Artificial intelligence is growing tremendously in the health sector. There were various other findings which has shown contribution of artificial intelligence in the health sector. Another recent finding claims that artificial intelligence can help diagnose prostate cancer better. The researchers of the study have developed a new artificial system which may improve the detection of prostate cancer in the coming years.
The system is named as FocalNet, which can identify the aggressiveness of the disease with the help of magnetic resonance imaging or MRI scans.
The researchers of the study at the University of California, Los Angeles (UCLA) in the US cliamed that it gives nearly the same level of accuracy as experienced radiologists.
During the testing of the new system, the results were impressive. MRI scans of 417 men with prostate cancer were analysed by FocalNet. The study was published in the journal IEEE Transactions on Medical Imaging which states that FocalNet was 80.5 per cent accurate in reading MRIs, while radiologists with at least 10 years of experience were 83.9 percent accurate.
During a manual detection with MRI, it takes thousands of tests to determine whether the tumor is cancerous or not and the grade of the cancer. But FocalNet uses an algorithm that comprises of million trainable variables. It is a neural network.
In the end the researchers compared the results of the new AI system with the readings by radiologists who had more than 10 years of experience. The research concluded that the new system can save time and give accurate results at the same time.
Read more articles on Health News.
All possible measures have been taken to ensure accuracy, reliability, timeliness and authenticity of the information; however Onlymyhealth.com does not take any liability for the same. Using any information provided by the website is solely at the viewers’ discretion. In case of any medical exigencies/ persistent health issues, we advise you to seek a qualified medical practitioner before putting to use any advice/tips given by our team or any third party in form of answers/comments on the above mentioned website.