Sürdürülebilir Kalkınma Amaçları
Yazarlar
Yayınlar
- MakaleYalnız künye2026Scopus SJRQ2Multi level throttled attention for accurate and efficient classification of retinal diseases in OCT images
Celik, Kemal; Celik, Fatih
The classification of retinal diseases using Optical Coherence Tomography images has gained significant attention in recent years. However, due to the heterogeneity of retinal disorders, achieving high classification accuracy remains challenging. While deep learning has improved the identification of various ophthalmic conditions, accurate and early diagnosis is still critical for effective clinical decision-making. Additionally, reducing computational complexity is essential for building scalable diagnostic systems. To address these challenges, we propose a novel Multi-level Throttled Attention (MLTA) model that first applies attention to extract important features, followed by throttling to filter out redundant or less useful features. This process is applied at multiple stages, operating on both Convolutional Neural Network layers and Transformer architectures, and then fuses them finally. This approach optimizes feature selection by preserving the most informative retinal features while discarding redundant ones from multi-level feature maps. As a result, the model enhances classification performance while reducing computational overhead. We evaluate our proposed model on two benchmark OCT datasets: OCT2017 and OCTID, achieving accuracy scores of 99.59 ± 0.04% and 99.71 ± 0.03%, respectively. Our method outperforms existing CNN-based and Vision Transformer-based models, demonstrating superior accuracy and efficiency through this hierarchical attention.
- MakaleAçık Erişim2023Neuropsychological and clinical correlations of optical coherence tomography findings in patients with schizophrenia
Kani, Ayse Sakalli; Çam, Cansun Sahin; Çelik, Esra Biberoglu; Dural, Uzay; Dönmez, Melike Duran; Turhan, Semra Akkaya; Toker, Ayse Ebru; Yildiz, Mesut
Objective: There are increasing studies examining retinal fiber layer (RNFL) and ganglion cell layer (GCL) thinning in patients with schizophrenia. However, the results are controversial, and clinical and cognitive reflections of these findings remain unclear. With this study, we aim to examine retinal abnormalities and establish correlations with cognitive and clinical parameters.Methods: In this cross-sectional study, we examined 29 patients with schizophrenia and 13 age and gender-matched healthy controls. All participants underwent psychometric assessment, neuropsychological tests, and optical coherence tomography (OCT) measurements. The retinal fiber layer and ganglion cell layer thickness were used as retinal parameters.Results: Five patients dropped out during the OCT measurement process, 24 patients with schizophrenia and nine healthy controls were included in the analysis. There was no statistically significant difference between groups in measuring retinal nerve fiber layer or ganglion cell layer thicknesses. The verbal fluency test score negatively correlated with left RNFL superior (p = - .422, p <.05). STROOP response duration positively correlated with right RNFL on average (p = .551, p <.05), left RNFL on average (p = .498, p <.05), right RNFL superior (p = .507, p <.05), left RNFL superior (p = .461, p <.05) and right RNFL temporal values (p = .434, p <.05). STROOP response error was also positively correlated with right RNFL temporal thickness (p = .430, p <.05). STROOP response duration was positively correlated with right GCL total (p = .646, p <.01), right GCL superior (p = .658, p <.01) and right GCL inferior (p = .596, p <.01) thickness.Conclusion: We did not find a significant relationship between reduced RNFL or GCL thickness and cognitive impairment. However, we had several positive correlations between cognitive task scores and RNFL and GCL thicknesses. Additionally, our study did not correlate symptom severity and clinical severity parameters with reduced RNFL or GCL thickness.
AtıfWoS1OpenAlex2
İncele
