They create an algorithm for the detection of breast cancer

Last year, in the midst of a pandemic, the breast cancer caused the death of 6,821 women in Argentina. Global awareness campaigns regarding the conduct of medical studies emphasize that, if this pathology is detected in time, the patient has up to a 90% chance to survive in the next five years. It should be noted that doctors are unable to diagnose it in the 10% and the 30% of the cases.

Carolina Mondino, graduated from the Bioengineering career of the Buenos Aires Technological Institute (ITBA), developed a way of classify tumors on mammograms through the creation of a algorithm. It is a tool designed from artificial intelligence to assist doctors in the detection of breast cancer.

The research was carried out within the framework of a final degree project that sought to generate methodologies that allow the development of solutions for leading cause of death for women who contract cancer diseases.

The project was based on studies that showed that, from convolutional neural networks (CNN), a computer can automatically classify tumors in mammograms, according to type and severity of injury, that is, if they are benign O evil. For this to happen, the mammogram is first entered into the program so that it examines the tumors that are present in it (if any). Then the system returns the prediction of the type and the seriousness of the tumor.

The accuracy value obtained in the project was 70% for the severity of the injury. In the classification of calcifications or masses, promising results were obtained as the 90% accuracy, a value that is comparable to current published research. Even the accuracy obtained is higher than some of the published research.

Mondino’s project had the support of the bioengineer Matías Nazareth Tajerian as a tutor, who, in addition to being a graduate of ITBA, works as a developer at the Hospital Italiano de Buenos Aires. “The objective of this project is to be able to add the algorithm to a software so that health professionals can use it as a complementary tool ”, highlighted its creator.

The World Health Organization (WHO) recommends that all women over 40 years become one annual mammogram to be able to diagnose breast cancer early. Along these lines, the tool aims to help in rapid detection at the earliest possible stage in order to have the diagnosis and treatment. In this way, being able to reduce the rate of mortality for breast cancer in women.

Where does it originate?

Breast cancer starts in the cladding cells (epithelium) of the ducts (85%) or lobes (15%) of the glandular tissue of the sinuses. Initially, the cancerous tumor is confined to the duct or lobe (in situ), where it generally does not cause symptom and has minimal potential for spread (metastasis).

As time goes by, this cancer in situ (stage 0) can progress and invade the breast tissue surrounding (invasive breast cancer), and then spread to the lymph nodes nearby (regional metastasis) or to other organs of the body (distant metastasis). When a woman dies of breast cancer, it is as a result of the generalized metastasis.

The breast cancer treatment it can be very effective, particularly when the disease is caught early. Often it consists of a combination of surgical removal, radiation therapy, and medication (hormone therapy, chemotherapy, and / or targeted biological therapy) to treat microscopic cancer that has spread from the breast tumor through the blood. Therefore, this procedure, which can prevent the progression and spread of cancer, life jacket.