New imaging information system could accelerate the prognosis of certain types of cancer

Researchers at the University of Colorado’s Anschutz Medical Campus have found that a new imaging information system may ultimately provide faster and more accurate prognosis for certain types of cancer.

The study will be presented at the Medical Image Computing and Computer-Assisted Intervention (MICCAI) conference on September 18 and will be published in the MICCAI 2022 Proceedings.

Oncologists have long used the Ki67 protein as a proliferation biomarker for human tumor cells. But the time, money and method of distribution have challenged medical professionals.

Fuyong Xing, PhD, first author of the article and an assistant professor in the Department of Biostatistics and Informatics at the Colorado School of Public Health, is the principal investigator of the National Institutes of Health (NIH) R21 project.

The goal is to develop a novel imaging information system that will automate the process of scanning the Ki67 protein for neuroendocrine tumors of the gastrointestinal tract and pancreas, and ultimately create a Ki67 labeling index scoring method that will be used by medical institutions around the world world can be shared.

“The system will greatly improve the efficiency and objectivity of biomarker calculation, so it can enable rapid disease detection,” Xing said. “This study (detection of cells/nuclei) serves as the basis for the evaluation of the Ki67 labeling index in our project and will provide a low-cost, efficient method for Ki67 evaluation in different datasets.”

Currently, oncologists often use “eyeball” estimation, or manually counting the number of these cells, to determine the prognosis for patients with pancreatic, gastrointestinal, and other cancers. The higher the Ki67 protein, the worse the prognosis.

Xing said the study is an important step in developing generalizable algorithms for evaluating the Ki67 labeling index. It has also been shown that the imaging technology used shows a significant improvement in analysis.

“Compared to the current ‘eyeball’ estimates and manual counting approaches to Ki67 assessment in clinical practice, this study has the potential to significantly speed up the process of Ki67 biomarker calculation,” said Xing. “Furthermore, it would free pathologists and researchers from their daily, routine and tedious work so that they can focus more on formulating high-level hypotheses and biological discoveries.”

Xing said the imaging informatics system could eventually serve as a place where results could be shared and accessed by medical institutions anywhere. There is currently no universal system for quantifying the labeling index across different datasets, which complicates treatment for patients treated at multiple medical institutions.

This part of the study looked at the pancreas[XF1] and gastrointestinal cancer. The index and imaging technology will continue to be tested in future studies to determine their long-term viability.

About the University of Colorado Anschutz Medical Campus

The University of Colorado Anschutz Medical Campus is a premier medical destination at the forefront of transformative science, medicine, education and patient care. The campus includes the University of Colorado Health Care Professional Schools, more than 60 centers and institutes, and two nationally recognized independent hospitals – UCHealth University of Colorado Hospital and Children’s Hospital Colorado