Advertisement

Multi-instance Deep Learning of Ultrasound Imaging Data for Pattern Classification of Congenital Abnormalities of the Kidney and Urinary Tract in Children

  • Shi Yin
    Affiliations
    School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China

    Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA
    Search for articles by this author
  • Qinmu Peng
    Affiliations
    School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China
    Search for articles by this author
  • Hongming Li
    Affiliations
    Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA
    Search for articles by this author
  • Zhengqiang Zhang
    Affiliations
    School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China
    Search for articles by this author
  • Xinge You
    Affiliations
    School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China
    Search for articles by this author
  • Katherine Fischer
    Affiliations
    Department of Surgery, Division of Pediatric Urology, The Children's Hospital of Philadelphia, Philadelphia, PA

    Center for Pediatric Clinical Effectiveness, The Children's Hospital of Philadelphia, Philadelphia, PA
    Search for articles by this author
  • Susan L. Furth
    Affiliations
    Department of Pediatrics, Division of Pediatric Nephrology, The Children's Hospital of Philadelphia, Philadelphia, PA
    Search for articles by this author
  • Yong Fan
    Correspondence
    Address correspondence to: Yong Fan, Ph.D., Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Richards Building, 7th Floor, 3700 Hamilton Walk, Philadelphia, PA 19104.
    Affiliations
    Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA
    Search for articles by this author
  • Gregory E. Tasian
    Affiliations
    Department of Surgery, Division of Pediatric Urology, The Children's Hospital of Philadelphia, Philadelphia, PA

    Center for Pediatric Clinical Effectiveness, The Children's Hospital of Philadelphia, Philadelphia, PA

    Department of Biostatistics, Epidemiology, and Informatics, The University of Pennsylvania, Philadelphia, PA
    Search for articles by this author

      Abstract

      OBJECTIVE

      To reliably and quickly diagnose children with posterior urethral valves (PUV), we developed a multi-instance deep learning method to automate image analysis.

      METHODS

      We built a robust pattern classifier to distinguish 86 children with PUV from 71 children with mild unilateral hydronephrosis based on ultrasound images (3504 in sagittal view and 2558 in transverse view) obtained during routine clinical care.

      RESULTS

      The multi-instance deep learning classifier performed better than classifiers built on either single sagittal images or single transverse images. Particularly, the deep learning classifiers built on single images in the sagittal view and single images in the transverse view obtained area under the receiver operating characteristic curve (AUC) values of 0.796 ± 0.064 and 0.815 ± 0.071, respectively. AUC values of the multi-instance deep learning classifiers built on images in the sagittal and transverse views with mean pooling operation were 0.949 ± 0.035 and 0.954 ± 0.033, respectively. The multi-instance deep learning classifiers built on images in both the sagittal and transverse views with a mean pooling operation obtained an AUC of 0.961 ± 0.026 with a classification rate of 0.925 ± 0.060, specificity of 0.986 ± 0.032, and sensitivity of 0.873 ± 0.120, respectively. Discriminative regions of the kidney located using classification activation mapping demonstrated that the deep learning techniques could identify meaningful anatomical features from ultrasound images.

