In recent years, the telemedicine. Even the current pandemic has promoted this service due to the danger that physical contact implies in any medical care. Although one of the limitations of this modality is that it cannot be performed in all specialties. Precisely that motivated staff from the National Autonomous University of Mexico (UNAM) to innovate and allow remote gynecological consultations to be a reality.
In this way, now a gynecologist in a distant town will be able to take ultrasound images of a fetus and send them remotely to the Institute of Perinatology to know the health status of the baby before birth. It will all be thanks to a Artificial Intelligence software developed by the UNAM with experts from the National Institute of Perinatology and the UAM-Iztapalapa.
Fernando Arámbula Cosío, from the Institute for Research in Applied Mathematics and Systems (IIMAS), owner of the “Automatic system to support the evaluation, classification and assignment of risks in fetuses with growth disorders”, explains that this project will be ready in 2022 .
“The idea is, through image analysis, to produce a diagnosis. For example, blood supply in the fetal brain, with Dopler ultrasound images that directly measure the blood flow in the brain and the software analyzes it, an estimate is made and a comparison can be made of the normal flow against something abnormal, which already the expert will recommend ”.
What will remote gynecological consultations be like?
Also a routine measurement for gynecologists in order to determine the size of the femur through ultrasound, can be automatically analyzed by the program. The same goes for the head circumference and abdomen, which must be in a standard to reveal normal growth, but if they are not, the experts will decide what to do.
Arámbula Cosío and his team developed Artificial Intelligence algorithms that can also improve ultrasound images, several of which are difficult to interpret to improve the detection of organs, for example, the cerebellum.
The expert reported that they are currently developing an algorithm that can measure the fetal heart contractions, to estimate if it is healthy, “you can train an algorithm with normal contractions and when we record the video of a new fetus and see that the curve shrinks and expands, we could detect abnormalities with respect to the normal population ”.
At the moment, the expert and his group have developed different algorithms that solve each of these actions, but it remains to be integrated and put into a single system and a single server that has remote access, in addition to the ability to process the images for analysis. .
What does it take to move forward?
High performance computing. The specialist specified that each of the algorithms that work with Artificial Intelligence requires large computing capacities to make the system work correctly, so it would be beneficial for them to access the services that will be offered through the Alliance call.
In turn, Fabián Romo Zamudio, from the General Directorate of Computing and Information and Communication Technologies (DGTIC), -who does not participate in this project-, specified: soon several like this will be supported with computer equipment that the private company Huawei donated at the end of 2020 to the UNAM for the creation of a new Laboratory for Teaching, Research and Development in Artificial Intelligence and Data Science.
Romo Zamudio stated: “With this infrastructure, with support, the experience of researchers and university teachers, alternatives can be found for problems from health aspects, combating poverty, food supply, attention to the challenges of climate change. There are many areas in which artificial intelligence can support human development. First of all, UNAM vindicates its vision not only technological, but also humanist, by always having that human vision and how it can benefit society ”.