Diagnostic screening programs help catch cancer, abnormalities or other diseases before they reach an advanced stage, saving lives and healthcare costs. Screening programs include, lung, breast, prostate, and cervical cancer, among many others.
New findings support the routine use of deep learning-based risk assessments, as this method can decrease subjectivity, reduce unnecessary imaging and improve diagnostic accuracy.
The COlorectal Cancer detection with AI, or COCA, model is a cost-effective, scalable solution that turns routine CT scans into opportunistic exams that can be used to proactively identify CRC.
Two respected radiology organizations have issued a stark warning on the new recommendations, stating that they risk confusing patients and “may contribute to thousands of additional breast cancer deaths each year.”
Though the study of AI in lung cancer screening is not new, prior research has been retrospective in nature, making it challenging to determine the impact.
Lung cancer remains the leading cause of cancer-related deaths in the United States. It is estimated that it claims approximately 125,000 lives in the U.S. every year.
New findings published in RSNA's Radiology highlight the shortcomings of using nodule characteristics and patient history alone to predict an individual’s true cancer risk.
