Radiography Classification: A Comparison between Eleven Convolutional Neural Networks

Ananda,; Karabağ, Cefa; Ter-Sarkisov, Aram; Alonso, Eduardo; Reyes-Aldasoro, Constantino Carlos

doi:10.1109/mcna50957.2020.9264285

Cited by 7 publications

(7 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The architectures compared were the following: ( GoogleNet, VGG-19, AlexNet, SqueezeNet, ResNet-18, Inception-v3, ResNet-50, VGG-16, ResNet-101, DenseNet-201 and Inception-ResNet-v2 ). This paper extends a preliminary version of this work [ 58 ]. Here, we extended the work by applying data augmentation to the two models that provided the best results, that is, ResNet-50 and Inception-ResNet-v2.…”

Section: Introductionsupporting

confidence: 70%

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

Ananda

Ngan

Karabağ

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

This paper investigates the classification of radiographic images with eleven convolutional neural network (CNN) architectures (GoogleNet, VGG-19, AlexNet, SqueezeNet, ResNet-18, Inception-v3, ResNet-50, VGG-16, ResNet-101, DenseNet-201 and Inception-ResNet-v2). 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.

show abstract

Section: Introductionsupporting

confidence: 70%

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

Ananda

Ngan

Karabağ

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…The architectures compared were the following: (GoogleNet, VGG-19, AlexNet, SqueezeNet, . This paper extends a preliminary version of this work [58]. Here, we extended the work by applying data augmentation to the two models that provided the best results, that is, ResNet-50 and Inception-ResNet-v2.…”

Section: Introductionmentioning

confidence: 74%

Classification and Visualisation of Normal and Abnormal Radiographs; a comparison between Eleven Convolutional Neural Network Architectures

Ananda

Ngan

Karabağ

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

This paper investigates the classification of radiographic images with eleven convolutional neural network (CNN) architectures (GoogleNet, VGG-19, AlexNet, SqueezeNet, ResNet-18, Inception-v3, ResNet-50, VGG-16, ResNet-101, DenseNet-201 and Inception-ResNet-v2). 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.

show abstract

“…It gained prominence for its exceptional performance in image classification tasks, including glaucoma detection. VGG-16 has demonstrated the ability to learn and extract meaningful features from glaucoma images, leading to accurate classification results [ 40 , 41 ].…”

Section: Cnn In Glaucoma Diagnosismentioning

confidence: 99%

“…By concatenating the outputs of these parallel operations, Inception v3 enhances the network’s ability to learn discriminative features. In glaucoma diagnosis, Inception v3 has exhibited strong performance, achieving high accuracy in classifying glaucomatous and healthy images [ 41 ].…”

Section: Cnn In Glaucoma Diagnosismentioning

confidence: 99%

See 1 more Smart Citation

Advancing glaucoma detection with convolutional neural networks: a paradigm shift in ophthalmology

2023

rjo

View full text Add to dashboard Cite

A leading cause of irreversible vision loss, glaucoma needs early detection for effective management. Intraocular Pressure (IOP) is a significant risk factor for glaucoma. Convolutional Neural Networks (CNN) demonstrate exceptional capabilities in analyzing retinal fundus images, a non-invasive and cost-effective imaging technique widely used in glaucoma diagnosis. By learning from large datasets of annotated images, CNN can identify subtle changes in the optic nerve head and retinal structures indicative of glaucoma. This enables early and precise glaucoma diagnosis, empowering clinicians to implement timely interventions. CNNs excel in analyzing complex medical images, detecting subtle changes indicative of glaucoma with high precision. Another valuable diagnostic tool for glaucoma evaluation, Optical Coherence Tomography (OCT), provides high-resolution cross-sectional images of the retina. CNN can effectively analyze OCT scans and extract meaningful features, facilitating the identification of structural abnormalities associated with glaucoma. Visual field testing, performed using devices like the Humphrey Field Analyzer, is crucial for assessing functional vision loss in glaucoma. The integration of CNN with retinal fundus images, OCT scans, visual field testing, and IOP measurements represents a transformative approach to glaucoma detection. These advanced technologies have the potential to revolutionize ophthalmology by enabling early detection, personalized management, and improved patient outcomes. CNNs facilitate remote expert opinions and enhance treatment monitoring. Overcoming challenges such as data scarcity and interpretability can optimize CNN utilization in glaucoma diagnosis. Measuring retinal nerve fiber layer thickness as a diagnostic marker proves valuable. CNN implementation reduces healthcare costs and improves access to quality eye care. Future research should focus on optimizing architectures and incorporating novel biomarkers. CNN integration in glaucoma detection revolutionizes ophthalmology, improving patient outcomes and access to care. This review paves the way for innovative CNN-based glaucoma detection methods. Abbreviations: CNN = Convolutional Neural Networks, AI = Artificial Intelligence, IOP = Intraocular Pressure, OCT = Optical Coherence Tomography, CLSO = Confocal Scanning Laser Ophthalmoscopy, AUC-ROC = Area Under the Receiver Operating Characteristic Curve, RNFL = Retinal Nerve Fiber Layer, RNN = Recurrent Neural Networks, VF = Visual Field, AP = Average Precision, MD = Mean Defect, sLV = square-root of Loss Variance, NN = Neural Network, WHO = World Health Organization

show abstract

Radiography Classification: A Comparison between Eleven Convolutional Neural Networks

Cited by 7 publications

References 39 publications

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

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

Classification and Visualisation of Normal and Abnormal Radiographs; a comparison between Eleven Convolutional Neural Network Architectures

Advancing glaucoma detection with convolutional neural networks: a paradigm shift in ophthalmology

Contact Info

Product

Resources

About