Detection of anaemia from retinal fundus images via deep
learning

Mitani, Akinori; Liu, Yun; Huang, Abigail E.; Corrado, Gregory S.; Peng, Lily; Webster, Dale R.; Hammel, Naama; Varadarajan, Avinash V.

doi:10.1038/s41551-019-0487-z

Cited by 158 publications

(112 citation statements)

References 49 publications

Supporting

Mentioning

108

Contrasting

Unclassified

Order By: Relevance

“…Instead, Grad-CAM generates a heat map corresponding to each image-level task label that highlights the regions of the input image that, in theory, are most indicative of that task label. This saliency method has been widely used for a variety of medical imaging tasks and modalities including but not limited to: visualizing the performance of a convolutional neural network in predicting (1) myocardial infarction 19 and hypogycemia 20 from electrocardiograms, (2) visual impairment 21 , refractive error 22 , and anaemia 23 from retinal photographs (3) long-term mortality 24 and tuberculosis 25 from chest x-ray images, and (4) appendicitis 26 , and pulmonary embolism 27 on computed tomography scans.…”

Section: Resultsmentioning

confidence: 99%

“…The copyright holder for this preprint this version posted March 2, 2021. ; https://doi.org/10.1101/2021.02.28.21252634 doi: medRxiv preprint 5 neural network in predicting (1) myocardial infarction 19 and hypogycemia 20 from electrocardiograms, (2) visual impairment 21 , refractive error , and anaemia 23 from retinal photographs (3) long-term mortality 24 and tuberculosis 25 from chest x-ray images, and 4appendicitis 26 , and pulmonary embolism 27 on computed tomography scans.…”

Section: Framework For Evaluating a Saliency Methods On Multi-label CLmentioning

confidence: 99%

See 1 more Smart Citation

Benchmarking saliency methods for chest X-ray interpretation

Saporta

Gui

Agrawal

et al. 2021

Preprint

View full text Add to dashboard Cite

Deep learning has enabled automated medical image interpretation at a level often surpassing that of practicing medical experts. However, many clinical practices have cited a lack of model interpretability as reason to delay the use of "black-box" deep neural networks in clinical workflows. Saliency maps, which "explain" a model's decision by producing heat maps that highlight the areas of the medical image that influence model prediction, are often presented to clinicians as an aid in diagnostic decision-making. In this work, we demonstrate that the most commonly used saliency map generating method, Grad-CAM, results in low performance for 10 pathologies on chest X-rays. We examined under what clinical conditions saliency maps might be more dangerous to use compared to human experts, and found that Grad-CAM performs worse for pathologies that had multiple instances, were smaller in size, and had shapes that were more complex. Moreover, we showed that model confidence was positively correlated with Grad-CAM localization performance, suggesting that saliency maps were safer for clinicians to use as a decision aid when the model had made a positive prediction with high confidence. Our work demonstrates that several important limitations of interpretability techniques for medical imaging must be addressed before use in clinical workflows.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Framework For Evaluating a Saliency Methods On Multi-label CLmentioning

confidence: 99%

Benchmarking saliency methods for chest X-ray interpretation

Saporta

Gui

Agrawal

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…We further interrogated the trained AI models using saliency maps [ 13 , 29 , 30 ], which highlight the regions of each radiograph that contribute most to the model’s prediction ( Supplementary Note 1 ), to determine specific confounds that deep convolutional networks for COVID-19 detection exploit. While our saliency maps sometimes highlight the lung fields as important ( Fig.…”

Section: Mainmentioning

confidence: 99%

AI for radiographic COVID-19 detection selects shortcuts over signal

DeGrave

Janizek

Lee

2020

Preprint

136

169

View full text Add to dashboard Cite

Artificial intelligence (AI) researchers and radiologists have recently reported AI systems that accurately detect COVID-19 in chest radiographs. However, the robustness of these systems remains unclear. Using state-of-the-art techniques in explainable AI, we demonstrate that recent deep learning systems to detect COVID-19 from chest radiographs rely on confounding factors rather than medical pathology, creating an alarming situation in which the systems appear accurate, but fail when tested in new hospitals.

show abstract

“…102 The same group has also developed a model to detect anemia from CFP with an AUC of 0.89, again training on images of the UK biobank study. 103 Although only providing proof of concept and lacking robust evaluation, these two examples show the potential benefit of telemedicine screenings for systemic disease evaluation in patients with DR. Oculomics, a term introduced for describing ocular biomarkers for systemic disease, could be of great interest in these systematic and ideally nationwide screenings. 104 Clinicians should, however, be aware, that many of the AI-related publications lack reporting standards.…”

Section: Different Imaging Approachesmentioning

confidence: 99%

<p>The Evolution of Diabetic Retinopathy Screening Programmes: A Chronology of Retinal Photography from 35 mm Slides to Artificial Intelligence</p>

Huemer¹,

Wagner²,

Sim³

2020

OPTH

View full text Add to dashboard Cite

As a third of people with diabetes mellitus (DM) will suffer the microvascular complications of diabetic retinopathy (DR) and therapeutic options can effectively prevent visual impairment, systematic screening has substantially reduced disease burden in developed countries. In an effort to tackle the rising incidence of DM, screening programmes have modernized in synchrony with technical and infrastructural advancements. Patient evaluation has shifted from face-to-face ophthalmologist-based review delivered through community grassroots to asynchronous store-and-forward modern telemedicine platforms commissioned on a nationwide scale. First pioneered with primitive 35-mm slide film retinal photography, the last decade has seen an emergence of high resolution and widefield imaging devices, which may reveal extents of DR indiscernible to the clinician but with implications of potential earlier identification. Similar progress has been seen in image analysis approachesautomated image analysis of retinal photographs of DR has evolved from qualitative feature detection to rules-based algorithms to autonomous artificial intelligence-powered classification. Such models have, relatively rapidly, been validated and are now receiving approval from health regulation authorities with deployment into the clinical sphere. In this review, we chart the evolution of global DR screening programmes since their inception highlighting major milestones in healthcare infrastructure, telemedicine approaches and imaging devices that have shaped the robust and effective frameworks recognised today. We also provide an outlook for the future of DR screening in the context of recent technological advancements with respect to their limitations in current times.

show abstract

Detection of anaemia from retinal fundus images via deep learning

Cited by 158 publications

References 49 publications

Benchmarking saliency methods for chest X-ray interpretation

Benchmarking saliency methods for chest X-ray interpretation

AI for radiographic COVID-19 detection selects shortcuts over signal

<p>The Evolution of Diabetic Retinopathy Screening Programmes: A Chronology of Retinal Photography from 35 mm Slides to Artificial Intelligence</p>

Contact Info

Product

Resources

About