Deep learning assisted detection of glaucomatous optic neuropathy and potential designs for a generalizable model

Ko, Yu Chieh; Wey, Shih Yu; Chen, Wei Ta; Chang, Yu Fan; Chen, Mei Ju; Chiou, Shih Hwa; Liu, Catherine Jui Ling; Lee, Chen‐Yi

doi:10.1371/journal.pone.0233079

Cited by 25 publications

(8 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used an ensemble approach by incorporating a support vector machine to identify discs with enlarged cup-to-disc ratio when the confidence score of the CNN classifier was less than 0.85. However, this approach is still limited by the overlapped distribution of cup-to-disc ratio among the healthy and glaucoma subjects [ 32 ]. Increasing the number and variability of the training images is a potential way to increase the generalizability of a DL model, but its effect reached plateau when using 60,000 or more training images in the DR model, and is suboptimal in glaucoma models [ 14 , 33 ].…”

Section: Discussionmentioning

confidence: 99%

Widen the Applicability of a Convolutional Neural-Network-Assisted Glaucoma Detection Algorithm of Limited Training Images across Different Datasets

Chen

et al. 2022

Biomedicines

Self Cite

View full text Add to dashboard Cite

Automated glaucoma detection using deep learning may increase the diagnostic rate of glaucoma to prevent blindness, but generalizable models are currently unavailable despite the use of huge training datasets. This study aims to evaluate the performance of a convolutional neural network (CNN) classifier trained with a limited number of high-quality fundus images in detecting glaucoma and methods to improve its performance across different datasets. A CNN classifier was constructed using EfficientNet B3 and 944 images collected from one medical center (core model) and externally validated using three datasets. The performance of the core model was compared with (1) the integrated model constructed by using all training images from the four datasets and (2) the dataset-specific model built by fine-tuning the core model with training images from the external datasets. The diagnostic accuracy of the core model was 95.62% but dropped to ranges of 52.5–80.0% on the external datasets. Dataset-specific models exhibited superior diagnostic performance on the external datasets compared to other models, with a diagnostic accuracy of 87.50–92.5%. The findings suggest that dataset-specific tuning of the core CNN classifier effectively improves its applicability across different datasets when increasing training images fails to achieve generalization.

show abstract

Section: Discussionmentioning

confidence: 99%

Widen the Applicability of a Convolutional Neural-Network-Assisted Glaucoma Detection Algorithm of Limited Training Images across Different Datasets

Chen

et al. 2022

Biomedicines

Self Cite

View full text Add to dashboard Cite

show abstract

“…Ko et al (32) evaluated and detected the performance of a CNN framework for vertical CDR (VCDR) classification using 944 fundus photographs, including 465 nonglaucomatous optic neuropathy (NGON) eyes and 479 glaucomatous optic neuropathy (GON) eyes. Based on stratified sampling, the images were divided into a training set consisting of 763 images and a test set consisting of 181 images.…”

Section: Segmentation Of the Optic Cup And The Optic Discmentioning

confidence: 99%

The use of deep learning technology for the detection of optic neuropathy

Li¹,

Wan²

2022

Quant Imaging Med Surg

View full text Add to dashboard Cite

“…Model [20]. The primary challenge of the development is applying neural networks in the feature extraction process.…”

Section: 21mentioning

confidence: 99%

Understanding and Visualization of Different Feature Extraction Processes in Glaucoma Detection

Krishna¹,

Nagamani²

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

In the recent years the usage of mobile phone is increased and it is the major reason for cause of vision loss in several people. The continuous usage increases pressure inside optic nerve head and it leads to glaucoma disease. Also, there are lot of other reasons which leads to the cause of glaucoma. The purpose of this paper is to determine the importance of feature extraction process in glaucoma detection and implementation of different techniques for extracting convenient features for training machine learning model using pre-processed OCT (Optical Coherence Tomography) images. The two major feature extraction techniques narrated in this paper are convolutional neural network (CNN) model-based feature extraction and image processing model-based feature extraction. A performance analysis was conducted to find best feature extraction technique and both techniques performed well.

show abstract

Deep learning assisted detection of glaucomatous optic neuropathy and potential designs for a generalizable model

Cited by 25 publications

References 23 publications

Widen the Applicability of a Convolutional Neural-Network-Assisted Glaucoma Detection Algorithm of Limited Training Images across Different Datasets

Widen the Applicability of a Convolutional Neural-Network-Assisted Glaucoma Detection Algorithm of Limited Training Images across Different Datasets

The use of deep learning technology for the detection of optic neuropathy

Understanding and Visualization of Different Feature Extraction Processes in Glaucoma Detection

Contact Info

Product

Resources

About