The aim of the study is to improve the accuracy of age related macular degeneration (AMD) disease in its earlier phases with proposed Capsule Network (CapsNet) architecture trained on speckle noise reduced spectral domain optical coherence tomography (SD-OCT) images based on an optimized Bayesian non-local mean (OBNLM) filter augmentation techniques.
Methods
A total of 726 local SD-OCT images were collected and labelled as 159 drusen, 145 dry AMD, 156 wet AMD and 266 normal. Region of interest (ROI) was identified. Speckle noise in SD-OCT images were reduced based on OBNLM filter. The processed images were fed to proposed CapsNet architecture to clasify SD-OCT images. Accuracy rates were calculated in both public and local dataset.
Results
Accuracy rate of local SD-OCT image dataset classification was achieved to a value of 96.39% after performing data augmentation and speckle noise reduction with OBNLM. The performance of proposed CapsNet was also evaluated on the public Kaggle dataset under the same processing procedures and the accuracy rate was calculated as 98.07%. The sensitivity and specificity rates were 96.72% and 99.98%, respectively.
Conclusions
The classification success of proposed CapsNet may be improved with robust pre-processing steps like; determination of ROI and denoised SD-OCT images based on OBNLM. These impactful image preprocessing steps yielded higher accuracy rates for determining different types of AMD including its precursor lesion on the both local and public dataset with proposed CapsNet architecture.
StarkKOldenMBrandlC, et al.The German AugUR study: study protocol of a prospective study to investigate chronic diseases in the elderly. BMC Geriatr2015; 15: 130.
2.
WongWLSuXLiX, et al.Global prevalence of age-related macular degeneration and disease burden projection for 2020 and 2040: a systematic review and meta-analysis. Lancet Glob Health2014; 2: e106–e116.
3.
JagerRDMielerWFMillerJW. Age-related macular degeneration. N Engl J Med2008; 358: 2606–2617.
4.
KanagasingamYBhuiyanAAbràmoffMD, et al.Progress on retinal image analysis for age related macular degeneration. Prog Retin Eye Res2014; 38: 20–42.
5.
FarsiuSChiuSJO’ConnellRV, et al.Quantitative classification of eyes with and without intermediate age-related macular degeneration using optical coherence tomography. Ophthalmology2014; 121: 162–172.
6.
HeoTYKimKMMinHK, et al.Development of a deep-learning-based artificial intelligence tool for differential diagnosis between dry and neovascular age-related macular degeneration. Diagnostics (Basel)2020; 10: 261.
7.
MishraZGanegodaASelichaJ, et al.Automated retinal layer segmentation using graph-based algorithm incorporating deep-learning-derived information. Sci Rep2020; 10: 9541.
8.
WangYLiuSLouS, et al.Application of optical coherence tomography in clinical diagnosis. J Xray Sci Technol2019; 27: 995–1006.
9.
WindsorMASunSJJFrickKD, et al.Estimating public and patient savings from basic research-a study of optical coherence tomography in managing antiangiogenic therapy. Am J Ophthalmol2018; 185: 115–122.
10.
AlsaihKYusoffMZTangTB, et al.Deep learning architectures analysis for age-related macular degeneration segmentation on optical coherence tomography scans. Comput Methods Programs Biomed2020; 195: 105566.
11.
Schmidt-ErfurthUSadeghipourAGerendasBS, et al.Artificial intelligence in retina. Prog Retin Eye Res2018; 67: 1–29.
12.
BurlinaPMJoshiNPekalaM, et al.Automated grading of age-related macular degeneration from color fundus images using deep convolutional neural networks. JAMA Ophthalmol2017; 135: 1170–1176.
13.
DevallaSKChinKSMariJM, et al.A deep learning approach to digitally stain optical coherence tomography images of the optic nerve head. Invest Ophthalmol Vis Sci2018; 59: 63–74.
14.