      CONCLUSION

      The multi-instance deep learning method provides an automatic and accurate means to extract informative features from ultrasound images and discriminate infants with PUV from male children with unilateral hydronephrosis.
      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 Urology
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Dodson JL
        • Jerry-Fluker JV
        • Ng DK
        • et al.
        Urological disorders in chronic kidney disease in children cohort: clinical characteristics and estimation of glomerular filtration rate.
        J Urol. 2011; 186: 1460-1466
        • Wiesel A
        • Queisser-Luft A
        • Clementi M
        • Bianca S
        • Stoll C
        Prenatal detection of congenital renal malformations by fetal ultrasonographic examination: an analysis of 709,030 births in 12 European Countries.
        Eur J Med Genet. 2005; 48: 131-144
        • Richter-Rodier M
        • Lange AE
        • Hinken B
        • et al.
        Ultrasound screening strategies for the diagnosis of congenital anomalies of the kidney and urinary tract.
        Ultraschall in Med. 2012; 33: E333-E338
        • Hálek J
        • Flögelová H
        • Michálková K
        • et al.
        Diagnostic accuracy of postnatal ultrasound screening for urinary tract abnormalities.
        Pediatr Nephrol. 2009; 25: 281
        • Nelson CP
        • Lee RS
        • Trout AT
        • et al.
        Interobserver and intra-observer reliability of the urinary tract dilation classification system in neonates: a mlticenter study.
        J Urol. 2019; 201: 1186-1192
        • Sharma K
        • Virmani J
        A decision support system for classification of normal and medical renal disease using ultrasound images: a decision support system for medical renal diseases.
        Int J Ambient Comput. 2017; 8: 52-69
        • Attia MW
        • Abou-Chadi FEZ
        • Moustafa HE
        • Mekky N
        Classification of ultrasound kidney images using PCA and neural networks.
        Int J Adv Comput Sc. 2015; 6: 53-57
        • Li H
        • Zhong H
        • Boimel PJ
        • Ben-Josef E
        • Xiao Y
        • Fan Y
        Deep convolutional neural networks for imaging based survival analysis of rectal cancer patients.
        Int J Radiat Oncol Biol Phys. 2017; 99: S183
        • Li H
        • Habes M
        • Wolk DA
        • Fan Y
        A deep learning model for early prediction of Alzheimer's disease dementia based on hippocampal magnetic resonance imaging data.
        Alzheimer's Dementia. 2019; 15: 1059-1070
        • Zheng Q
        • Tasian G
        • Fan Y
        Transfer learning for diagnosis of congenital abnormalities of the kidney and urinary tract in children based on ultrasound imaging data.
        in: Proceedings of IEEE 15th International Symposium on Biomedical Imaging. 2018: 1487-1490
        • Zheng Q
        • Furth SL
        • Tasian GE
        • Fan Y
        Computer-aided diagnosis of congenital abnormalities of the kidney and urinary tract in children based on ultrasound imaging data by integrating texture image features and deep transfer learning image features.
        J Pediatr Urol. 2019; 15: 75.e71-75.e77
        • Amores J
        Multiple instance classification: review, taxonomy and comparative study.
        Artif Intell. 2013; 201: 81-105
        • Zaheer M
        • Kottur S
        • Ravanbakhsh S
        • Poczos B
        • Salakhutdinov RR
        • Smola AJ
        Deep sets.
        Proc Adv Neural Inf Process Syst. 2017; : 3391-3401
        • Yin S
        • Peng Q
        • Li H
        • et al.
        Automatic kidney segmentation in ultrasound images using subsequent boundary distance regression and pixelwise classification networks.
        Med Image Anal. 2020; 60: 1-14
        • Yin S
        • Zhang Z
        • Li H
        • et al.
        Fully-automatic segmentation of kidneys in clinical ultrasound images using a boundary distance regression network.
        in: Proceedings of IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019). Venice, Italy. 2019: 1741-1744
        • Karen Simonyan AZ
        Very deep convolutional networks for large-scale image recognition.
        arXiv:1409.1556. 2014;
        • He K
        • Zhang X
        • Ren S
        • Sun J
        Deep residual learning for image recognition.
        Proc Comput Vis Pattern Recogn. 2016; : 770-778
        • Szegedy C
        • Ioffe S
        • Vanhoucke V
        • Alemi AA
        Inception-v4, inception-ResNet and the impact of residual connections on learning.
        in: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence. 2017: 4278-4284
        • Pulido JE
        • Furth SL
        • Zderic SA
        • Canning DA
        • Tasian GE
        Renal parenchymal area and risk of ESRD in boys with posterior urethral valves.
        Clin J Am Soc Nephrol. 2014; 9: 499-505
        • Rickard M
        • Lorenzo AJ
        • Braga LH
        • Munoz C
        Parenchyma-to-hydronephrosis area ratio is a promising outcome measure to quantify upper tract changes in infants with high-grade prenatal hydronephrosis.
        Urology. 2017; 104: 166-171
        • O'Neill WC
        Renal relevant radiology: use of ultrasound in kidney disease and nephrology procedures.
        Clin J Am Soc Nephrol: CJASN. 2014; 9: 373-381
        • Yin Shi
        • Qinmu Peng
        • Hongming Li
        • et al.
        Computer-Aided Diagnosis of Congenital Abnormalities of the Kidney and Urinary Tract in Children Using a Multi-Instance Deep Learning Method Based on Ultrasound Imaging Data.
        IEEE 17th International Symposium on Biomedical Imaging (ISBI). 2020; : 1347-1350https://doi.org/10.1109/ISBI45749.2020.9098506