Swiss researchers use AI for breast cancer characterization
Published: Monday, Jul 22nd 2024, 16:50
Retour au fil d'actualité
Artificial intelligence (AI) is set to make the classification of breast cancer diagnoses more precise and cost-effective. Researchers at the Paul Scherrer Institute (PSI) and the Massachusetts Institute of Technology have developed an image analysis that can use AI to assess the stage of the disease.
The goal is to make the prognoses more reliable, the PSI in Villigen AG announced on Monday. Some tumors grow very slowly or hardly ever change stage from a rather harmless preliminary stage to a life-threatening form.
In women, there is a preliminary stage of breast cancer in the milk ducts, known as ductal carcinoma in situ. This form, known as DCIS for short, develops into a threatening invasive breast carcinoma in 30 to 50 percent of cases.
As DCIS is highly curable, doctors would generally recommend treatment. According to PSI, doctors have so far lacked evidence to reliably decide which tumor will remain harmless or turn into a life-threatening carcinoma.
The use of artificial intelligence could improve the assessment of the extent of a tumor disease (staging) with the help of data that is easy and inexpensive to collect, as the study showed, according to a PSI press release. The researchers provided a learning algorithm with 560 tissue samples from 122 patients.
These were mixed with a dye that causes the chromatin in the cell nucleus to glow fluorescently. Chromatin consists, among other things, of the genetic material DNA and proteins. The appearance allows conclusions to be drawn about the organization and thus the activity of the DNA contained in the cell nucleus, wrote the PSI.
In combination with powerful AI algorithms, cheap and easy-to-obtain chromatin images could provide enough information to investigate how the cell state and tissue organization change, it was said. However, numerous further studies are required before they can be used in practice.
©Keystone/SDA
French 
English 
German 
Spanish 
Arabic