A major global cause of blindness, age-related macular degeneration (AMD) is characterized by progressive vision loss and frequently coexists with choroidal neovascularization (CNV), an aberrant development of blood vessels. Medical problems require the knowledge of physicians, but because neural networks are opaque, machine learning techniques have not been well received in the medical community. However, these techniques may be useful in the diagnosis of retinal disorders. Our research employs Deep Neural Network (DNN) technology to classify CNV from Optical Coherence Tomography (OCT) pictures in a unique manner. For timely intervention and treatment, we used well-tuned MobileNet and VGG19 models to guarantee precise CNV identification. Acknowledging reluctance in the medical com-munity toward machine learning, we tackled the need for accurate and comprehensible diagnosis. Through careful preprocessing of the data and the use of transfer learning on Convolutional Neural Network (CNN) models, such as VGG 19 and MobileNet, our methodology produced remarkable validation accuracies of 99.89% and 99.3% per respective. Our findings highlight the ability of improved deep neural networks to increase classification accuracy while simultaneously lowering processing demands. By aiding in the early detection and management of serious retinal disorders, this research advances reliable diagnostic instruments.
Skip Nav Destination
Article navigation
31 January 2025
INTERNATIONAL CONFERENCE ON ROBOTICS, AUTOMATION, AND INTELLIGENT COMPUTING: ICRAIC 2K24
18–19 May 2024
Pune, India
Research Article|
January 31 2025
Enhanced CNV classification in OCT images: Leveraging efficiently fine-tuned MobileNet and VGG19 models for choroidal neovascularization (CNV) detection
Jalpesh Vasa;
Jalpesh Vasa
a)
Smt. K. D. Patel Department of Information Technology (KDPIT), Chandubhai S. Patel Institute of Technology (CSPIT), Charotar University of Science and Technology (CHARUSAT)
, Changa-388421, Gujarat, India
a)Corresponding author: [email protected]
Search for other works by this author on:
Bimal Patel;
Bimal Patel
b)
Smt. K. D. Patel Department of Information Technology (KDPIT), Chandubhai S. Patel Institute of Technology (CSPIT), Charotar University of Science and Technology (CHARUSAT)
, Changa-388421, Gujarat, India
Search for other works by this author on:
Megha Goriya;
Megha Goriya
c)
Smt. K. D. Patel Department of Information Technology (KDPIT), Chandubhai S. Patel Institute of Technology (CSPIT), Charotar University of Science and Technology (CHARUSAT)
, Changa-388421, Gujarat, India
Search for other works by this author on:
Ayush Ghadiya;
Ayush Ghadiya
d)
Smt. K. D. Patel Department of Information Technology (KDPIT), Chandubhai S. Patel Institute of Technology (CSPIT), Charotar University of Science and Technology (CHARUSAT)
, Changa-388421, Gujarat, India
Search for other works by this author on:
Zeel Amrutiya
Zeel Amrutiya
e)
Smt. K. D. Patel Department of Information Technology (KDPIT), Chandubhai S. Patel Institute of Technology (CSPIT), Charotar University of Science and Technology (CHARUSAT)
, Changa-388421, Gujarat, India
Search for other works by this author on:
a)Corresponding author: [email protected]
AIP Conf. Proc. 3255, 020001 (2025)
Citation
Jalpesh Vasa, Bimal Patel, Megha Goriya, Ayush Ghadiya, Zeel Amrutiya; Enhanced CNV classification in OCT images: Leveraging efficiently fine-tuned MobileNet and VGG19 models for choroidal neovascularization (CNV) detection. AIP Conf. Proc. 31 January 2025; 3255 (1): 020001. https://doi.org/10.1063/5.0254209
Download citation file:
Pay-Per-View Access
$40.00
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
13
Views
Citing articles via
Inkjet- and flextrail-printing of silicon polymer-based inks for local passivating contacts
Zohreh Kiaee, Andreas Lösel, et al.
Design of a 100 MW solar power plant on wetland in Bangladesh
Apu Kowsar, Sumon Chandra Debnath, et al.
Effect of coupling agent type on the self-cleaning and anti-reflective behaviour of advance nanocoating for PV panels application
Taha Tareq Mohammed, Hadia Kadhim Judran, et al.
Related Content
Effects of pulsed ultrasound on the choroid and retina
J Acoust Soc Am (August 2005)
Transfer learning for efficient classification of grouper sound
J. Acoust. Soc. Am. (September 2020)
A deep learning approach for detection of neovascularization in fundus images using transfer learning
AIP Conf. Proc. (July 2024)
Deep learning with concatenate model to detect COVID-19 lung disease with CT scan images
AIP Conference Proceedings (March 2022)
A quantitative assay of neovascularization using high-frequency ultrasonic spectroscopy
J Acoust Soc Am (November 2013)