New study suggests artificial intelligence could significantly improve breast cancer screening

A new Swedish study published on Wednesday suggests that Artificial Intelligence could be useful in breast cancer screening.

After the world of art and cinema, now it’s the turn of the medical sector. Artificial Intelligence could be useful in medicine, and in breast cancer screening in particular, at least that’s the conclusion of a study published this Wednesday in the specialist journal The Lancet Oncology.

Carried out in Sweden on some 80,000 women divided into two groups, the study tested the performance of Artificial Intelligence by performing a mammogram, a classic breast cancer screening test.

The first group of patients was examined by two radiologists, and the second by a single radiologist, assisted by AI. The AI-assisted group performed no worse: in fact, slightly more cancers were detected.

With only one radiologist needed in the AI-assisted procedure, the use of this technology could potentially halve the workload of these doctors.

These results are promising, as screening is widely considered to be one of the main ways of combating breast cancer.

Breast cancer is not only the most common cancer among women, but also the most deadly. According to the latest epidemiological data from Morocco, unveiled on January 21 on the occasion of the first National Cancer Registry Day under the theme “Cancer Surveillance in Morocco – Past, Present and Future”, the most frequently diagnosed cancer is lung cancer in men and breast cancer in women.

Moreover, experts in Morocco are warning of a steady rise in the number of cancers, which now exceeds 50,000 cases a year, compared with 48,000 cases in 2019.

This digitized invention will revolutionize medicine, cutting the workload of professionals in half, and ensuring a better diagnosis in a shorter time.

For all that, it’s too early to conclude on the real interest of AI in the field: it will take several years to find out whether it has been as effective as a double human opinion. To do this, the researchers will compare in two years’ time the rate of cancers that will have escaped screening but will have been diagnosed in the meantime.

These initial data also leave us uncertain about the risk of “over-diagnosis”, i.e. the detection of lesions that would not have developed into dangerous cancers without treatment.

This question of overdiagnosis is at the heart of certain criticisms of the merits of generalized screening, even though research increasingly clearly confirms its value in reducing breast cancer mortality.

The risk of overdiagnosis “should encourage caution in interpreting the results”, warned oncologist Nereo Segnan, a stranger to the study, in a commentary for Lancet Oncology, while acknowledging its promising nature.

Young Moroccan students at the Ecole Mohammedia d’Ingénieurs (EMI) are in the process of bringing to market the first intelligent scanner for early and efficient diagnosis of breast cancer.