Segmentation of Choroidal Area in Optical Coherence Tomography Images Using a Transfer Learning-Based Conventional Neural Network: A Focus on Diabetic Retinopathy and a Literature Review

Segmentation of Choroidal Area in Optical Coherence Tomography Images Using a Transfer Learning-Based Conventional Neural Network: A Focus on Diabetic Retinopathy and a Literature Review Publisher Pubmed

Saeidian J¹ ; Azimi H¹ ; Azimi Z² ; Pouya P³ ; Asadigandomani H⁴ ; Riaziesfahani H⁴ ; Hayati A⁵ ; Daneshvar K⁴ ; Khalili Pour E⁴

Show Affiliations

1. Faculty of Mathematical Sciences and Computer, Kharazmi University, No. 50, Taleghani Avenue, Tehran, Iran
2. Department of Mathematics, Faculty of Science, Arak University, Arak, Iran
3. Student Research Committee, Tabriz University of Medical Sciences, Tabriz, Iran
4. Retina Service, Farabi Eye Hospital, Tehran University of Medical Sciences, South Kargar Street, Qazvin Square, Qazvin Street, Tehran, Iran
5. Students’ Research Committee (SRC), Qazvin University of Medical Sciences, Qazvin, Iran

Source: BMC Medical Imaging Published:2024

Abstract

Background: This study aimed to evaluate the effectiveness of DeepLabv3+with Squeeze-and-Excitation (DeepLabv3+SE) architectures for segmenting the choroid in optical coherence tomography (OCT) images of patients with diabetic retinopathy. Methods: A total of 300 B-scans were selected from 21 patients with mild to moderate diabetic retinopathy. Six DeepLabv3+SE variants, each utilizing a different pre-trained convolutional neural network (CNN) for feature extraction, were compared. Segmentation performance was assessed using the Jaccard index, Dice score (DSC), precision, recall, and F1-score. Binarization and Bland-Altman analysis were employed to evaluate the agreement between automated and manual measurements of choroidal area, luminal area (LA), and Choroidal Vascularity Index (CVI). Results: DeepLabv3+SE with EfficientNetB0 achieved the highest segmentation performance, with a Jaccard index of 95.47, DSC of 98.29, precision of 98.80, recall of 97.41, and F1-score of 98.10 on the validation set. Bland-Altman analysis indicated good agreement between automated and manual measurements of LA and CVI. Conclusions: DeepLabv3+SE with EfficientNetB0 demonstrates promise for accurate choroid segmentation in OCT images. This approach offers a potential solution for automated CVI calculation in diabetic retinopathy patients. Further evaluation of the proposed method on a larger and more diverse dataset can strengthen its generalizability and clinical applicability. © The Author(s) 2024.

2. Advancing Diabetic Retinopathy Screening: A Systematic Review of Artificial Intelligence and Optical Coherence Tomography Angiography Innovations, Diagnostics (2025)

3. Artificial Intelligence in Retinal Image Analysis: Development, Advances, and Challenges, Survey of Ophthalmology (2023)

4. From the Diagnosis of Infectious Keratitis to Discriminating Fungal Subtypes; a Deep Learning-Based Study, Scientific Reports (2023)

Experts (# of related papers)

View all Related Experts

Mohammad Soleimani (2)

Elias Khalilipour (1)

Style	Citing Format
MLA	Saeidian J, et al.. "Segmentation of Choroidal Area in Optical Coherence Tomography Images Using a Transfer Learning-Based Conventional Neural Network: A Focus on Diabetic Retinopathy and a Literature Review." BMC Medical Imaging, vol. 24, no. 1, 2024, pp. -.
APA	Saeidian J, Azimi H, Azimi Z, Pouya P, Asadigandomani H, Riaziesfahani H, Hayati A, Daneshvar K, Khalili Pour E (2024). Segmentation of Choroidal Area in Optical Coherence Tomography Images Using a Transfer Learning-Based Conventional Neural Network: A Focus on Diabetic Retinopathy and a Literature Review. BMC Medical Imaging, 24(1), -.
Chicago	Saeidian J, Azimi H, Azimi Z, Pouya P, Asadigandomani H, Riaziesfahani H, Hayati A, Daneshvar K, Khalili Pour E. "Segmentation of Choroidal Area in Optical Coherence Tomography Images Using a Transfer Learning-Based Conventional Neural Network: A Focus on Diabetic Retinopathy and a Literature Review." BMC Medical Imaging 24, no. 1 (2024): -.
Harvard	Saeidian J et al. (2024) 'Segmentation of Choroidal Area in Optical Coherence Tomography Images Using a Transfer Learning-Based Conventional Neural Network: A Focus on Diabetic Retinopathy and a Literature Review', BMC Medical Imaging, 24(1), pp. -.
Vancouver	Saeidian J, Azimi H, Azimi Z, Pouya P, Asadigandomani H, Riaziesfahani H, et al.. Segmentation of Choroidal Area in Optical Coherence Tomography Images Using a Transfer Learning-Based Conventional Neural Network: A Focus on Diabetic Retinopathy and a Literature Review. BMC Medical Imaging. 2024;24(1):-.
BibTex	@article{ author = {Saeidian J and Azimi H and Azimi Z and Pouya P and Asadigandomani H and Riaziesfahani H and Hayati A and Daneshvar K and Khalili Pour E}, title = {Segmentation of Choroidal Area in Optical Coherence Tomography Images Using a Transfer Learning-Based Conventional Neural Network: A Focus on Diabetic Retinopathy and a Literature Review}, journal = {BMC Medical Imaging}, volume = {24}, number = {1}, pages = {-}, year = {2024} }
RIS	TY - JOUR AU - Saeidian J AU - Azimi H AU - Azimi Z AU - Pouya P AU - Asadigandomani H AU - Riaziesfahani H AU - Hayati A AU - Daneshvar K AU - Khalili Pour E TI - Segmentation of Choroidal Area in Optical Coherence Tomography Images Using a Transfer Learning-Based Conventional Neural Network: A Focus on Diabetic Retinopathy and a Literature Review JO - BMC Medical Imaging VL - 24 IS - 1 SP - EP - PY - 2024 ER -

Science Communicator Platform

Authors

Authors Affiliations

Abstract