Artificial intelligence promising for CA, retinopathy diagnoses

December 12, 2017

(HealthDay)—A deep learning algorithm can detect metastases in sections of lymph nodes from women with breast cancer; and a deep learning system (DLS) has high sensitivity and specificity for identifying diabetic retinopathy, according to two studies published online Dec. 12 in the Journal of the American Medical Association.

Babak Ehteshami Bejnordi, from the Radboud University Medical Center in Nijmegen, Netherlands, and colleagues compared the performance of automated deep learning algorithms for detecting metastases in hematoxylin and eosin-stained tissue sections of of women with with pathologists' diagnoses in a diagnostic setting. The researchers found that the area under the receiver operating characteristic curve (AUC) ranged from 0.556 to 0.994 for the algorithms. The lesion-level, true-positive fraction achieved for the top-performing algorithm was comparable to that of the pathologist without a time constraint at a mean of 0.0125 false-positives per normal whole-slide image.

Daniel Shu Wei Ting, M.D., Ph.D., from the Singapore National Eye Center, and colleagues assessed the performance of a DLS for detecting referable diabetic retinopathy and related eye diseases using 494,661 retinal images. The researchers found that the AUC of the DLS for referable diabetic retinopathy was 0.936, and sensitivity and specificity were 90.5 and 91.6 percent, respectively. For vision-threatening diabetic retinopathy, the AUC was 0.958, and sensitivity and specificity were 100 and 91.1 percent, respectively.

"In this evaluation of retinal images from multiethnic cohorts of patients with diabetes, the DLS had and specificity for identifying and related eye diseases," Ting and colleagues write.

Several authors from the Bejnordi study disclosed financial ties to the pharmaceutical and medical device industries. Several authors from the Ting study hold patents related to the system used in the study.

Abstract/Full Text -
Ting (subscription or payment may be required)

Explore further: Study examines use of deep machine learning for detection of diabetic retinopathy

More information: Abstract/Full Text - Benjordi (subscription or payment may be required)
Editorial (subscription or payment may be required)

Related Stories

Study examines use of deep machine learning for detection of diabetic retinopathy

November 29, 2016
In an evaluation of retinal photographs from adults with diabetes, an algorithm based on deep machine learning had high sensitivity and specificity for detecting referable diabetic retinopathy, according to a study published ...

Will 'AI' be part of your health-care team?

December 12, 2017
(HealthDay)—Artificial intelligence is assuming a greater role in many walks of life, with research suggesting it may even help doctors diagnose disease.

New screening tool can identify diabetic retinopathy

October 16, 2017
(HealthDay)—A new screening tool can adequately detect risk of diabetic retinopathy in adults with diabetes in low-income communities in Mexico, according to a study published in the October issue of Preventing Chronic ...

UWF retinal imaging process could reduce practice burden

June 5, 2015
(HealthDay)—Real-time ultrawide field (UWF) retinal image evaluation by nonphysician imagers can accurately detect diabetic retinopathy (DR) and help reduce center image grading burden, according to a study published online ...

Researchers use deep learning to create an algorithm to detect a common diabetic eye disease

April 28, 2017
Researchers from the Byers Eye Institute at Stanford University have found a way to use artificial intelligence to fight a complication of diabetes that affects the eyes. This advance has the potential to reduce the worldwide ...

Risk of falls up with mild, moderate diabetic retinopathy

November 19, 2017
(HealthDay)—Among Asians, individuals with mild and moderate diabetic retinopathy (DR) are more likely to have fallen, and greater perceived barriers to diabetes self-management (DSM) are associated with the severity of ...

Recommended for you

Study advances gene therapy for glaucoma

January 16, 2018
While testing genes to treat glaucoma by reducing pressure inside the eye, University of Wisconsin-Madison scientists stumbled onto a problem: They had trouble getting efficient gene delivery to the cells that act like drains ...

New study offers added hope for patients awaiting corneal transplants

January 9, 2018
New national research led by Jonathan Lass of Case Western Reserve University School of Medicine has found that corneal donor tissue can be safely stored for 11 days before transplantation surgery to correct eye problems ...

Diabetic blindness caused and reversed "trapped" immune cells in rodent retinas

January 3, 2018
Johns Hopkins researchers have discovered a cell signaling pathway in mice that triggers vision loss in patients with diabetic retinopathy and retinal vein occlusion – diseases characterized by the closure of blood vessels ...

Ophthalmologists increasingly dissatisfied with electronic health records

December 29, 2017
Ophthalmologists' use of electronic health records (EHR) systems for storing and accessing patients' medical histories more than doubled between 2006 and 2016, while their perceptions of financial and clinical productivity ...

Higher omega-3 fatty acid intake tied to lower glaucoma risk

December 26, 2017
(HealthDay)—Increased daily intake of ω-3 fatty acids is associated with lower odds of glaucoma, but higher levels of total polyunsaturated fatty acid (PUFA) intake are associated with higher odds of developing glaucoma, ...

Protein analysis allows for treatment of eye-disease symptoms with existing drugs

December 21, 2017
Demonstrating the potential of precision health, a team led by a researcher at the Stanford University School of Medicine has matched existing drugs to errant proteins expressed by patients with a rare eye disease.

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.