Abstract
BackgroundArtificial intelligence (AI) is the recently advanced technology in machine learning which is increasingly used to help radiologists, especially when working in arduous conditions. Microsoft Corporation offered a free-trial service calling Custom Vision to develop AI for images.ResultsThis study included 161 prostate cancer images with 189 lesions from 52 patients. The 160-tag iteration presented the best performance: precision 20.0%, recall 6.3%, mean average precision (M.A.P.) 13.1%, and prediction rate 31.58%. The performance of a 1-h training was better than quick training, but was not different from a 2-h training.ConclusionHealth personnel can easily develop AI for the detection of prostate cancer lesions in MRI. However, the AI development is further required, and the result should be interpreted along with radiologist.
Highlights
Artificial intelligence (AI) is the recently advanced technology in machine learning which is increasingly used to help radiologists, especially when working in arduous conditions
The machine learning is a feature-based algorithm of the AI before the advent of deep learning (DL), which is the main algorithm for developing AI for medical imaging
Ten images with 19 Prostate cancer (PCa) lesions were tested in each iteration
Summary
Artificial intelligence (AI) is the recently advanced technology in machine learning which is increasingly used to help radiologists, especially when working in arduous conditions. Microsoft Corporation offered a free-trial service calling Custom Vision to develop AI for images. Artificial intelligence (AI), which is the recently advanced technology in machine learning, may improve CAD for radiology in clinical practice. AI recently causes concern that machine may replace human in the near future, these fears have occurred periodically among radiologists since the Microsoft Corporation introduced its cloud platform called Azure supplying over 100 services, some are freetrial and some are always free. Under the budgetconstrained situation in the authors’ hospital, an attempt was made to develop AI for detecting cancer lesions within MRI under “custom vision” which is one of the free-trial services from Azure. It was aimed to test the possibility of using this service; this is a pilot study conducted solely by clinicians with some guidance from one computer scientist
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
