AI Breakthrough Offers New Hope in Detecting and Managing Lobular Breast Cancer
Ohio State University scientists are on the brink of a major breakthrough in the fight against lobular breast cancer, one of the most challenging forms of the disease to detect and manage. This aggressive variant, which accounts for between 10% and 15% of breast cancer diagnoses in the United States, is known for its elusive nature and propensity to spread silently before symptoms become apparent. The Ohio State University Comprehensive Cancer Center – Arthur G. James Cancer Hospital and Richard J. Solove Research Institute are now utilizing cutting-edge artificial intelligence techniques to predict which patients may face a higher risk of recurrence over the next ten years.
Unlike the more common invasive ductal carcinoma, which forms distinct clumps that can be more easily visualized on mammograms, lobular breast cancer develops in long chains of cells, leading to a subtle thickness that may not be readily detectable. This makes it particularly difficult to identify early, often resulting in the cancer spreading to other parts of the body before it is discovered. Dr. Arya Roy, a lead researcher in the study and breast cancer specialist at OSUCCC – James, emphasized the importance of a more tailored approach to treatment, noting that existing genomic tests often provide ambiguous results for lobular cancer and hinder the decision-making process for oncologists.
By integrating AI models with digital pathology images, researchers aim to identify key biomarkers and patient-specific indicators that can be used to formulate a predictive scoring system. This scoring system is intended to help oncologists better understand the likelihood of cancer recurrence and tailor treatment plans to individual patients. Dr. Roy explained that the ultimate goal is to develop an AI-driven tool that can be used to monitor all lobular breast cancer patients, allowing for more accurate surveillance and potentially improving patient outcomes.
However, experts caution that while the potential of AI in medical imaging is promising, there are still significant challenges to overcome. Dr. Harvey Castro, an ER physician and AI expert in Texas, pointed out that training AI systems on outdated data can lead to ‘temporal drift,’ where the algorithms fail to keep up with the rapid changes in the field of medicine. He also highlighted the persistent issue of dense breast tissue, which can further complicate both traditional and AI-based detection methods, especially across diverse racial and age groups.
Despite these challenges, the study marks an important step forward in the use of AI for cancer detection and management. The researchers are currently working to develop the tool, with clinical trials and funding for further research in place. The long-term vision is to create a system that not only identifies at-risk patients but also supports more personalized and effective treatment strategies, ultimately giving hope to those battling this difficult form of breast cancer.