BFU Develops Neural Network for Early Pancreatic Cancer Detection

Researchers at Immanuel Kant Baltic Federal University have developed a neural network model designed to detect pancreatic cancer at an early stage. The algorithm analyzes images obtained through computed tomography (CT) and can identify suspicious lesions, marking them on scans with accuracy comparable to that of experienced physicians.

According to the developers, the model demonstrated strong performance metrics: 88 percent accuracy, 98 percent sensitivity, and 98 percent specificity. These results suggest the system could serve as a reliable assistant for oncologists and radiologists.

The researchers note that the system addresses a major clinical challenge. Pancreatic cancer is often diagnosed at later stages, which significantly complicates treatment. The new model can detect even small tumors, making it a valuable tool for early diagnosis.