⚡ Quick Summary
A novel transformer-based model, Retformer, has been developed for the early detection of Alzheimer’s disease (AD) using retinal imaging. This model demonstrates superior performance, outperforming benchmark algorithms by margins of up to 11%.
🔍 Key Details
- 📊 Dataset: Retinal images from AD patients and age-matched healthy controls
- 🧩 Features used: Various modalities of retinal imaging
- ⚙️ Technology: Transformer-based architecture with explainable AI
- 🏆 Performance: Outperformed benchmark algorithms by up to 11%
🔑 Key Takeaways
- 🧠 Alzheimer’s disease affects millions globally, making early diagnosis crucial.
- 🔍 Retformer utilizes retinal imaging to detect AD effectively.
- 📈 Gradient-weighted Class Activation Mapping provides insights into model decision-making.
- 💡 The model identifies key features in retinal images that correlate with AD.
- 🏥 Potential for transforming AD detection through non-invasive imaging techniques.
- 🌟 Study published in Sci Rep by Jamshidiha et al.
- 🔬 Research highlights the importance of explainable AI in medical diagnostics.
📚 Background
Alzheimer’s disease is a progressive neurodegenerative disorder that poses significant challenges to healthcare systems worldwide. With no effective treatments currently available, the need for early diagnosis is paramount. Traditional diagnostic methods can be invasive and time-consuming, highlighting the necessity for innovative approaches that leverage advanced technologies.
🗒️ Study
The study introduced the Retformer, a transformer-based model designed to analyze retinal images for the detection of AD. By training on diverse datasets comprising retinal images from both AD patients and healthy controls, the model learns to recognize complex patterns that may indicate the presence of the disease.
📈 Results
The Retformer model demonstrated remarkable performance, surpassing various benchmark algorithms by margins of up to 11% across different performance metrics. The use of the Gradient-weighted Class Activation Mapping algorithm allowed researchers to visualize which regions of the retinal images were most influential in the model’s classification decisions, providing valuable insights into the underlying mechanisms of AD detection.
🌍 Impact and Implications
The implications of this research are profound. By utilizing retinal imaging, the Retformer model offers a non-invasive and efficient method for early AD detection. This could lead to timely interventions, ultimately improving patient outcomes and quality of life. Furthermore, the integration of explainable AI in medical diagnostics enhances trust and transparency in AI-driven healthcare solutions.
🔮 Conclusion
The development of the Retformer model marks a significant advancement in the field of Alzheimer’s disease detection. By harnessing the power of retinal imaging and explainable AI, this research paves the way for more accurate and accessible diagnostic tools. Continued exploration in this area holds promise for transforming how we approach neurodegenerative diseases in the future.
💬 Your comments
What are your thoughts on the use of retinal imaging for Alzheimer’s disease detection? We invite you to share your insights and engage in a discussion! 💬 Leave your comments below or connect with us on social media:
An explainable transformer model for Alzheimer’s disease detection using retinal imaging.
Abstract
Alzheimer’s disease (AD) is a neurodegenerative disorder that affects millions worldwide. In the absence of effective treatment options, early diagnosis is crucial for initiating management strategies to delay disease onset and slow down its progression. In this study, we propose Retformer, a novel transformer-based architecture for detecting AD using retinal imaging modalities, leveraging the power of transformers and explainable artificial intelligence. The Retformer model is trained on datasets of different modalities of retinal images from patients with AD and age-matched healthy controls, enabling it to learn complex patterns and relationships between image features and disease diagnosis. To provide insights into the decision-making process of our model, we employ the Gradient-weighted Class Activation Mapping algorithm to visualise the feature importance maps, highlighting the regions of the retinal images that contribute most significantly to the classification outcome. These findings are compared to existing clinical studies on detecting AD using retinal biomarkers, allowing us to identify the most important features for AD detection in each imaging modality. The Retformer model outperforms a variety of benchmark algorithms across different performance metrics by margins of up to 11%.
Author: [‘Jamshidiha S’, ‘Rezaee A’, ‘Hajati F’, ‘Golzan M’, ‘Chiong R’]
Journal: Sci Rep
Citation: Jamshidiha S, et al. An explainable transformer model for Alzheimer’s disease detection using retinal imaging. An explainable transformer model for Alzheimer’s disease detection using retinal imaging. 2025; 15:26773. doi: 10.1038/s41598-025-12498-2