For the first time, artificial intelligence accurately diagnoses breast cancer

This is a world first! The AI ​​algorithm has been clinically validated in breast cancer detection for a wide range of specific subtypes.

The study published in the journal npj breast cancer from nature, It is the product of a collaboration between Institut Curie in France and Ibex Medical Analytics, a leader in AI-assisted cancer diagnosis. It is the first to present an algorithm capable of accurately detecting several pathological features in breast biopsies (or tissue samples).

Quick and objective help for pathologists

With more than 2.2 million new cases in 2020, the breast cancer It is the most common malignant disease in the world. Usually, the diagnosis of this type of cancer is determined after histological examination of breast biopsy specimens, which can be tedious and subjective and thus a source of error. Moreover, the number of pathologists has decreased in recent years, while the overall incidence of breast cancer has increased. ” Therefore, there is an increasing need for automated solutions and decision support tools for pathologists to detect cancers faster and with the highest accuracy. Reports statment from the Curie Institute. The system was developed for intervention to support the medical profession.

I was impressed with the results of the study, and the very high levels of accuracy and breadth of detection capabilities offered by the AI ​​technology

Concretely, the AI ​​algorithm was trained to identify 51 breast characteristics using methods Deep learning, over hundreds of thousands of sample images. Next, the search focused on 841 whole slice images from breast biopsies. An AI algorithm analyzed these images and the results were evaluated against a consensus diagnosis made by two pathologists. ” I was impressed with the results of the study, and the very high levels of accuracy and breadth of detection capabilities it provides Artificial intelligence technologysimilar to experts in pathology said Stuart Schnett, MD, professor of pathology at the University of Michigan Harvard Medical School He co-authored the study.

See also  Study proves that the brain is responsible for obesity

Distinguish between different types of breast cancer

Different types of breast cancer have been identified by AI, including rare subtypes. For example, the system distinguishes invasive breast cancer of the non-specific type from invasive/invasive lobular carcinoma, which accounts for 70% and 10–15% of all cases, respectively. breast tumors invasive. But the AI ​​algorithm also found rare types such as metaplastic or myxomatous carcinomas. In addition, it made it possible to identify tumor-infiltrating lymphocytes (TILs), biomarkers of lymphocyte-dominant breast cancers.

We are pleased with this collaboration, which has enabled some pathologists from the Curie Institute to gain first-hand experience with this AI tool. said Anne-Vincent Salomon, MD, chair of the department of pathology at the Institut Curie and professor at the Paris University of Sciences and Letters. ” to me In the long term, this will allow us to improve diagnosis, speed up treatment decisions, and ultimately improve care for our patients. »

Leave a Reply

Your email address will not be published.