Grading Prenatal Hydronephrosis from Ultrasound Imaging Using Deep Convolutional Neural Networks

We evaluate the performance of a Deep Convolutional Neural Network in grading the severity of prenatal hydronephrosis (PHN), one of the most common congenital urological anomalies, from renal ultrasound images. We present results on a variety of classification tasks based on clinically defined grades of severity, including predictions of whether or not an ultrasound image represents a case that is at high risk for further complications requiring surgical intervention with approximately 80% accuracy. The prediction rates obtained by the model are well beyond the rates of agreement among trained clinicians, suggesting that this work can lead to a useful diagnostic aid.

[1]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[2]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[3]  Kourosh Afshar,et al.  Prediction of the outcome of antenatally diagnosed hydronephrosis: a multivariable analysis. , 2012, Journal of pediatric urology.

[4]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[5]  Tara N. Sainath,et al.  Improving deep neural networks for LVCSR using rectified linear units and dropout , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[6]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[7]  Rob Fergus,et al.  Learning from Noisy Labels with Deep Neural Networks , 2014, ICLR.

[8]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Dimitris Vassis,et al.  Using neural networks and SVMs for automatic medical diagnosis: A comprehensive review , 2015 .

[10]  R. F. Wagner,et al.  Statistics of Speckle in Ultrasound B-Scans , 1983, IEEE Transactions on Sonics and Ultrasonics.

[11]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[12]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[13]  Alison M Darcy,et al.  Machine Learning and the Profession of Medicine. , 2016, JAMA.

[14]  Gustavo Pérez,et al.  Automated detection of lung nodules with three-dimensional convolutional neural networks , 2017, Symposium on Medical Information Processing and Analysis.

[15]  Kjell Tullus,et al.  Febrile urinary tract infections in children. , 2011, The New England journal of medicine.

[16]  Ronald M. Summers,et al.  Deep Learning in Medical Imaging: Overview and Future Promise of an Exciting New Technique , 2016 .

[17]  Remco J. Renken,et al.  Classification of Parkinsonian Syndromes from FDG-PET Brain Data Using Decision Trees with SSM/PCA Features , 2015, Comput. Math. Methods Medicine.

[18]  Anam Tariq,et al.  Automated detection of exudates in colored retinal images for diagnosis of diabetic retinopathy. , 2012, Applied optics.

[19]  Chen Huang,et al.  Learning Deep Representation for Imbalanced Classification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Kun-Suk Kim,et al.  Is antibiotic prophylaxis necessary in infants with obstructive hydronephrosis? , 2007, The Journal of urology.

[21]  Michael I. Jordan,et al.  Machine learning: Trends, perspectives, and prospects , 2015, Science.

[22]  Mark D Cicero,et al.  Training and Validating a Deep Convolutional Neural Network for Computer-Aided Detection and Classification of Abnormalities on Frontal Chest Radiographs , 2017, Investigative radiology.

[23]  Richard S. Lee,et al.  The Society for Fetal Urology consensus statement on the evaluation and management of antenatal hydronephrosis. , 2010, Journal of pediatric urology.

[24]  M. Bouzada,et al.  Risk factors for urinary tract infection in children with prenatal renal pelvic dilatation. , 2008, The Journal of urology.

[25]  Jürgen Schmidhuber,et al.  Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[26]  Ramesh Babu,et al.  Postnatal outcome of fetal hydronephrosis: Implications for prenatal counselling , 2010, Indian journal of urology : IJU : journal of the Urological Society of India.

[27]  Patrice Y. Simard,et al.  Best practices for convolutional neural networks applied to visual document analysis , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[28]  K. Krippendorff.  Reliability in Content Analysis: Some Common Misconceptions and Recommendations , 2004 .

[29]  M. Woodward,et al.  Postnatal management of antenatal hydronephrosis , 2002, BJU international.

[30]  Armando J Lorenzo,et al.  Associations of Initial Society for Fetal Urology Grades and Urinary Tract Dilatation Risk Groups with Clinical Outcomes in Patients with Isolated Prenatal Hydronephrosis , 2017, The Journal of urology.

[31]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[32]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[33]  Honglak Lee,et al.  Learning hierarchical representations for face verification with convolutional deep belief networks , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[34]  Andrew Y. Ng,et al.  Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks , 2017, ArXiv.

[35]  Armando J Lorenzo,et al.  Six of one, half a dozen of the other: A measure of multidisciplinary inter/intra-rater reliability of the society for fetal urology and urinary tract dilation grading systems for hydronephrosis. , 2017, Journal of pediatric urology.

[36]  Tianqi Chen,et al.  Empirical Evaluation of Rectified Activations in Convolutional Network , 2015, ArXiv.

[37]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[38]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[39]  Yoni Donner,et al.  Fully Automating Graf's Method for DDH Diagnosis Using Deep Convolutional Neural Networks , 2016, LABELS/DLMIA@MICCAI.

[40]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[41]  Liva Ralaivola,et al.  Confusion Matrix Stability Bounds for Multiclass Classification , 2012, ArXiv.

[42]  R. F. Wagner,et al.  Fundamental correlation lengths of coherent speckle in medical ultrasonic images , 1988, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[43]  Shailendra Narayan Singh,et al.  A Review on the Strategies and Techniques of Image Segmentation , 2015, 2015 Fifth International Conference on Advanced Computing & Communication Technologies.

[44]  Scott T. Acton,et al.  Ultrasound Despeckling for Contrast Enhancement , 2010, IEEE Transactions on Image Processing.

[45]  Yi Yang,et al.  Long-term follow-up and management of prenatally detected, isolated hydronephrosis. , 2010, Journal of pediatric surgery.

[46]  Robert Koprowski,et al.  Machine learning, medical diagnosis, and biomedical engineering research - commentary , 2014, Biomedical engineering online.

[47]  M. Elif Karsligil,et al.  Classification of laryngeal disorders based on shape and vascular defects of vocal folds , 2015, Comput. Biol. Medicine.