Abstract
Age-related macular degeneration (AMD) is the main cause of irreversible blindness among the elderly and require early diagnosis to prevent vision loss, and careful treatment is essential. Optical coherence tomography (OCT), the most commonly used imaging method in the retinal area for the diagnosis of AMD, is usually interpreted by a clinician, and OCT can help diagnose disease on the basis of the relevant diagnostic criteria, but these judgments can be somewhat subjective. We propose an algorithm for the detection of AMD based on a weakly supervised convolutional neural network (CNN) model to support computer-aided diagnosis (CAD) system. Our main contributions are the following three things. (1) We propose a concise CNN model for OCT images, which outperforms the existing large CNN models using VGG16 and GoogLeNet architectures. (2) We propose an algorithm called Expressive Gradients (EG) that extends the existing Integrated Gradients (IG) algorithm so as to exploit not only the input-level attribution map, but also the high-level attribution maps. Due to enriched gradients, EG can highlight suspicious regions for diagnosis of AMD better than the guided-backpropagation method and IG. (3) Our method provides two visualization options: overlay and top-k bounding boxes, which would be useful for CAD. Through experimental evaluation using 10,100 clinical OCT images from AMD patients, we demonstrate that our EG algorithm outperforms the IG algorithm in terms of localization accuracy and also outperforms the existing object detection methods in terms of class accuracy.
Highlights
Deep learning is of growing importance in many applications, such as image recognition and image localization
We have proposed a weakly supervised deep learning-based method for predicting the class of Age-related macular degeneration (AMD) and locating its lesions in Optical coherence tomography (OCT) images
Our proposed convolutional neural network (CNN) model for OCT images achieves a higher accuracy for AMD detection than the existing large CNN models
Summary
Deep learning is of growing importance in many applications, such as image recognition and image localization. The deep learning-based methods, [6] and [7], have utilized well-known convolutional neural network (CNN) models, VGG16 [10] and GoogLeNet [11], and achieved the accuracies of 93.45% and 94%, respectively They only can do prediction, but cannot localize suspected AMD lesions in OCT images and so might not be very useful as a CAD system. Supervised lesion localization for AMD detection using OCT images maps in the images having relatively small amount of information (e.g., OCT images) As a result, it can localize the lesions better than the conventional guided-backpropagation method and the IG algorithm, which are exploiting only the gradients with respect to input image, for OCT images. For all the models in [6,7,8], we modified their output layer such that they can predict four classes instead of two
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
