- 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.
may change the face of breast cancer diagnosis in the UK through more accurate
and earlier detection of breast cancer lesions on MRI scans.
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.
Why Use Artificial
Intelligence In Breast Cancer Diagnosis
several advances in cancer diagnosis and treatment, missed or late diagnosis
still accounts for a major share of cancer related deaths in the UK.
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
‘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.’
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 WorksIntelliScan,
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
algorithms to correctly detect breast
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
- 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.
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."
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
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
the information entered and recognizing specific patterns at several levels.
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).
- Robots learn to help doctors spot breast cancer - (https://phys.org/wire-news/282562098/robots-learn-to-help-doctors-spot-breast-cancer.html)