…. thanks to a Centro Diagnostico Italiano (CDI) and Bracco Imaging project
The CDI project is called the “AI-for-COVID Imaging Archive”, which is already openly available online for the entire international scientific community. At the heart of the project is an innovative digital platform that gives doctors and healthcare professionals access to a database of radiographic images of COVID patients. By applying artificial intelligence for diagnostic purposes, the project enables doctors to obtain a clearer understanding of the progress of COVID-19 in patients, which makes for better triage in hospitals and facilitates the delivery of personalized and timely treatments.
The platform has been developed as part of an all-Italian project called AI-for-COVID promoted by Centro Diagnostico Italiano (CDI Italian Diagnostic Centre – Bracco Group healthcare services). CDI, which has been working in the fields of Radiomics and Genomics for some time, is running the project in collaboration with Bracco Imaging and several major public and private clinics and research institutes. Specifically, CDI has availed itself of the assistance of the following prominent and highly reputed treatment and research hospitals (IRCCS), public-sector local hospitals (ASST) and research institutes: Fondazione IRCCS Ca’ Granda Ospedale Maggiore Policlinico (Milan), Fondazione IRCCS Policlinico San Matteo (Pavia), Azienda ospedaliero-universitaria Careggi (Florence), ASST Santi Paolo e Carlo (Milan), ASST Fatebenefratelli-Sacco (Milan), and ASST Ospedale San Gerardo (Monza), and Ospedale Casa Sollievo della Sofferenza (S.G.Rotondo).
PREDICTIVE DIAGNOSTIC IMAGING THROUGH RADIOMICS
As Sergio Papa, director of diagnostic imaging at CDI, explains: “Radiological imaging is playing a crucial role in diagnosing COVID-19 patients and determining treatment options. Effectively, what we have done is to recruit Radiomics (which, along with Genomics, represents the new frontier of personalized medicine) into the battle against this terrible pandemic by putting valuable medical data at the disposition of all doctors and hospitals. Diagnostic imaging generates a vast volume of data that, thanks to the power of artificial intelligence, can be correlated to the clinical development and course of the disease. Our AI-for-COVID project has given a fresh impulse to our research into the pathology caused by COVID, with particular regard to the damage it causes the lungs, and is helping us to implement targeted measures for patients whose pre-existing conditions render them more susceptible to the deleterious effects of the disease.”
MORE THAN 800 X-RAYS ALREADY UPLOADED TO THE “AI-FOR-COVID IMAGING ARCHIVE”
By referencing the AI-For-Covid Imaging Archive, doctors can make use of chest X-rays taken upon hospital admission to identify which patients are at greatest risk of pulmonary deterioration and therefore most liable to require mechanical ventilation. In other words, artificial intelligence provides a practical tool for predictive diagnostic imaging. The open-access platform, which is already available for the entire international scientific community at the URL aiforcovid.radiomica.it, currently contains over 800 chest X-ray images that are associated with critical clinical information acquired at the same time as the X-rays were taken.
THE ROLE OF ISTITUTO ITALIANO DI TECNOLOGIA (IIT) OF GENOA AND UNIVERSITÀ CAMPUS BIO-MEDICO OF ROME IN THE DEVELOPMENT OF THE ALGORITHMS
Istituto Italiano di Tecnologia (IIT: the Italian Institute of Technology) of Genoa, the Campus Bio-Medico University of Rome (UCBM) and the CDI and Bracco Imaging team analysed the data and developed the AI algorithms for the project, while Amazon Web Services (AWS) provided important help in setting up the digital platform. As part of its Diagnostic Development Initiative, AWS has supported the AI-for-COVID project, recognizing it as one of the most innovative international initiatives of its type. The platform incorporates a range of AWS technologies, including the machine-learning and artificial intelligence capabilities of Amazon SageMaker, a fully managed service for creating, training and deploying machine learning models, as well as for data processing and analytics.
THE RADIOLOGISTS OPINION
Prof. Lorenzo Preda, Director of the Radiology Department at the Ospedale San Matteo di Pavia, says: “Joint efforts between the San Matteo in Pavia and the other hospitals in the network coordinated by CDI-Bracco has, in a very short timeframe, made available input data acquired in the field for developing an extremely powerful AI system. The AIforCOVID Imaging Archive platform is another step in this sharing process.”
Michaela Cellina, a radiologist at Fatebenefratelli Sacco in Milan, says: “Throughout the COVID-19 pandemic, the role played by radiologists and radiological imaging techniques, particularly X-rays and CT, has been essential. Against the backdrop of our working conditions in 2020, with overcrowded emergency rooms and especially long processing times to get swab results back, radiological imaging proved to be a vital frontline tool for diagnosis and patient management. Because of the limited resources we had (and continue to have), with very few beds available for hospitalization, especially in intensive care, applying artificial intelligence tools capable of predicting patient outcomes from radiological examinations makes a real difference, enabling optimal management of patients and available resources. During this emergency, Italy’s radiologists have shown remarkable commitment. The development of multicentre studies and sharing data and direct clinical experience have markedly accelerated the development of effective weapons to fight this battle, one that we are still fighting.”
DIANA BRACCO, CHAIR AND CEO OF THE BRACCO GROUP, EXPRESSES HER SATISFACTION
Diana Bracco, Chair and CEO of the Bracco Group, declared, “I am delighted to see Centro Diagnostico Italiano working on this project alongside Bracco Imaging and many other public and private clinics and research institutes. Thanks to the application of artificial intelligence to diagnostic imaging, a sector in which we are a world leader, we have been able to contribute to the fight against the pandemic. In the area of Big Data and Radiomics, CDI has always been at the forefront, leading the way in applying pioneering techniques for analysing radiological data and integrating them with genomic and histopathological data. Successful research nowadays entails integrating the knowledge of scientists from several different fields and adopting a multidisciplinary approach that is not circumscribed by cultural boundaries.”
SCIENTIFIC PAPER ALREADY AVAILABLE FOR CONSULTATION FROM CORNELL UNIVERSITY
The preliminary results of the CDI-Bracco Imaging research project are summarized in the article: “AIforCOVID: predicting the clinical outcomes in patients with COVID-19 applying AI to chest-X-rays. An Italian multicentre study”, which is available in preview as an open-access document at the Cornell University website.