Histology images hold great potential as a resource for target and biomarker discovery activities. However, in order to use such complex phenotypic data, it is imperative that robust image analysis tools are developed. Novo Nordisk is seeking an image analysis algorithm for the robust segmentation of histology sections.
Image credit: Waughd/Wikipedia/CC BY-SA 4.0
This is a Reduction-to-Practice Challenge that requires written documentation, output from the proposed algorithm, and submission of the source code and/or an executable for validation, if requested by the Seeker.
Overview
The pancreas is an organ that produces key enzymes and hormones essential for digestion and glucose regulation. Cellular damage can lead to diseases such as diabetes, pancreatitis, and pancreatic cancer. To better study and understand disease pathology, Novo Nordisk is seeking an algorithm to accurately detect islets, acinar cells, adipose cells, ductal area and vessels from scanned images of pancreatic tissue. Please refer to the attachments in the Detailed Description & Requirements section for more details and annotated images.
Submissions to this Challenge must be received by 11:59 PM (US Eastern Time) on July 6, 2020.
Source: InnoCentive