New 3D Technique Reveals Precancerous Pancreatic Lesions (IMAGE)

Johns Hopkins Medicine

New 3D Technique Reveals Precancerous Pancreatic Lesions

Caption

This video (https://drive.google.com/file/d/1RA32s3I-bsG8XcNopss-ViIwO1sBxwgu/view) shows a human pancreas specimen, which was cut into thousands of sections, stained using histological dyes and digitized. Here, a machine learning tool called CODA is used to align the serial pancreas images and automatically detect over 100 precancerous lesions called PanINs (represented in different colors) in a single sample, emphasizing the shocking numbers of precancers that can exist in the pancreas.

Credit

Ashley Kiemen

Usage Restrictions

N/A

License

Original content

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.