Deep learning-based CNN for multiclassification of ocular diseases using transfer learning

Figures & data

Table 1. Identification/classification of cataract and glaucoma using deep learning methods.

Reference	Method	Dataset/Disease	Accuracy (%)
(Chen et al. 2015)	Convolutional neural network (CNN)	Public datasets: ORIGA (650 images) and SCES (1722 images)/Glaucoma detection	80
(Asaoka et al. 2019)	ResNet CNN	1364 images procured from multiple institutes in Japan/Glaucoma detection	99
(Maheshwari et al. 2020)	AlexNet CNN	RIM-ONE, an online dataset (169 images)/Glaucoma detection	98
(Acharya et al. 2010)	Artificial neural network (ANN) classifier	140 images collected from department of Ophthalmology, Kasturba Medical College Hospital, Manipal, India/normal, cataract and post-cataract images	93.3
(Gao et al. 2015)	Convolutional recursive neural networks (CRNN)	ACHIKO-NC, a publica dataset (5378 images)/Detection and grading of Cataract opacity	70.7
(Kim et al. 2019)	Custom CNN	304 images obtained from Korea University hospital/Cataract grading	68.36
(Tham et al. 2021)	ResNet-50	9747 images obtained from the Singapore epidemiology of eye diseases study/multi-classification of cataract, diabetic retinopathy and maculopathy	94.8
(An et al. 2019)	VGG-19	357 images/Glaucoma detection	96.3
(Phan et al. 2019)	DenseNet201, ResNet152, VGG-19	3312 images collected from Yamanashi University glaucoma outpatient clinic and Yamanashi Koseiren Hospital/Glaucoma detection	90
(Diaz-Pinto et al. 2019)	ResNet50, InceptionResNetV2, InceptionV3, VGG-19, VGG-16	1707 images from multiple public datasets/Glaucoma detection	95.7
(Ahn et al. 2018)	InceptionV3	1542 images collected at Kim’s Eye Hospital, Korea/Glaucoma grading	92.2
(Gharaibeh et al. 2018)	Image processing, segmentation classification	DIARETDB1, a public dataset contained 89 color fundus images categorized manually into diabetic retinopathy and normal images	97.7 (classification accuracy)
(Gharaibeh et al. 2021)	Image processing and classification	Public datasets: DIARETDB0 and DIARETDB1, consisting of different grades of non-proliferative diabetic retinopathy images	96.8
(Gharaibeh et al. 2023)	Image processing, segmentation classification	The Alzheimer’s disease neuroimaging initiative public dataset including brain MRI images	Ranging between 95–98
(Abu-Ein et al. 2022)	Image processing and classification	A public dataset: Eye-PACS consisting of 88,702 fundus images related to diabetic retinopathy	98.4

Figure 1. Ocular disease classification using CNN.

Figure 2. Data augmentation by (a) rotation 30° & 70°, (b) 1.4 & 1.8, (c) 10, 25 & 40, 60.

Figure 3. Fire protection module in SqueezeNet architecture.

Figure 4. Overall architecture of SqueezeNet.

Figure 5. Schematic diagram of DarkNet-53.

Figure 6. Architecture of DarkNet-53 network.

Figure 7. Overall architecture of EfficientNet-b0.

Figure 8. Ocular disease classification using SqueezeNet (batch size-6, optimizer-Adam) (with augmented image data).

Figure 9. Ocular disease classification using darknet-53 (batch size-6, optimizer-sgdm) (with augmented image data).

Figure 10. Ocular disease classification using EfficientNet-b0 (batch size-6, optimizer-sgdm) (with augmented image data).

Figure 11. Effect of batch size and optimizer type on the ocular disease classification accuracy for various deep learning-based CNN (with data augmentation).

Figure 12. Confusion matrix for darknet-53 (batch size-6, optimizer-SGDM) with 99.4% accuracy.

Figure 13. Accuracy with and without data augmentation for the different CNN networks.

Table 2. Accuracy of various optimised networks.

Network	Accuracy (With data augmentation)	Accuracy (Without data augmentation)	Input size	Output size	Number of layers	Parameters (millions)
SqueezeNet	95%	92%	227 × 227	801 × 826	18	1.24
Darknet-53	99.4%	96%	256 × 256	436 × 359	53	8.8
EfficientNet-b0	90%	87%	224 × 224	1920 × 926	82	5.3

Figure 14. 99.4% accuracy of darknet-53 (batch size-6, optimizer-SGDM) obtained during the training process.

Figure 15. Loss function of the optimized darknet-53 model (batch size-6, optimizer-SGDM) obtained during the training process.

Table 3. Performance metrics of the optimised darknet-53 (batch size-6, optimiser-SGDM).

Performance metric	Value (%)
Accuracy	99.40
Precision	99.39
Recall	99.40
f1-score	99.39
Specificity	99.69
FNR (cataract)	0.59
FNR (glaucoma)	0.60
FNR (normal)	0.60
FNR (overall)	0.60

Figure 16. (a) Receiver operating curve and (b) loss curve for the best accuracy CNNs.

