nach oben

International Ophthalmology

Erschienen in:

01.12.2024 | Original Paper

Exploration of AI-powered DenseNet121 for effective diabetic retinopathy detection

verfasst von: K. Santhiya Lakshmi, B. Sargunam

Erschienen in: International Ophthalmology | Ausgabe 1/2024

Einloggen, um Zugang zu erhalten

Abstract

Objective

Diabetic Retinopathy (DR) is a severe complication of diabetes that damages the retina and affects approximately 80% of patients with diabetes for 10 years or more. This condition primarily impacts young and productive individuals, resulting in significant long-term medical complications for patients and society. The early stages of diabetic retinopathy often advance without noticeable symptoms, resulting in delayed identification and intervention. Therefore, develop approaches employing transfer learning methodologies to enhance early detection capabilities, facilitating timely diagnosis and intervention to mitigate the progression of diabetic retinopathy.

Methods

This study introduces a transfer learning approach for detecting four stages of DR: No DR, Mild, Moderate, and Severe. The methods AlexNet, VGG16, ResNet50, Inception v3, and DenseNet121 are utilized and trained using the Kaggle DR dataset.

Results

To assess the efficiency of the suggested improved network, the Kaggle dataset is employed to analyze four performance metrics: Sensitivity, Precision, Accuracy, and F1 score. DenseNet121 demonstrated superior accuracy among the two models, outperforming other models, making it a suitable option for automatic DR sign detection.

Conclusion

The integration of the DenseNet121 model shows great promise in transforming the timely identification and treatment of DR, resulting in enhanced patient results in the long run and alleviating the burden on society.

Institute NE (2015) Facts About Diabetic Eye Disease [Internet]. https://nei.nih.gov/health/diabetic/retinopathy. Accessed 6 May 2023

Forouhi NG, Wareham NJ (2010) Epidemiology of diabetes. Medicine 42(12):698–702. https://doi.org/10.1016/j.mpmed.2014.09.007CrossRef

Tabish SA (2007) Is diabetes becoming the biggest epidemic of the twenty- first century. Int J Health Sci 1(2):V–VIII

Lin X, Yufeng X, Pan X, Jingya X, Ding Y, Xue S, Xiaoxiao S, Yuezhong R, Fei SP (2020) Global, regional, and national burden and trend of diabetes in 195 countries and territories: an analysis from 1990 to 2025. Sci Rep 10(1):1–11. https://doi.org/10.1038/s41598-020-71908-9CrossRef

Atre S (2019) The burden of diabetes in India. Lancet Glob Health 7(4):e418. https://doi.org/10.1016/S2214-109X(18)30556-4CrossRefPubMed

Early Treatment DR Study Research Group (1991) Grading DR from stereoscopic colour fundus photographs - an extension of the modified airlie house classification, ETDRS Report Number 10. Ophthalmology 98(5):786–806. https://doi.org/10.1016/S0161-6420(13)38012-9CrossRef

International Council of Ophthalmology (2017) ICO guidelines for diabetic eye care, San Francisco (CA). International Council of Ophthalmology [Internet]. http://www.icoph.org/ICOGuidelinesforDiabeticEyeCare. Accessed 10 May 2023

Tang MCS, Teoh SS, Ibrahim H (2022) Retinal vessel segmentation from fundus images using DeepLabv3+. In: IEEE 18th international colloquium on signal processing & applications (CSPA-2022). pp 377–381. https://doi.org/10.1109/CSPA55076.2022.9781891

Tang MCS, Teoh SS, Ibrahim H, Embong Z (2021) Neovascularization detection and localization in fundus images using deep learning. Sensors 21(16):5327. https://doi.org/10.3390/s21165327ADSCrossRefPubMedPubMedCentral

10.

Khojasteh P, Passos Júnior LA, Carvalho T, Rezende E, Aliahmad B, Papa JP, Kumar DK (2019) Exudate detection in fundus images using deeply-learnable features. Comput Biol Med 104:62–69. https://doi.org/10.1016/j.compbiomed.2018.10CrossRefPubMed

11.

Zheng R, Liu L, Zhang S, Zheng C, Bunyak F, Xu R, Li B, Sun M (2018) Detection of exudates in fundus photographs with imbalanced learning using conditional generative adversarial network. Biomed Opt Express 9(10):4863–4878. https://doi.org/10.1364/BOE.9.004863ADSCrossRefPubMedPubMedCentral

12.

Eftekhari N, Pourreza HR, Masoudi M, Ghiasi-Shirazi K, Saeedi E (2019) Microaneurysm detection in fundus images using a two-step convolutional neural network. Biomed Eng Online 18(1):67. https://doi.org/10.1186/s12938-019-0675-9CrossRefPubMedPubMedCentral

13.

Choi JY, Yoo TK, Seo JG, Wak JK, Um T, Rim TK (2017) Multicategorical deep learning neural network to classify retinal images: a pilot study employing small database. PLoS ONE 11:e0187336. https://doi.org/10.1371/journal.pone.0187336CrossRef

14.

Ting DSW, Cheung CYL, Lim G, Tan GSW, Quang ND, Gan A, Hamzah H, Garcia-Franco R, San Yeo LY, Lee SY (2017) Development and validation of a deep learning system for DR and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA 318(22):2211–2223. https://doi.org/10.1001/jama.2017.18152CrossRefPubMedPubMedCentral

15.

Tang MCS, Teoh SS, Ibrahim H, Embong Z (2022) A deep learning approach for the detection of neovascularization in fundus images using transfer learning. IEEE Access 10:20247–20258. https://doi.org/10.1109/ACCESS.2022.3151644CrossRef

16.

Tang MCS, Teoh SS (2020) Blood vessel segmentation in fundus images using hessian matrix for diabetic retinopathy detection. In: 11th IEEE annual information technology, electronics and mobile communication conference (IEMCON-2020). pp 0728–0733. https://doi.org/10.1109/IEMCON51383.2020.9284931.

17.

Islam KT, Wijewickrema S, Leary SO (2019) Identifying DR from oct images using deep transfer learning with artifificial neural networks. In: IEEE 32nd international symposium on computer-based medical systems (CBMS). pp 281–286. https://doi.org/10.1109/CBMS.2019.00066

18.

Tang MCS, Teoh SS (2023) Brain tumor detection from MRI images based on ResNet18. In: 6th International conference on information systems and computer networks (ISCON-2023). p 1. https://doi.org/10.1109/ISCON57294.2023.10112025

19.

Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097–1105. https://doi.org/10.1145/3065386CrossRef

20.

University of oxford (2021) Visual geometry group. https://www.robots.ox.ac.uk/~vgg/software/via/, Accessed 25 May 2023

21.

Hacisoftaoglu RE, Karakaya M, Sallam AB (2020) Deep learning frameworks for diabetic retinopathy detection with smartphone-based retinal imaging systems. Pattern Recogn Lett 135:409–417. https://doi.org/10.1016/j.patrec.2020.04.009ADSCrossRef

22.

He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition, pp 770–778. https://doi.org/10.48550/arXiv.1512.03385

23.

Szegedy C (2015) Going deeper with Convolutions. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR). https://doi.org/10.1109/CVPR.2015.7298594

24.

Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 4700–4708. https://doi.org/10.48550/arXiv.1608.06993

25.

Kaggle Dataset. Diabetic Retinopathy 224 × 224 (2019 Data). [Available: Diabetic Retinopathy 224 × 224 (2019 Data) | Kaggle] Accessed: 5 Jun 2023

26.

Ur-Rehman M, Khan SH, Abbas Z, Danish Rizvi SM (2019) Classification of DR images based on customised CNN architecture. In Proceedings of the Amity international conference on artifificial intelligence, AICAI, Dubai, United Arab Emirates, pp 244–248. https://doi.org/10.1109/AICAI.2019.8701231

27.

Powers DM (2011) Evaluation: from precision, recall and f-measure to roc, informedness, markedness and correlation. J Mach Learn Technol https://doi.org/10.48550/arXiv.2010.16061

28.

Mohanty C, Mahapatra S, Acharya B, Kokkoras F, Gerogiannis VC, Karamitsos I, Kanavos A (2023) Using deep learning architectures for detection and classification of diabetic retinopathy. Sensors 23(12):5726. https://doi.org/10.3390/s23125726ADSCrossRefPubMedPubMedCentral

29.

Abdel Maksoud E, Barakat S, Elmogy M (2022) A computer-aided diagnosis system for detecting various diabetic retinopathy grades based on a hybrid deep learning technique. Med Biol Eng Comput 60:2015–2038CrossRefPubMed

30.

Rafid AUI, Sanjana S, Munir MB et al (2023) An early-stage diagnosis of diabetic retinopathy based on ensemble framework. SIViP. https://doi.org/10.1007/s11760-023-02796-5CrossRef

31.

