We build a machine learning model that is able to detect abnormalities in X-ray images. We use the MURA dataset released by Stanford University in 2017 to train and evaluate our model. The dataset contains a total of 14,656 multi-view X-ray studies labeled as either normal or abnormal by professional radiologists. We train a binary Convolutional Neural Network classifier on this dataset and employ Class Activation Mappings to localize the abnormality on the X-ray image if found. Our model, an ensemble of DenseNet169 and ResNet50, obtains an accuracy of 0.844 and an AUROC of 0.836 on the test set. In this paper, we describe the methodologies that we used to train and evaluate the model and to extend the classifier into a detector
Chapters
Title |
Author |
Supervisor |
Degree |
Institute |
Title |
Author |
Supervisor |
Degree |
Institute |
Title |
Author |
Supervisor |
Degree |
Institute |
Title |
Author |
Supervisor |
Degree |
Institute |
Book |
Author(s) |
Year |
Publisher |
Book |
Author(s) |
Year |
Publisher |
Chapter |
Author(s) |
Book |
Book Authors |
Year |
Publisher |
Chapter |
Author(s) |
Book |
Book Authors |
Year |
Publisher |
Similar News
Headline |
Date |
News Paper |
Country |
Headline |
Date |
News Paper |
Country |
Similar Articles
Article Title |
Authors |
Journal |
Vol Info |
Language |
Article Title |
Authors |
Journal |
Vol Info |
Language |
Similar Article Headings
Heading |
Article Title |
Authors |
Journal |
Vol Info |
Heading |
Article Title |
Authors |
Journal |
Vol Info |