Deep Convolutional Neural Network-Based Automatic Classification of Neonatal Hip Ultrasound Images: A Novel Data Augmentation Approach with Speckle Noise Reduction

Neonatal hip ultrasound imaging has been widely used for a few decades in the diagnosis of developmental dysplasia of the hip (DDH). Graf's method of hip ultrasonography is still the most reproducible because of its classification system; yet, the reproducibility is questionable as a result of the high dependency on the skills of the sonographer and the evaluator. A computer-aided diagnosis system may help evaluators increase their precision in the diagnosis of DDH using Graf's method. This study describes a fully automatic computer-aided diagnosis system for the classification of hip ultrasound images captured in Graf's standard plane based on convolutional neural networks (CNNs). Automatically segmented image patches containing all of the necessary anatomical structures were given to the proposed CNN system to extract discriminative features and classify the recorded hips. For ease of evaluation, the data set was divided into three groups: normal, mild dysplasia and severe dysplasia. This study proposes a different approach to data augmentation using speckle noise reduction with an optimized Bayesian non-local mean filter. Data augmentation with this filter increased the accuracy of the proposed CNN system from 92.29% to 97.70%. This new approach for automatic classification of DDH, classifies dysplastic neonatal hips with a high accuracy rate and might help evaluators to increase their evaluation success.