Robots May Soon Help Doctors Accurately Diagnose Breast Cancer on Imaging

Highlights:

Artificial intelligence (IntelliScan) may soon help in earlier and more accurate diagnosis of breast cancer lesions, significantly improving patient prognosis in the UK
Missed or delayed diagnosis is a major cause of mortality in the UK accounting for about 20 percent of cancer deaths in the UK.

Artificial intelligence may change the face of breast cancer diagnosis in the UK through more accurate and earlier detection of breast cancer lesions on MRI scans.

In a two-year experiment, thousands of breast scans from all the MRI machines across the UK will be analyzed. Using advanced cutting edge technology robots (artificial intelligence) will be taught how to accurately spot breast cancer lesions, aiming to improve diagnosis and patient outcome.

Artificial Intelligence in Healthcare - An Overview
Artificial intelligence (AI) in healthcare is the discipline using data intensive computer based solutions to improve patient care and outcome.

‘IntelliScan System will help radiologists report a higher number of MRI scan images much faster and more precisely, helping to save patient’s lives by earlier diagnosis and treatment.’

Tweet it Now

Why Use Artificial Intelligence In Breast Cancer Diagnosis

Despite several advances in cancer diagnosis and treatment, missed or late diagnosis still accounts for a major share of cancer related deaths in the UK.

Scientists in the UK hope and believe that employing artificial intelligence systems such as the IntelliScan will overcome the gaps in the existing system and result in improved diagnosis and survival of cancer patients.

The current two-year project, estimated to cost around £830,000 will be funded by Innovate UK, and hopes to completely change the way NHS UK uses MRI scans to diagnose breast cancer.

How IntelliScan Works

IntelliScan, the artificial intelligence system is being developed by Brunel University Innovation Center, London, First Option Software and Teesside University. It combines deep machine learning and advanced image-processing smart algorithms to correctly detect breast cancer lesions on MRI scans. In addition the system also incorporates cloud hosting and remote data processing.

IntelliScan will automatically flag up what it learns (through deep machine learning) to perceive as abnormal lesions and categorize them by severity in every case
Radiologists reporting the scans will be able to handle many more scans more accurately and much faster resulting in early diagnosis and treatment
Once the system is fully developed, the plan is to link it to MRI machines across UK and integrate it into the healthcare system
Hospital radiographers and radiologists will automatically obtain digitally advanced images and reports reducing reporting time and improving diagnostic accuracy
IntelliScan will also help in assessing response to treatment by comparing pre and post-treatment scans resulting in best possible healthcare delivery to the patient.

“The technique will provide unique information to support doctors during the diagnostic process,” said Brunel’s Sergio Malo. “And the machine learning algorithm will use the doctors’ feedback for further training and for continuous improvement of the detection tool across the UK.”

According to Professor Tat-Hean Gan, Brunel Innovation Centre’s director “The system integrates a series of visualisation, data processing, data communication and decision-support systems which will enable it to dramatically improve access to breast healthcare and cancer treatment compliance,”.

What Is Artificial Intelligence and Deep Machine Learning and Advanced Image Processing?

Artificial intelligence is intelligence shown by a machine as against natural intelligence exhibited by humans and other animals.

Deep machine learning is a method employed to teach a computer to perform human-like tasks, such as voice recognition, identifying images and spotting abnormalities and making predictions. Instead of a set of predefined programs which is the practice in computers, deep learning establishes basic criteria and parameters about the inputted data and gradually by trains the computer to learn to respond and make decisions in its own by processing the information entered and recognizing specific patterns at several levels.

Advanced imaging processing refers to classifying and identifying abnormalities in visual images by artificial intelligence systems based on specific criteria which the machine learns to interpret from entered data (images in this case).

Reference:

Robots learn to help doctors spot breast cancer - (https://phys.org/wire-news/282562098/robots-learn-to-help-doctors-spot-breast-cancer.html)

Source-Medindia