New Imaging Information System To Provide More Accurate Cancer Prognosis

Researchers in the U.S. report that a novel imaging information system that they are developing could lead to a cheaper, faster, and more accurate prognosis for some cancers.

CT Scan

CT Scan

The research team from the University of Colorado Anschutz Medical Campus, also called CU Anschutz, presented their study findings at the Medical Image Computing and Computer-Assisted Intervention (MICCAI). Its new system could make it possible to spot the biomarkers of certain cancers more accurately.

Read Also: A Magnetic Resonance Imaging Technique May Be Able to Cause Vascular Recellularization

Oncologists have long relied on the Ki67 protein as a biomarker for the increase of tumor cells in humans. Medical professionals, however, have had to combat challenges revolving around time, funds, and the distribution method. This system may aid in ultimately overcoming these problems.

The paper’s first author, Fuyong Xing, Ph.D., is the lead investigator in the R21 Project of the National Institute of Health (NIH).

A system for faster cancer prognosis

According to the researchers, oncologists mainly rely on “eyeball” estimation or manual calculation of cells when making a prognosis for people with certain cancers, including pancreatic cancer and gastrointestinal cancer. Higher levels of the Ki67 protein are indicative of a worse prognosis.

The system being developed by these CU Anschutz scientists aims to remove the guessing element when ascertaining cell numbers. It will automate the Ki67 scanning process for these cancers and help to develop a standard Ki67 labeling index assessment technique. This method may be shared among medical experts globally.

Read Also: UCLA: MRI Not a Reliable Method for Tumor Size Estimation in Prostate Cancer

“The system will significantly improve the efficiency and objectivity of the biomarker computation, so that it can enable quick disease detection,” said Xing, an assistant professor of biostatistics and informatics at the Colorado School of Public Health. “This study (cell/nuclei detection) serves as the foundation of Ki67 labeling index assessment in our project, and it will provide a low-cost, efficient method for Ki67 scoring in different datasets.”

The researchers said the imaging technology used displayed great improvement in their analysis. Their focus was on pancreatic[XF1] and gastrointestinal cancers in this part of their research.

This new imaging information system promises to speed up the process of computing the Ki67 protein biomarker, Xing stated. He expressed optimism that “it would release pathologists and researchers from daily, routine and tedious work so they can pay more attention to formulating high-level hypotheses and biological discovery.”

The study’s first author believed their research is a vital step toward putting together generalizable Ki67 labeling index assessment algorithms. There is at the moment no common system for calculating the labeling index in different datasets. This makes the treatment of patients at multiple facilities thorny.

Read Also: Medical Imaging Breakthrough: A Scanner That Can Do a Total Body Scan in Few Minutes

Xing hoped the novel imaging information system could offer a point where medical facilities across the world can share and retrieve results. Along with his colleagues, he plans to continue to test the index and imaging technology for long-term viability in future research.


Low-Resource Adversarial Domain Adaptation for Cross-modality Nucleus Detection



Want to Stay Informed?

Join the Gilmore Health News Newsletter!

Want to live your best life?

Get the Gilmore Health Weekly newsletter for health tips, wellness updates and more.

By clicking "Subscribe," I agree to the Gilmore Health and . I also agree to receive emails from Gilmore Health and I understand that I may opt out of Gilmore Health subscriptions at any time.