b lesions increases diagnostic performance.
        Clin Radiol. 2019; 74: 306-313
        • Shia WC
        • Lin LS
        • Chen DR.
        Classification of malignant tumours in breast ultrasound using unsupervised machine learning approaches.
        Sci Rep. 2021; 11: 1418
        • Stavros AT
        • Freitas AG
        • deMello GGN
        • Barke L
        • McDonald D
        • Kaske T
        • Wolverton D
        • Honick A
        • Stanzani D
        • Padovan AH
        • Moura APC
        • de Campos MCV
        Ultrasound positive predictive values by BI-RADS categories 3-5 for solid masses: An independent reader study.
        Eur Radiol. 2017; 27: 4307-4315
        • Tagliafico AS
        • Piana M
        • Schenone D
        • Lai R
        • Massone AM
        • Houssami N.
        Overview of radiomics in breast cancer diagnosis and prognostication.
        Breast. 2020; 49: 74-80
        • Valdora F
        • Houssami N
        • Rossi F
        • Calabrese M
        • Tagliafico AS.
        Rapid review: Radiomics and breast cancer.
        Breast Cancer Res Treat. 2018; 169: 217-229
        • Weismann C.
        Ultrasound elastography techniques in breast cancer.
        Radiologe. 2021; 61: 170-176
        • Zhang X
        • Li H
        • Wang C
        • Cheng W
        • Zhu Y
        • Li D
        • Jing H
        • Li S
        • Hou J
        • Li J
        • Li Y
        • Zhao Y
        • Mo H
        • Pang D.
        Evaluating the accuracy of breast cancer and molecular subtype diagnosis by ultrasound image deep learning model.
        Front Oncol. 2021; 11623506
        • Zheng X
        • Huang Y
        • Wang Y
        • Liu Y
        • Li F
        • Han J
        • Wang J
        • Cao L
        • Zhou J.
        Combination of different types of elastography in downgrading ultrasound Breast Imaging-Reporting and Data System category 4a breast lesions.
        Breast Cancer Res Treat. 2019; 174: 423-432
        • Zheng X
        • Yao Z
        • Huang Y
        • Yu Y
        • Wang Y
        • Liu Y
        • Mao R
        • Li F
        • Xiao Y
        • Wang Y
        • Hu Y
        • Yu J
        • Zhou J.
        Deep learning radiomics can predict axillary lymph node status in early-stage breast cancer.
        Nat Commun. 2020; 11: 1236
        • Zhou H
        • Jin Y
        • Dai L
        • Zhang M
        • Qiu Y
        • Wang K
        • Tian J
        • Zheng J.
        Differential diagnosis of benign and malignant thyroid nodules using deep learning radiomics of thyroid ultrasound images.
        Eur J Radiol. 2020; 127108992
        • Zhou LQ
        • Wu XL
        • Huang SY
        • Wu GG
        • Ye HR
        • Wei Q
        • Bao LY
        • Deng YB
        • Li XR
        • Cui XW
        • Dietrich CF.
        Lymph node metastasis prediction from primary breast cancer US images using deep learning.
        Radiology. 2020; 294: 19-28
        • Zhou BY
        • Wang LF
        • Yin HH
        • Wu TF
        • Ren TT
        • Peng C
        • Li DX
        • Shi H
        • Sun LP
        • Zhao CK
        • Xu HX.
        Decoding the molecular subtypes of breast cancer seen on multimodal ultrasound images using an assembled convolutional neural network model: A prospective and multicentre study.
        eBioMedicine. 2021; 74103684