YanQWeeksDEXinH, et al.Deep-learning-based prediction of late age-related macular degeneration progression. Nat Mach Intell2020; 2: 141–150.
15.
MargetaJCriminisiACabrera LozoyaA, et al.Fine-tuned convolutional neural nets for cardiac MRI acquisition plane recognition. Comput Methods Biomech and Biomed Eng Imaging Vis2017; 5: 339–349.
16.
TajbakhshNGotwayMBLiangJ. Computer-aided pulmonary embolism detection using a novel vessel-aligned multiplanar image representation and convolutional neural networks. In: International conference on medical image computing and computer-assisted intervention, Springer, 2015, pp. 62–69.
17.
Coup´ePHellierPKervrannC, et al.Nonlocal means-based speckle filtering for ultrasound images. IEEE Trans Image Process2009; 18: 2221–2229.
18.
PhayeSSRSikkaADhallA, et al. Dense and diverse capsule networks: making the capsules learn better 2018, arXiv abs/1805.04001.
19.
HintonGEKrizhevskyAWangSD. Transforming auto-encoders. In: HonkelaTDuchWGirolamiMKaskiS (eds)Artificial neural networks and machine learning – ICANN 2011. Lecture notes in computer science, vol 6791. Berlin, Heidelberg: Springer, 2011, pp. 44–51.
20.
SabourSFrosstNHintonGE. Dynamic routing between capsules 2017, arXiv abs/1710.09829.
21.
KingmaDPBaJ. Adam: a method for stochastic optimization CoRR. 2015, arXiv abs/1412.6980.
22.
De FauwJLedsamJRRomera-ParedesB, et al.Clinically applicable deep learning for diagnosis and referral in retinal disease. Nat Med2018; 24: 1342–1350.
23.
KarriSPChakrabortyDChatterjeeJ. Transfer learning based classification of optical coherence tomography images with diabetic macular edema and dry age-related macular degeneration. Biomed Opt Express2017; 8: 579–592.
24.
RongYXiangDZhuW, et al.Surrogate-assisted retinal OCT image classification based on convolutional neural networks. IEEE J Biomed Health Inform2019; 23: 253–263.
25.
TingDSWPasqualeLRPengL, et al.Artificial intelligence and deep learning in ophthalmology. Br J Ophthalmol2019; 103: 167–175.
26.
TingDSWPengLVaradarajanAV, et al.Deep learning in ophthalmology: the technical and clinical considerations. Prog Retin Eye Res2019; 72: 100759.
27.
LeeCSTyringAJDeruyterNP, et al.Deep-learning based, automated segmentation of macular edema in optical coherence tomography. Biomed Opt Express2017; 8: 3440–3448.
28.
LeeCSBaughmanDMLeeAY. Deep learning is effective for classifying normal versus age-related macular degeneration OCT images. Ophthalmol Retina2017; 1: 322–327.
29.
HussainZGimenezFYiD,et al.Differential data augmentation techniques for medical imaging classification tasks. Ann Symp Proc/AMIA Symp 2017; 2017: 979–984.
30.
SezerASezerHB. Deep convolutional neural network-based automatic classification of neonatal hip ultrasound images: a novel data augmentation approach with speckle noise reduction. Ultrasound Med Biol2020; 46: 735–749.
31.
KermanyDSGoldbaumMCaiW, et al.Identifying medical diagnoses and treatable diseases by image-based deep learning resource identifying medical diagnoses and treatable diseases by image-based deep learning. Cell2018; 172: 1122–1131.e9.
32.
AlqudahAM. AOCT-NET: a convolutional network automated classification of multiclass retinal diseases using spectral-domain optical coherence tomography images. Med Biol Eng Comput2020; 58: 41–53.
33.
GnanaduraiDSadasivamV. Image de-noising using double density wavelet transform based adaptive thresholding technique. Int J Wavelets Multiresolut Inf Process2005; 03: 141–152.
