This technology is an artificial intelligence system for eye disease detection that is trained using eye movements of clinical and medical experts as they view ophthalmic images.
Unmet Need: Interpretable clinical AI system for eye disease detection
Diagnosis of glaucoma and age-related macular degeneration requires timely assessment by medical experts while also lacking a gold standard. Artificial intelligence (AI) systems can aid diagnosis, but the lack of interpretability and expert-level decision-making hinders their implementation in the clinic. There are currently no AI systems that combine the domain expertise of medical experts to engineer a system for enhanced glaucoma detection.
The Technology: Expert eye-movement-informed artificial intelligence for eye disease detection
This technology is a more accurate and interpretable artificial intelligence (AI) system for eye disease detection that is trained using eye-tracking data from medical professionals during the analysis of patient eye imaging. The algorithm is developed using eye tracking equipment on experts which will be analyzed and integrated with the classification and identification of glaucoma. Using visual transformers, contrastive learning, and other machine learning methods, this system develops a sense of eye-movement-informed attention and enables weakly-supervised learning of eye disease diagnosis. This system can guide medical trainees and experts in analyzing eye images to reduce diagnostic errors.
Applications:
- Diagnosis of glaucoma and age-related macular degeneration
- Diagnostic assistance to reduce misdiagnosis
- Training tool for ophthalmology and radiology
- Optometry diagnosis performance analysis
- Discovery of new ocular diagnostic features
Advantages:
- High-accuracy system trained by expert data
- Unbiased and weakly-supervised learning
- Compatible with current clinical application
- Reduces physician time and cost
Lead Inventor:
Kaveri Thakoor, Ph.D.
Patent Information:
Patent Pending
Related Publications:
Kaushal S, Kenia R, Aima S, Thakoor KA. “Medical-Expert Eye Movement Augmented Vision Transformers for Glaucoma Diagnosis.” 2024 IEEE EMBS Int Conf Biomed Health Inform (BHI). 2024:1-8.
Tian Y, Sharma A, Mehta S, Kaushal S, Liebmann JM, Cioffi GA, Thakoor KA. “Automated Identification of Clinically Relevant Regions in Glaucoma OCT Reports Using Expert Eye Tracking Data and Deep Learning.” Transl Vis Sci Technol. 2024 Oct;13(10):24.
Akerman M, Choudhary S, Liebmann JM, Cioffi GA, Chen RW, Thakoor KA. “Extracting decision-making features from the unstructured eye movements of clinicians on glaucoma OCT reports and developing AI models to classify expertise.” Front Med. 2023 Sep 29;10:1251183.
Thakoor KA, Koorathota SC, Hood DC, Sajda P. “Robust and Interpretable Convolutional Neural Networks to Detect Glaucoma in Optical Coherence Tomography Images.” IEEE Trans Biomed Eng. 2022 Aug; 68(8): 2456-2466.
Tech Ventures Reference:
