Observational Study
Copyright ©The Author(s) 2025. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Psychiatry. Sep 19, 2025; 15(9): 108359
Published online Sep 19, 2025. doi: 10.5498/wjp.v15.i9.108359
Self-AttentionNeXt: Exploring schizophrenic optical coherence tomography image detection investigations
Mehmet Kaan Kaya, Sermal Arslan, Suheda Kaya, Gulay Tasci, Burak Tasci, Filiz Ozsoy, Sengul Dogan, Turker Tuncer
Mehmet Kaan Kaya, Sermal Arslan, Universal Eye Clinic, Elazig 23100, Türkiye
Suheda Kaya, Gulay Tasci, Department of Psychiatry, Elazig Fethi Sekin City Hospital, Elazig 23100, Türkiye
Burak Tasci, Vocational School of Technical Sciences, Firat University, Elazig 23100, Türkiye
Filiz Ozsoy, Department of Psychiatry, Tokat Gaziosmanpasa University, Tokat 60100, Türkiye
Sengul Dogan, Turker Tuncer, Department of Digital Forensics Engineering, College of Technology, Firat University, Elazig 23119, Türkiye
Co-corresponding authors: Burak Tasci and Sengul Dogan.
Author contributions: Kaya MK, Kaya S, Tasci B, and Dogan S wrote the original draft; Kaya MK and Arslan S contributed to the data curation and investigation; Kaya MK and Dogan S contributed to the visualization; Arslan S, Tasci G, Tasci B, Ozsoy F, and Tuncer T contributed to the review and editing; Kaya S, Tasci B, and Tuncer T contributed to the methodology; Kaya S, Dogan S, and Tuncer T contributed to the formal analyses; Kaya S and Ozsoy F contributed to the validation; Tasci G and Tasci B contributed to the conceptualization; Tasci G and Ozsoy F contributed to the resources; Tasci G, Tasci B, Dogan S, and Tuncer T contributed to the supervision; Tasci B, Dogan S, and Tuncer T contributed to the project administration; Dogan S and Tuncer T contributed to the software; All authors approved the final version of manuscript to publish; Tasci B and Dogan S made equal contributions as co-corresponding authors.
Institutional review board statement: The study was approved by the local ethical committee, Ethics Committee of Firat University, No. 2023/07-15.
Informed consent statement: Informed consent was obtained from all participants for inclusion in the study and publication of anonymized optical coherence tomography images. All procedures were conducted in accordance with the Declaration of Helsinki.
Conflict-of-interest statement: The authors have no conflicts of interest to declare.
STROBE statement: The authors have read the STROBE Statement-checklist of items, and the manuscript was prepared and revised according to the STROBE Statement-checklist of items.
Data sharing statement: Mendeley optical coherence tomography dataset: https://data.mendeley.com/datasets/rscbjbr9sj/3. Schizophrenia optical coherence tomography dataset is available upon request.
Open Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: https://creativecommons.org/Licenses/by-nc/4.0/
Corresponding author: Sengul Dogan, Professor, Department of Digital Forensics Engineering, College of Technology, Firat University, University District, Elazig 23119, Türkiye. sdogan@firat.edu.tr
Received: April 13, 2025
Revised: May 16, 2025
Accepted: June 30, 2025
Published online: September 19, 2025
Processing time: 136 Days and 13.3 Hours
Abstract
BACKGROUND

Optical coherence tomography (OCT) enables high-resolution, non-invasive visualization of retinal structures. Recent evidence suggests that retinal layer alterations may reflect central nervous system changes associated with psychiatric disorders such as schizophrenia (SZ).

AIM

To develop an advanced deep learning model to classify OCT images and distinguish patients with SZ from healthy controls using retinal biomarkers.

METHODS

A novel convolutional neural network, Self-AttentionNeXt, was designed by integrating grouped self-attention mechanisms, residual and inverted bottleneck blocks, and a final 1 × 1 convolution for feature refinement. The model was trained and tested on both a custom OCT dataset collected from patients with SZ and a publicly available OCT dataset (OCT2017).

RESULTS

Self-AttentionNeXt achieved 97.0% accuracy on the collected SZ OCT dataset and over 95% accuracy on the public OCT2017 dataset. Gradient-weighted class activation mapping visualizations confirmed the model’s attention to clinically relevant retinal regions, suggesting effective feature localization.

CONCLUSION

Self-AttentionNeXt effectively combines transformer-inspired attention mechanisms with convolutional neural networks architecture to support the early and accurate detection of SZ using OCT images. This approach offers a promising direction for artificial intelligence-assisted psychiatric diagnostics and clinical decision support.

Keywords: Self-AttentionNeXt; Optical coherence tomography image classification; Schizophrenia detection; Biomedical image classification; Deep learning in ophthalmology; Retinal imaging biomarkers

Core Tip: This study presents Self-AttentionNeXt, a novel deep learning architecture that integrates self-attention mechanisms from transformer models with convolutional neural networks for the classification of optical coherence tomography images. By focusing on retinal image regions most relevant to schizophrenia, the model achieves high diagnostic accuracy. The integration of inverted bottleneck attention blocks and residual connections enhances both feature representation and training stability. Self-AttentionNeXt demonstrates that combining attention mechanisms with convolutional neural networks can offer a powerful tool for supporting ophthalmic evaluation in patients with schizophrenia.