Chen X, Xu Y, Wong DWK, Wong TY, Liu J. 2015. Glaucoma detection based on deep convolutional neural network. In: 2015 37th Annual international conference of the IEEE engineering in medicine and biology society (EMBC); Milan, Italy. p. 715–718.

 Google Scholar

Asaoka R, Tanito M, Shibata N, Mitsuhashi K, Nakahara K, Fujino Y, Kiuchi Y. 2019. Validation of a deep learning model to screen for glaucoma using images from different fundus cameras and data augmentation. Ophthalmol Glaucoma. 2(4):224–231. doi: 10.1016/j.ogla.2019.03.008.

 PubMedGoogle Scholar

Maheshwari S, Kanhangad V, Pachori RB. 2020. CNN-based approach for glaucoma diagnosis using transfer learning and LBP-based data augmentation. arXiv Preprint. http://arxiv.org/abs/2002.08013.

 Google Scholar

Acharya RU, Yu W, Zhu K, Nayak J, Lim T-C, Chan JY. 2010. Identification of cataract and post-cataract surgery optical images using artificial intelligence techniques. J Med Syst. 34(4):619–628. doi: 10.1007/s10916-009-9275-8.

 PubMed Web of Science ®Google Scholar

Gao X, Lin S, Wong TY. 2015. Automatic feature learning to grade nuclear cataracts based on deep learning. IEEE Trans Biomed Eng. 62(11):2693–2701. doi: 10.1109/TBME.2015.2444389.

 PubMed Web of Science ®Google Scholar

Kim D, Jun TJ, Eom Y, Kim C, Kim D. 2019. Tournament based ranking CNN for the cataract grading. Proceeding Annual International Conference of the IEEE Engineering in Medicine and Biology Society; Berlin, Germany. p. 1630–1636.

 Google Scholar

Tham YC, Anees A, Zhang L, Goh JHL, Rim TH, Nusinovici S, Hamzah H, Chee M-L, Tjio G, Li S, et al. 2021. Referral for disease-related visual impairment using retinal photograph-based deep learning: a proof-of-concept, model development study. Lancet Digit Heal. 3(1):e29–40. doi:10.1016/S2589-7500(20)30271-5.

 PubMedGoogle Scholar

An G, Omodaka K, Hashimoto K, Tsuda S, Shiga Y, Takada N, Kikawa T, Yokota H, Akiba M, Nakazawa T. 2019. Glaucoma diagnosis with machine learning based on optical coherence tomography and color fundus images. J Healthc Eng. 2019:1–9. doi: 10.1155/2019/4061313.

 Web of Science ®Google Scholar

Phan S, Satoh S, Yoda Y, Kashiwagi K, Oshika T. 2019. Evaluation of deep convolutional neural networks for glaucoma detection. Jpn J Ophthalmol. 63(3):276–283. doi: 10.1007/s10384-019-00659-6.

 PubMed Web of Science ®Google Scholar

Diaz-Pinto A, Morales S, Naranjo V, Köhler T, Mossi JM, Navea A. 2019. Cnns for automatic glaucoma assessment using fundus images: an extensive validation. Biomed Eng Online. 18(1):1–19. doi: 10.1186/s12938-019-0649-y.

 PubMed Web of Science ®Google Scholar

Ahn JM, Kim S, Ahn K-S, Cho S-H, Lee KB, Kim US, Bhattacharya S. 2018. A deep learning model for the detection of both advanced and early glaucoma using fundus photography. PLoS One. 13(11):0207982. doi: 10.1371/journal.pone.0207982.

 PubMed Web of Science ®Google Scholar

Gharaibeh N, Al-Naami B, Nahar KM. 2018. An effective image processing method for detection of diabetic retinopathy diseases from retinal fundus images. Int J Signal Imag Syst Eng. 11(4):206–216.

 Web of Science ®Google Scholar

Gharaibeh N, Abu-Ein A, Nahar KM. 2021. A hybrid SVM NAÏVE-BAYES Classifier for bright lesions recognition in eye fundus images. Int J Electr Eng Inform. 13(3):530–545.

 Google Scholar

Gharaibeh N, Abu-Ein AA, Nahar KM, Abu-Ain WA, Al-Nawashi MM. 2023. Swin transformer-based segmentation and multi-scale feature pyramid fusion module for Alzheimer’s disease with machine learning. Int J Online Biomed Eng. 19(4):22–50.

 Web of Science ®Google Scholar

Abu-Ein AA, Tahat NM, Al-Smadi MM, Al-Nawashi MM, Al-Nawashi M. 2022 Dec 2. Combining artificial intelligence and image processing for diagnosing diabetic retinopathy in retinal fundus images. Int J Onl Eng. 18(13):131–151. doi: 10.3991/ijoe.v18i13.33985.

 Google Scholar