Filter by input type
Select all
News
Pages
Events
Filter by category
Select all
AI ANALYTICS
Mobile Apps and Internet of Things
Advancement of science
big data
Connected communities
Coronavirus
Courses and training
DIAGNOSIS
Initial Editorial
Editorials
A world in the cloud
Events
Infographics
Artificial Intelligence and Science
IoT Apps
News
Digital platforms
Social networks
Review of scientific publications
Course Summary
Synopsis of essay
Overview of reference frames
Synopsis of recent publications
Use of Digital Platforms
Study on accuracy assessment of deep learning in medical image analysis was published

The article "Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis" published in Nature, presents an assessment of the diagnostic accuracy of deep learning through the review of more than 11,921studies related to the topic.

Deep learning (DL), one of the subfields of Artificial Intelligence, is capable of changing medical diagnoses as we know them. However, despite advances in science, its diagnostic accuracy is still uncertain. The objective of the aforementioned study was to "evaluate the diagnostic accuracy of DL algorithms to identify pathology in medical imaging."

"Successful integration of DL technology into routine clinical practice relies upon achieving diagnostic accuracy that is non-inferior to healthcare professionals. In addition, it must provide other benefits, such as speed, efficiency, cost, bolstering accessibility and the maintenance of ethical conduct," the authors explain about the use of deep learning in medical practice.

By searching for articles related to deep learning in the Medline and EMBASE databases, they identified more than 11,000 studies, of which 503 were finally systematically reviewed.

"Eighty-two studies in ophthalmology, 82 in breast disease and 115 in respiratory disease were included for meta-analysis. Two hundred twenty-four studies in other specialities were included for qualitative review. Peer-reviewed studies that reported on the diagnostic accuracy of DL algorithms to identify pathology using medical imaging were included," the authors explain.

Across specialty areas the results show different outcomes, "Terminology and outcome measures was noted. This can lead to an overestimation of the diagnostic accuracy of DL algorithms on medical imaging," they acknowledge.

Finally, the authors comment that the rapid development of AI- or DL-based technologies has great potential in healthcare, especially in radiology. "This systematic review and meta-analysis appraised the quality of the literature and provided pooled diagnostic accuracy for DL techniques in three medical specialities," they conclude.

Read the full text at the following link: https://www.nature.com/articles/s41746-021-00438-z

Related Content

Secured By miniOrange