Just as the ability to 'capture the moment' counts in fine art photography, the experience of the radiologist has made all the difference in visualising scar tissue in the heart during cardiac MRI scans. An invention by Italian scientists promises to revolutionise this fundamental diagnostic practice, making it accurate at the first 'click' thanks to artificial intelligence. The software, called "THAITI", was developed and patented by an interdisciplinary team consisting of Daniela Besozzi and Daniele M. Papetti from the University of Milano-Bicocca, Marco S. Nobile from the Ca' Foscari University in Venice and Camilla Torlasco from the IRCCS Istituto Auxologico Italiano in Milan.
Its value was recognised by the Global Conference on Cardiovascular Magnetic Resonance (CMR 2024), which awarded the Italian invention first prize in the Shark Tank competition, judging THAITI to be "innovative, of clinical impact, with translational value and ready for commercialisation". The model, which is patented in Italy and internationally, is now seeking investment thanks to the collaboration of the technology transfer offices of the University of Milano-Bicocca, Ca' Foscari University and the Istituto Auxologico Italiano.
The software is able to calculate the optimal value of the so-called 'inversion time', a parameter required for the acquisition of images aimed at identifying the possible presence of scar tissue in the heart after the administration of a contrast agent. As the inversion time is closely related to the amount of contrast present in the heart, it is different for each patient and its optimal value varies repeatedly during the same examination. Normally, the operator selects and modifies the inversion time in a process guided by experience and based on the appearance of the previous image and the characteristics of the patient. THAITI uses an artificial intelligence model, based on the patient's physiological and anthropometric information and the technical information about the examination, to determine the optimal, personalised and dynamic inversion time to obtain a series of high-quality images of the cardiac tissue throughout the MRI examination.
Our invention," explains Camilla Torlasco, cardiologist and coordinator of the Cardiac Magnetic Resonance Service at the Istituto Auxologico Italiano, "optimises the quality of the images obtained and is therefore a valuable tool to support diagnosis. In addition, THAITI streamlines the workflow, reduces operator fatigue and improves the patient experience.
"THAITI is a tool for applying a precision medicine approach," explains Daniele M. Papetti, researcher at the University of Milano-Bicocca, "because the turnaround time is calculated using the specific characteristics of each patient. In addition, THAITI guarantees the possibility of obtaining images of uniform quality, which facilitates the reproducibility of examinations and their results".
The prototype is at an advanced stage of development. The basic functionalities of THAITI have been fine-tuned,' says Marco S. Nobile, Professor of Computer Science at Ca' Foscari University, 'it remains to perfect the user interface and ensure the scalability of the system, which must be able to respond in real time to a large number of requests, potentially from all over the world.
The software does not require any investment in instrumentation to use, a user licence is sufficient. "This aspect," adds Daniela Besozzi, Professor of Computer Science at the University of Milano-Bicocca, "not only facilitates the adoption of THAITI, but also makes it a solution of particular impact both for low or lower middle income countries, where the diffusion of cardiac MRI is also limited by the difficulty of providing adequate training to radiology operators, and for low volume or recently opened cardiac MRI centres.
Cardiac MRI is a fundamental examination for the evaluation of ischaemic heart disease and cardiomyopathies, situations in which the presence and characteristics of possible scar tissue are essential for diagnostic and prognostic purposes and to guide the clinical management of patients. In addition, cardiac MRI can be used to accurately study congenital heart disease, diseases of the pericardium and aorta and, to a lesser extent, the valvular system. THAITI has been trained in a variety of cardiovascular diseases to ensure maximum generalisability.