NL
DE
In a significant development, pathologists are exploring the potential of artificial intelligence (AI) to enhance breast cancer treatment decisions.
Traditionally, pathologists have played a pivotal role in assessing tumor tissue under a microscope. Their observations are critical in determining treatment plans and predicting patient outcomes. However, this method is not always foolproof, leading to over or under-treatment in some cases. For instance, a significant number of early-stage triple-negative breast cancer patients receive chemotherapy when it may not be necessary. Furthermore, accurately predicting the success of "neo-adjuvant" chemotherapy, administered before tumor removal, has been challenging.
Recent years have witnessed substantial progress in leveraging AI to analyze digitized microscopic tissue samples. AI-driven software can accurately extract vital information from these images, enabling predictions about disease recurrence and treatment outcomes.
In a new collaborative research project, i.e. COMMITMENT project, funded by the KWF Dutch Cancer Society, and led by Jeroen van der Laak en Francesco Ciompi, researchers aim to apply this AI technology to benefit three distinct groups of breast cancer patients.
The improved ability to assess the risk of disease progression in breast cancer holds tremendous potential. It can lead to more personalized treatment decisions, sparing patients from unnecessary chemotherapy and improving their quality of life. Additionally, it can identify patients who don't meet current chemotherapy guidelines but could still benefit from it.
Collaborating with international partners, researchers will collect pathology images and related data on treatments, molecular test outcomes, and disease progression. They will refine existing software, apply it to images, and conduct statistical analyses to optimize predictions, such as the likelihood of disease recurrence. This groundbreaking research has the potential to revolutionize breast cancer care by tailoring treatments for better outcomes.
The project is carried out using data from patients treated in the past. The next step involves testing the software on newly diagnosed patients. Additionally, the software must be certified before practical use. To maximize the chances of success, we will collaborate with a commercial partner in these follow-up steps.
