AI model detects very early normally ‘invisible’ tissue changes of pancreatic cancer
Peer-Reviewed Publication
Updates every hour. Last Updated: 23-Jun-2026 01:16 ET (23-Jun-2026 05:16 GMT/UTC)
An AI model (REDMOD) can pick up the very early subtle tissue changes of pancreatic ductal adenocarcinoma, the most common form of pancreatic cancer, which conventional imaging and the human eye find difficult to detect, finds research published online in the journal Gut. As such, it offers the potential to shift an all too common late stage, terminal disease diagnosis to one that is at an early stage (stage 0) and treatable, say the researchers. While REDMOD was more accurate than experienced radiologists, it requires testing in high risk patients, defined as those with unexpected weight loss and newly diagnosed diabetes, before it can be widely used in clinical practice, they add.
Researchers at the University of Illinois Chicago have developed an anti-cancer therapy inspired by bacteria found in cancer tumors.
When tested in combination with radiation in animal models of prostate cancer, it was highly effective — the approach effectively shut down tumor growth. The therapy is made from a fragment of a bacterial protein, a peptide called aurB.
Activation of a specific part of the Dicer enzyme can change its shape in a way that affects its critical role in proper cell division, with implications for both cancer biology and fertility, according to researchers at The University of Texas MD Anderson Cancer Center.
Risk of developing a subsequent primary cancer varied significantly by age at initial diagnosis, sex, and type of first cancer, according to a study by Oxana Palesh and Susan Hong and colleagues at Virginia Commonwealth University, U.S., published April 28th in the open-access journal PLOS Medicine.
For many patients with breast cancer, deciding whether cancer has spread to nearby lymph nodes still depends on labor-intensive pathology workflows that require tissue cutting, staining, and expert interpretation.