Artificial intelligence (AI) stands to increasingly affect the practice of medicine as advances in deep learning for computer vision and natural language processing are translated to medical contexts. Applications of deep learning to retinal imaging have shown promise in recent years, beginning with a 2016 study by authors from Google demonstrating near-ophthalmologist accuracy in the classification of diabetic retinopathy from fundus photographs.1 However, the challenges facing AI in retinal imaging parallel the challenges with applying AI to medicine in general. Many of these problems arise owing to limitations in data. Large amounts of annotated data are traditionally required to “train” deep-learning models to perform well. Not only can high-volume data annotation be costly (the aforementioned diabetic retinopathy study required approximately 527 000 evaluations of fundus images by ophthalmologists) but sometimes sufficient data cannot be obtained, as may be the case for rare conditions. In addition, an unbalanced distribution of characteristics, such as patient demographic characteristics, in the training data may result in poor performance in underrepresented populations. The new study in this issue of JAMA Ophthalmology by Burlina et al2 represents a key step toward combatting these challenges by applying cutting-edge, self-supervised, “low-shot” learning methods to improve performance in retina image classification under the conditions of few training examples.
Identify all potential conflicts of interest that might be relevant to your comment.
Conflicts of interest comprise financial interests, activities, and relationships within the past 3 years including but not limited to employment, affiliation, grants or funding, consultancies, honoraria or payment, speaker's bureaus, stock ownership or options, expert testimony, royalties, donation of medical equipment, or patents planned, pending, or issued.
Err on the side of full disclosure.
If you have no conflicts of interest, check "No potential conflicts of interest" in the box below. The information will be posted with your response.
Not all submitted comments are published. Please see our commenting policy for details.
Hunt MS, Kihara Y, Lee AY. Novel Low-Shot Deep Learning Approach for Retinal Image Classification With Few Examples. JAMA Ophthalmol. Published online September 03, 2020. doi:10.1001/jamaophthalmol.2020.3256
Coronavirus Resource Center
Customize your JAMA Network experience by selecting one or more topics from the list below.
Create a personal account or sign in to: