- The use of AI algorithms to analyze the images of diagnostic tests in oncology translates into an improvement in the quality of life for the patient.
- It allows the interpretation time by the doctor to be reduced by up to 80% and to detect the patients who will best respond to a specific therapy.
- Based on the progress made, there is a commitment to achieve the first virtual biopsies over the next five years.
With the help of technology, what was previously only possible in science fiction movies is now possible. One of the most important advances can be seen with Artificial Intelligence and its ability to analyze large amounts of information in a matter of seconds. As a result the world is now on the verge of achieving the first virtual biopsies.
This important advance will be possible thanks to the union of two leading companies worldwide. In the first place is the Spanish Quibim (acronym for Quantitative Imaging Biomarkers In Medicine). It is dedicated to design and creation of pioneering tools that extract information from medical images. To achieve this, it uses Artificial Intelligence to accelerate diagnosis and identify possible diseases early. This increases the chances of survival and avoids more invasive therapeutic techniques for the patient.
As a main ally, it uses the cloud services of Microsoft Azure. In this way he has created a repository of more than 10 million anonymized medical images for some of the most relevant innovative projects and biobanks worldwide in pediatric cancer (Primage), prostate cancer (ProCancer-I) and even COVID-19 (Imaging COVID-19 AI).
The potential of Artificial Intelligence for medical diagnosis
Quibim, whose headquarters are in Valencia, and which also has offices and subsidiaries in Madrid, Barcelona, Cambridge (United Kingdom) and New York (USA), was founded with the ambition of making the medical imaging to become one of the catalysts for precision health. These tools provide objective results from image analysis and reduce physician interpretation time by up to 80%.
Faced with this scenario, the company sought create AI tools that analyze diagnostic images under the new concept of ‘medical imaging panel’. Especially in cases of lung and prostate cancerto identify these patients early to be treated at an earlier stage of the disease.
For example, with a model that, through chest CT analysis, determines whether the patient will respond to new immunotherapy treatments or know, from a prostate MRIif it will develop a relapse and metastasis in the next few years.
The Microsoft cloud, an effective tool for data centralization
Quibim has a global business strategy, which requires a modular, flexible cloud infrastructure fully prepared for mass scaling, capable of serving a large volume of customers located around the world. For this reason, the company uses a multi-tenant architecture, which optimizes resources and improves the security and reliability of both the environment and the clients.
As a cornerstone of its security strategy, the company has consolidated its on-premises access, identity, and management systems within Microsoft Azure Active Directory. Likewise, Application Gateway has been implemented to improve security in access to the platforms.
The orchestration and management of algorithms responsible for analyzing the different parts of the body (breast, brain, prostate, colon) are carried out in Azure Kubernetes Services. While the storage of medical images managed by Quibim. -more than 10 million-, is deployed in Azure Storage Accounts. Finally, Azure Webapps makes it easy to deploy web applications.
The future of preventive medicine
The next big challenge is create the largest biobank of medical images worldwidegenerating a universal and centralized repository of cases classified according to different variables, such as pathology, anatomical region or the technique used to obtain the image.
In the next 5 years, Quibim aims to introduce significant improvements in the care of thousands of patients -especially children- through diagnosis by means of virtual biopsies.
“We hope to be able to monitor patients closely, with a high degree of accuracy and without the need for a highly invasive procedure, avoiding hospital surgeries and the inconvenience of testing. This is the case of children, for whom, for ethical reasons, a normal biopsy cannot be performed, or in certain lung cancers, which, due to their location, become difficult to diagnose”, says Ángel Alberich-Bayarri, CEO and co-founder of Quibim.
Also read:
Artificial Intelligence and Radiology: trends for the health sector in 2022
K Health, the first medical video consultation app with Artificial Intelligence
How does Artificial Intelligence help to detect breast cancer?