Mithun Ghosh
Sahil Hassan
Prama Debnath
Abstract
The Musculoskeletal Radiographs (MURA) dataset, proposed by Stamford Machine Learning (ML) group, contains 40,561 images of bone X-rays from 14,863 studies. The X-ray images belong to seven body areas of the upper extremity- wrist, elbow, finger, humerus, forearm, hand, and shoulder. Radiologists have classified the data into two classes, namely normal and abnormal. Six board-certified Stanford radiologists labeled the data samples using majority votes, which is considered the gold standard. The 169 layers deep model, introduced by the Stamford ML group, works well on a par with the gold standard except
for the humerus radiographs, despite humerus data labeled with high accuracy. We propose to develop a comparatively shallower version of a neural network and a convolutional network with 10 hidden layers each in an Adaboost framework in the humerus data and the model performance is on par or sometimes superior to the Stamford ML group model. We evaluate the performance of the model using the validation error and Cohen’s kappa coefficients. We have shown that our modeling
framework is much faster in terms of the training time of the model and as accurate compared to the deep neural network introduced by the Stamford ML group. Also, with increased resources, our model will perform much better.
Keywords
Neural Network;
Convolution Neural Network;
Image classification;
Kappa coefficient;
Adaboost learning.
