Collaborating Authors


IIT-Jodhpur researchers come up with deep learning-based cataract detection method


New Delhi, Apr 28 (PTI) Researchers at the Indian Institute of Technology (IIT) in Jodhpur have formulated a deep learning-based cataract detection method which is inexpensive and offers very high levels of accuracy. According to the research team, eye images acquired by low-cost near-infrared (NIR) cameras can aid in low-cost, easy-to-use and practical solutions for cataract detection. "The proposed multitask deep learning algorithm is inexpensive and results in very high levels of accuracy. This research presents a deep learning-based cataract detection method that involves iris segmentation and multitask network classification. The proposed segmentation algorithm efficiently and effectively detects non-ideal eye boundaries," said Richa Singh, Professor, Department of Computer Science and Engineering, IIT-Jodhpur.

Microsoft's Newest AI technology, "PeopleLens," is Helping Blind People See


The aim was to create a machine learning system to help blind people … They then used deep learning algorithms to train a computer vision model …

Deep learning algorithm shows accuracy in detecting glaucoma on fundus photographs


Automated deep learning analysis of fundus photographs showed high diagnostic accuracy in determining primary open-angle glaucoma, with increased ability to detect glaucoma earlier than human readers. A deep learning (DL) algorithm was trained, validated and tested on the fundus stereophotographs of participants enrolled in the Ocular Hypertension Treatment Study (OHTS), a randomized clinical trial evaluating the safety and efficacy of IOP-lowering medications in preventing progression from ocular hypertension to primary open-angle glaucoma (POAG). Assessment of optic disc and visual field changes in the OHTS was performed by two reading centers and a masked committee of glaucoma specialists, "a demanding, laborious and complicated task," according to the authors. The OHTS data set consisted of fundus photographs from 1,636 participants, of which 1,147 were included in the training set, 167 in the validation set and 322 in the test set. The DL model detected conversion to POAG with high diagnostic accuracy, suggesting that artificial intelligence can offer a reliable tool to automate the determination of glaucoma for clinical trial management, simplifying the process of human interpretation and, possibly, making it more standardized, objective and accurate.

AI Detects Diabetic Retinopathy in Real-Time


By 2050, the National Institute of Health (NIH) National Eye Institute estimates that 14.6 million Americans will have diabetic retinopathy. A new study published in The Lancet demonstrates how artificial intelligence (AI) machine learning can screen in real-time for diabetic retinopathy--a leading cause of preventable blindness, particularly in areas with low-income or middle-income economies. According to the Centers for Disease Control (CDC), one in four American adults with vision loss reported anxiety or depression. Moreover, vision loss has been linked to fear, anxiety, worry, social isolation, and loneliness. Scientists affiliated with Google Health and their collaborators applied artificial intelligence (AI) machine learning to detect one of the most common causes of preventable blindness--diabetic retinopathy.

Deep learning analysis detects diabetic retinopathy on ultra-widefield scanning laser …


During her talk at Angiogenesis, Dr. Loewenstein outlines how artificial intelligence could revolutionize diabetic retinopathy screening.


AAAI Conferences

We proposed a deep learning method for interpretable diabetic retinopathy (DR) detection. The visual-interpretable feature of the proposed method is achieved by adding the regression activation map (RAM) after the global averaging pooling layer of the convolutional networks (CNN). With RAM, the proposed model can localize the discriminative regions of an retina image to show the specific region of interest in terms of its severity level. We believe this advantage of the proposed deep learning model is highly desired for DR detection because in practice, users are not only interested with high prediction performance, but also keen to understand the insights of DR detection and why the adopted learning model works. In the experiments conducted on a large scale of retina image dataset, we show that the proposed CNN model can achieve high performance on DR detection compared with the state-of-the-art while achieving the merits of providing the RAM to highlight the salient regions of the input image.

Deep learning applications in clinical ophthalmology - PubMed


Rapid advances in retinal imaging technology combined with deep learning approaches for image analysis have provided new avenues of investigation in ophthalmic disease. First, deep learning provides a de novo approach to image analysis, identifying previously unrecognized imaging features that correlate with functional changes. In age-related macular degeneration (AMD), deep learning approaches identified subtle retinal features, hyporeflective outer retinal bands in the central macula, that are associated with delayed rod-mediation dark adaptation, a functional biomarker of early AMD. Second, deep learning allows prediction of clinical outcomes such as visual field progression in glaucoma. Lastly, deep learning models can also be used to segment anatomic features from ophthalmic imaging, enabling accurate and fully automated periorbital measurements with many potential clinical applications in oculoplastics.

Your eyes hold the key to your true biological age, study finds


The eyes may offer a "window into the soul," as poets say, but they also have a lot to say about your health. Dry eyes can be a sign of rheumatoid arthritis. High levels of cholesterol can cause a white, gray or blue ring to form around the colored part of your eye, called the iris. A coppery gold ring circling the iris is a key sign of Wilson's disease, a rare genetic disorder that causes copper to build up in the brain, liver and other organs, slowing poisoning the body. And that's not all: Damage to blood vessels in the back of your eye, called the retina, can be early signs of nerve damage due to diabetes, high blood pressure, coronary artery disease, even cancer, as well as glaucoma and age-related macular degeneration.

Global explainability in aligned image modalities Artificial Intelligence

Deep learning (DL) models are very effective on many computer vision problems and increasingly used in critical applications. They are also inherently black box. A number of methods exist to generate image-wise explanations that allow practitioners to understand and verify model predictions for a given image. Beyond that, it would be desirable to validate that a DL model \textit{generally} works in a sensible way, i.e. consistent with domain knowledge and not relying on undesirable data artefacts. For this purpose, the model needs to be explained globally. In this work, we focus on image modalities that are naturally aligned such that each pixel position represents a similar relative position on the imaged object, as is common in medical imaging. We propose the pixel-wise aggregation of image-wise explanations as a simple method to obtain label-wise and overall global explanations. These can then be used for model validation, knowledge discovery, and as an efficient way to communicate qualitative conclusions drawn from inspecting image-wise explanations. We further propose Progressive Erasing Plus Progressive Restoration (PEPPR) as a method to quantitatively validate that these global explanations are faithful to how the model makes its predictions. We then apply these methods to ultra-widefield retinal images, a naturally aligned modality. We find that the global explanations are consistent with domain knowledge and faithfully reflect the model's workings.

Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution View Artificial Intelligence

The increasing availability of large collections of electronic health record (EHR) data and unprecedented technical advances in deep learning (DL) have sparked a surge of research interest in developing DL based clinical decision support systems for diagnosis, prognosis, and treatment. Despite the recognition of the value of deep learning in healthcare, impediments to further adoption in real healthcare settings remain due to the black-box nature of DL. Therefore, there is an emerging need for interpretable DL, which allows end users to evaluate the model decision making to know whether to accept or reject predictions and recommendations before an action is taken. In this review, we focus on the interpretability of the DL models in healthcare. We start by introducing the methods for interpretability in depth and comprehensively as a methodological reference for future researchers or clinical practitioners in this field. Besides the methods' details, we also include a discussion of advantages and disadvantages of these methods and which scenarios each of them is suitable for, so that interested readers can know how to compare and choose among them for use. Moreover, we discuss how these methods, originally developed for solving general-domain problems, have been adapted and applied to healthcare problems and how they can help physicians better understand these data-driven technologies. Overall, we hope this survey can help researchers and practitioners in both artificial intelligence (AI) and clinical fields understand what methods we have for enhancing the interpretability of their DL models and choose the optimal one accordingly.