Das D, Biswas SK, Bandyopadhyay S (2022) A critical review on diagnosis of diabetic retinopathy using machine learning and deep learning. Multimed Tools Appl 81:25613–25655. https://doi.org/10.1007/s11042-022-12642-4CrossRefPubMedPubMedCentral

32.

Grauslund J (2022) Diabetic retinopathy screening in the emerging era of artificial intelligence. Diabetologia 65(9):1415–1423. https://doi.org/10.1007/s00125-022-05727-0CrossRefPubMed

Titel: Exploration of AI-powered DenseNet121 for effective diabetic retinopathy detection
verfasst von: K. Santhiya Lakshmi
B. Sargunam
Publikationsdatum: 01.12.2024
Verlag: Springer Netherlands
Erschienen in: International Ophthalmology / Ausgabe 1/2024
Print ISSN: 0165-5701
Elektronische ISSN: 1573-2630
DOI: https://doi.org/10.1007/s10792-024-03027-7

Neu im Fachgebiet Augenheilkunde

Metastase in der periokulären Region

Metastasen Leitthema

Orbitale und periokuläre metastatische Tumoren galten früher als sehr selten. Aber mit der ständigen Aktualisierung von Medikamenten und Nachweismethoden für die Krebsbehandlung werden neue Chemotherapien und Strahlenbehandlungen eingesetzt. Die …

Staging und Systemtherapie bei okulären und periokulären Metastasen

Metastasen Leitthema

Metastasen bösartiger Erkrankungen sind die häufigsten Tumoren, die im Auge diagnostiziert werden. Sie treten bei ungefähr 5–10 % der Patienten mit soliden Tumoren im Verlauf der Erkrankung auf. Besonders häufig sind diese beim Mammakarzinom und …

CME: Wundheilung nach Trabekulektomie

Trabekulektomie CME-Artikel

Wird ein Glaukom chirurgisch behandelt, ist die anschließende Wundheilung von entscheidender Bedeutung. In diesem CME-Kurs lernen Sie, welche Pathomechanismen der Vernarbung zugrunde liegen, wie perioperativ therapiert und Operationsversagen frühzeitig erkannt werden kann.

„standard operating procedures“ (SOP) – Vorschlag zum therapeutischen Management bei periokulären sowie intraokulären Metastasen

Metastasen Leitthema

Peri- sowie intraokuläre Metastasen sind insgesamt gesehen selten und meist Zeichen einer fortgeschrittenen primären Tumorerkrankung. Die Therapie ist daher zumeist palliativ und selten kurativ. Zudem ist die Therapiefindung sehr individuell. Die …

Update Augenheilkunde

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.

Newsletter bestellen

Live-Webinar "Urologie und Sexualmedizin in der Praxis"

Springer Medizin

Exploration of AI-powered DenseNet121 for effective diabetic retinopathy detection

Abstract

Objective

Methods

Results

Conclusion

Neu im Fachgebiet Augenheilkunde

Metastase in der periokulären Region

Staging und Systemtherapie bei okulären und periokulären Metastasen

CME: Wundheilung nach Trabekulektomie

„standard operating procedures“ (SOP) – Vorschlag zum therapeutischen Management bei periokulären sowie intraokulären Metastasen

Update Augenheilkunde

Live-Webinar "Urologie und Sexualmedizin in der Praxis"

Springer Medizin

Abstract

Objective

Methods

Results

Conclusion

Bitte loggen Sie sich ein, um Zugang zu diesem Inhalt zu erhalten

Weitere Artikel der Ausgabe 1/2024

Impact of removing soft contact lenses 1 day versus 1 month before surgery on the outcomes of microkeratome laser in situ keratomileusis

Diabetic corneal neuropathy and its relation to the severity of retinopathy in patients with type 2 diabetes mellitus: an in vivo confocal microscopy study

Analysis and validation of potential ICD-related biomarkers in development of myopia using machine learning

Ocular injuries associated with motor vehicle accidents: long term effects on quality of life

Unlocking the secrets of success in probing for congenital nasolacrimal duct obstruction: investigating the factors that matter

Resilient back-propagation machine learning-based classification on fundus images for retinal microaneurysm detection

Neu im Fachgebiet Augenheilkunde

Metastase in der periokulären Region

Staging und Systemtherapie bei okulären und periokulären Metastasen

CME: Wundheilung nach Trabekulektomie

„standard operating procedures“ (SOP) – Vorschlag zum therapeutischen Management bei periokulären sowie intraokulären Metastasen

Update Augenheilkunde