Project description
Artificial intelligence system increases colorectal polyp detection rates
According to the World Cancer Research Fund, colorectal cancer is the third most frequent form of cancer worldwide. Traditionally, colorectal cancer screening takes place through colonoscopy. Despite technological advancements to improve visualisation and resolution, there are still procedural limitations, which may leave up to 20 % of polyps undetected. This leads to more than 44 500 cases of preventable cancer in Europe every year. The EU-funded MagentiqEye project has developed an automatic polyp detection system that works as an additional eye, highlighting any polyps that appear on the physician's screen during examination. Using deep learning and computer vision techniques, this artificial intelligence system could greatly improve the quality and performance of colonoscopy tests.
Objective
The World Cancer Research Fund estimates the colorectal cancer to be the third-most
occurring form of cancer around the world. In 2012, more than 1 Million people were
diagnosed with colorectal cancer. These incidences of colorectal cancer have boosted demand
for their diagnostics worldwide. In fact, colon cancer screening has increased greatly in first
world countries with mature health care delivery systems. Despite this progress the problem
of undetected or missed polyps during colonoscopy procedures remains a significant problem:
about 8 -10% of the CR cancer cases, resulting in more than 44,500 of preventable cancer in
Europe annually. MagentiqEye has developed an Automatic Polyp Detection System (the
APDS) which uses mainly Deep Learning and Computer Vision techniques in order to detect
the polyps which appear on the physician screen during the test. APDS is an AI system which
works as additional eye, helping doctors to detect polyps. This decision support system can
improve the quality and performance (less miss-rete) of the colonoscopy test, having a high
impact in the prevention of cancer. MagentiqEye seeks funding to conduct a feasibility study
to prove technical and commercial viability, conducting an analytical exercise to position the
product. The objective is to test the economic viability of the system among a larger pool of
potential clients (user-acceptance), and to assess if the chosen commercialisation approach
will be conducive of the projected growth on the European level.
Fields of science (EuroSciVoc)
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques.
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques.
- social sciencessociologydemographymortality
- natural sciencescomputer and information sciencesartificial intelligencecomputer vision
- medical and health sciencesclinical medicineoncologycolorectal cancer
- natural sciencescomputer and information sciencesartificial intelligencemachine learningdeep learning
You need to log in or register to use this function
Programme(s)
Funding Scheme
SME-1 - SME instrument phase 1Coordinator
3541416 HAIFA
Israel
The organization defined itself as SME (small and medium-sized enterprise) at the time the Grant Agreement was signed.