Classification and Visualisation of Normal and Abnormal Radiographs; A Comparison between Eleven Convolutional Neural Network Architectures.

Sensors (Basel)

giCentre, Department of Computer Science, School of Mathematics, Computer Science and Engineering, City, University of London, London EC1V 0HB, UK.

Published: August 2021

This paper investigates the classification of radiographic images with eleven convolutional neural network (CNN) architectures (). The CNNs were used to classify a series of wrist radiographs from the Stanford Musculoskeletal Radiographs (MURA) dataset into two classes-normal and abnormal. The architectures were compared for different hyper-parameters against accuracy and Cohen's kappa coefficient. The best two results were then explored with data augmentation. Without the use of augmentation, the best results were provided by Inception-ResNet-v2 (Mean accuracy = 0.723, Mean kappa = 0.506). These were significantly improved with augmentation to Inception-ResNet-v2 (Mean accuracy = 0.857, Mean kappa = 0.703). Finally, Class Activation Mapping was applied to interpret activation of the network against the location of an anomaly in the radiographs.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8400172PMC
http://dx.doi.org/10.3390/s21165381DOI Listing

Publication Analysis

Top Keywords

eleven convolutional
8
convolutional neural
8
neural network
8
inception-resnet-v2 accuracy
8
classification visualisation
4
visualisation normal
4
normal abnormal
4
radiographs
4
abnormal radiographs
4
radiographs comparison
4

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!