Old Dominion University Among World's Best in Computer-Aided Tumor Grading
November 15, 2019
The ODU Vision Lab Team, from left: Linmin Pei, Lasitha Vidyaratne, advisor Khan Iftekharuddin, and Monibor Rahman.
By Keith Pierce
This year, roughly 24,000 adults in the United States will be diagnosed with a brain tumor. For early treatment and therapy planning, it is essential for health professionals to know the grade or classification of these tumors. That's where researchers from Old Dominion University's Vision Lab have been ranked among the best in the world.
More than 80 teams from around the world competed in the 2019 Computational Precision Medicine: Radiology-Pathology Challenge on Brain Tumor Classification 2019 (CPM-RadPath) challenge. Results were announced at the Medical Image Computing and Computer Assisted Intervention Society (MICCAI) conference in Shanghai, China.
ODU's Vision Lab placed second between the first-place team, Shenzhen Institutes of Advanced Technology/Chinese Academy of Sciences, and the third-place team, National Taiwan University of Science and Technology.
"We are honored to be considered among the world's best when it comes to this extremely important type of research," said Khan Iftekharuddin, associate dean for research and graduate programs for the Batten College of Engineering and Technology and director of the ODU Vision Lab. "This recognition puts the ODU Vision Lab, the Batten College of Engineering and Technology and the University in the spotlight on the global stage."
Analyzing and classifying brain tumors is traditionally done by pathologists who examine tissue sections under a light microscope. This process continues to be widely applied in clinical settings, yet translating it to bedside and clinical research studies involving hundreds or thousands of tissue specimens remains a challenge.
"Considering the huge amount of digital imaging data collected and reviewed by the clinicians every day in clinical settings for brain tumor classification, discovery of effective methods is needed to automate and scale-up tumor classification," Iftekharuddin said. "These methods are expected to bring precision translational medicine for brain tumor patients a step closer."
According to MICCAI, computer-aided classification has the potential to improve the tumor diagnosis and grading process, as well as to enable quantitative studies of the mechanisms underlying disease onset and progression.
With funding from the National Institute of Biomedical Imaging and Bioengineering, at the National Institutes of Health, the ODU Vision Lab has been developing advanced computational modeling and machine learning methods for effective analysis of this radiology and pathology imaging big data for tumor detection, segmentation, grading and patient survival prediction for more than a decade.
"I'm very proud of the ODU Vision Lab team that, in recent years, has also won first place in brain tumor survival prediction category; and third place in brain tumor segmentation category in the Multimodal Brain Tumor Segmentation Challenge," Iftekharuddin said.
