3 Silver

Medical Image Recognition Using Deep Learning

Image recognition of the human body is expected to improve and help doctors improve medical diagnostics. Machine learning related to image recognition of diseased / not diseased organs can minimize possibilities of medical errors. In addition, deep learning with image recognition can be used to recognize certain disease and diagnostic patterns within the body in order to enhance and speed up disease diagnosis. This is important in many cases because a delay in diagnosis means delays in treatment.

Deep learning methods are a set of algorithms in machine learning, which try to automatically learn multiple levels of representation and abstraction that help understand the data. It has been used with huge amount of different types of group of techniques: supervised and unsupervised models.  Both groups automatically extract complex representation and patterns from the data. These algorithms are largely motivated by the field of artificial intelligence, which has overall proposition of emulate the human brain’s ability to observe, analyze, learn, and make decisions, especially for extremely complex problems.

In this Knowledge Sharing article – awarded Best of Applied Analytics in the 2017 Knowledge Sharing Competition – Ronaldo Lopes, Mauro Damo, William Schneider, and Wei Lin

• review methods and techniques of Deep Learning

• use these techniques in a study over a dataset of human body images

• apply the mentioned machine learning techniques using open source tools, which, for this article, Python was chosen      

The authors present a solid case that medical imaging technologies will play a key role in the future of medical diagnosis and therapeutics in the near future.

Read the full article here

0 Kudos