A hybrid dual-stream CNN framework with dynamic data augmentation and improved Manta Ray Foraging Optimization for robust glaucoma detection.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος:	A hybrid dual-stream CNN framework with dynamic data augmentation and improved Manta Ray Foraging Optimization for robust glaucoma detection.
Συγγραφείς:	Atia A; Department of Information Systems, Faculty of Computers and Information, Kafrelsheikh University, Kafrelsheikh, Egypt. azzamohamed@fci.kfs.edu.eg., Abdel-Kader H; Department of Information Systems, Faculty of Computers and Information, Menoufia University, Shibin El-Kom, Al Minufiyah, Egypt., Abo-Seida OM; Department of Computer Science, Faculty of Computers and Information, Kafrelsheikh University, Kafrelsheikh, Egypt., Abdelatey A; Department of Information Systems, Faculty of Computers and Information, Menoufia University, Shibin El-Kom, Al Minufiyah, Egypt.; Faculty of Computers and Artificial Intelligence, Menoufia National University, Tukh Tambisha, Al Minufiyah, Egypt.
Πηγή:	Scientific reports [Sci Rep] 2026 Apr 17; Vol. 16 (1). Date of Electronic Publication: 2026 Apr 17.
Τύπος έκδοσης:	Journal Article
Γλώσσα:	English
Στοιχεία περιοδικού:	Publisher: Nature Publishing Group Country of Publication: England NLM ID: 101563288 Publication Model: Electronic Cited Medium: Internet ISSN: 2045-2322 (Electronic) Linking ISSN: 20452322 NLM ISO Abbreviation: Sci Rep Subsets: MEDLINE
Imprint Name(s):	Original Publication: London : Nature Publishing Group, copyright 2011-
Ιατρικοί όροι (MeSH):	Glaucoma/diagnosis , Glaucoma/diagnostic imaging , Image Processing, Computer-Assisted/methods , Image Interpretation, Computer-Assisted/methods, Convolutional Neural Networks ; Humans ; Algorithms ; Deep Learning
Περίληψη:	A progressive neurological condition, glaucoma is one of the main causes of irreversible blindness in the globe. Early detection is crucial to preventing irreversible vision loss however conventional diagnostic methods are often time-consuming, and heavily reliant on clinical expertise. This study presents an innovative deep learning framework designed to automate glaucoma detection while addressing key challenges such as data imbalance, image quality inconsistencies, and the need for accurate feature extraction. The proposed framework begins with a dedicated preprocessing pipeline that enhances image clarity, and isolates clinically relevant regions of interest. To handle class imbalance, a novel hybrid data augmentation strategy is introduced, combining geometric transformations with adaptive Gaussian noise injection that adjusts intensity according to image characteristics, thereby simulating realistic clinical variability. At its core, the framework leverages a dual-stream CNN architecture that integrates DenseNet121 for structural feature extraction and ResNet50 for texture representation. A lightweight channel-wise attention mechanism is then introduced to selectively emphasize clinically significant channels while suppressing redundant features, thereby balancing efficiency and interpretability. To optimize model performance while reducing computational overhead, an Improved Manta Ray Foraging Optimization (IMRFO) algorithm is employed. IMRFO enhances the standard MRFO with Partial Centroid Opposition-Based Learning (PCOBL) to dynamically fine-tune hyperparameters, including augmentation settings and transfer learning configurations. Experimental validation was conducted on four public benchmark datasets, ACRIMA, Drishti-Gs, ORIGA, and RIM-ONE-DL, demonstrating the framework's superior performance across all evaluation metrics. The model achieved 100.00% accuracy, precision, recall, and AUC on both ACRIMA and Drishti-Gs, with losses of 0.003 and 0.001, respectively. On ORIGA, it reached 99.70% accuracy, 99.80% precision, 99.30% recall, and 99.50% AUC (loss = 0.01). On RIM-ONE-DL, the model scored 99.90% accuracy, 99.70% precision, 99.50% recall, and 99.70% AUC (loss = 0.006). These findings confirm the framework's robustness and clinical applicability for effective glaucoma screening. (© 2026. The Author(s).)
Competing Interests:	Declarations. Competing interests: The authors declare no competing interests.
References:	Sci Rep. 2025 Apr 16;15(1):13087. (PMID: 40240457) Sensors (Basel). 2022 Jan 07;22(2):. (PMID: 35062405) Diagnostics (Basel). 2023 May 14;13(10):. (PMID: 37238222) Sci Rep. 2022 Aug 18;12(1):14080. (PMID: 35982106) Comput Methods Programs Biomed. 2020 Aug;192:105341. (PMID: 32155534) Photodiagnosis Photodyn Ther. 2025 Aug;54:104621. (PMID: 40482945) Ophthalmol Sci. 2022 Oct 19;3(1):100233. (PMID: 36545260) Dtsch Arztebl Int. 2008 Aug;105(34-35):583-9. (PMID: 19471619) Sci Rep. 2021 May 6;11(1):9704. (PMID: 33958686) Sci Rep. 2024 Nov 29;14(1):29660. (PMID: 39613799) Sci Rep. 2021 Jan 21;11(1):1945. (PMID: 33479405) Sci Rep. 2023 Oct 27;13(1):18408. (PMID: 37891238) Healthcare (Basel). 2022 Dec 09;10(12):. (PMID: 36554021) Sensors (Basel). 2021 Jan 15;21(2):. (PMID: 33467457) Annu Int Conf IEEE Eng Med Biol Soc. 2010;2010:3065-8. (PMID: 21095735) Front Physiol. 2023 Jun 13;14:1175881. (PMID: 37383146) Comput Methods Programs Biomed. 2025 Dec;272:109014. (PMID: 40946521) BMC Bioinformatics. 2023 Apr 19;24(1):157. (PMID: 37076790) Biomed Eng Online. 2019 Mar 20;18(1):29. (PMID: 30894178) Ophthalmology. 2014 Nov;121(11):2081-90. (PMID: 24974815) Comput Med Imaging Graph. 2025 Jul;123:102559. (PMID: 40315660) Acta Ophthalmol. 2018 Mar;96(2):161-167. (PMID: 29197157) Int Ophthalmol. 2024 Feb 17;44(1):90. (PMID: 38367098) Comput Biol Med. 2025 Apr;188:109830. (PMID: 39983361)
Contributed Indexing:	Keywords: Dual-stream convolutional neural network (CNN); Dynamic Gaussian noise; Glaucoma detection; Lightweight channel-wise attention mechanism
Entry Date(s):	Date Created: 20260417 Date Completed: 20260715 Latest Revision: 20260813
Update Code:	20260827
PubMed Central ID:	PMC13090355
DOI:	10.1038/s41598-026-45384-6
PMID:	41998000
Βάση Δεδομένων:	MEDLINE

View record at Springer

Περιγραφή
ISSN:	2045-2322
DOI:	10.1038/s41598-026-45384-6