Cancer Detection Improved with New Image Analysis Technique
By MedImaging International staff writers Posted on 02 Mar 2015 |
Researchers developed a novel image-analysis technique designed to improve breast cancer detection and diagnosis.
The goal of the team was to develop a new quantitative image analysis technique to improve prediction of cancer risk, or cancer prognosis, and help find more effective cancer screening and treatment strategies. To this end, the team built image processing algorithms that could analyze multiple digital X-ray images, and build statistical data learning-based prediction models, to generate quantitative image markers.
The research team was led by Dr. Bin Zheng, electrical and computer engineering professor at the University of Oklahoma, College of Engineering (Norman, OK, USA).
Breast cancer screening, for example includes risk factors such as age, family cancer history, lifestyle, breast density, and results from tests for common susceptible cancer gene mutations. These risk factors are reviewed and are used to cancer risk assessment models. These models are then applied in epidemiology studies.
Using the new models, only a small number of those women in the near-term high-risk category would be screened more frequently. Those with average or lower near-term risk of developing cancer would be screened less frequently, allowing radiologists to focus on women in the high-risk group. A smaller number of women screened annually also reduce the risk of false-positive recalls in those women with low near-term cancer risk.
Prof. Bin Zheng, said, “Our preliminary study results demonstrate that our new near-term risk prediction model based on a computer-aided detection scheme of four-view mammograms yielded a substantially higher discriminatory power than other existing known risk factors to predict near-term cancer risk.”
Related Links:
University of Oklahoma, College of Engineering
The goal of the team was to develop a new quantitative image analysis technique to improve prediction of cancer risk, or cancer prognosis, and help find more effective cancer screening and treatment strategies. To this end, the team built image processing algorithms that could analyze multiple digital X-ray images, and build statistical data learning-based prediction models, to generate quantitative image markers.
The research team was led by Dr. Bin Zheng, electrical and computer engineering professor at the University of Oklahoma, College of Engineering (Norman, OK, USA).
Breast cancer screening, for example includes risk factors such as age, family cancer history, lifestyle, breast density, and results from tests for common susceptible cancer gene mutations. These risk factors are reviewed and are used to cancer risk assessment models. These models are then applied in epidemiology studies.
Using the new models, only a small number of those women in the near-term high-risk category would be screened more frequently. Those with average or lower near-term risk of developing cancer would be screened less frequently, allowing radiologists to focus on women in the high-risk group. A smaller number of women screened annually also reduce the risk of false-positive recalls in those women with low near-term cancer risk.
Prof. Bin Zheng, said, “Our preliminary study results demonstrate that our new near-term risk prediction model based on a computer-aided detection scheme of four-view mammograms yielded a substantially higher discriminatory power than other existing known risk factors to predict near-term cancer risk.”
Related Links:
University of Oklahoma, College of Engineering
Latest Imaging IT News
- New Google Cloud Medical Imaging Suite Makes Imaging Healthcare Data More Accessible
- Global AI in Medical Diagnostics Market to Be Driven by Demand for Image Recognition in Radiology
- AI-Based Mammography Triage Software Helps Dramatically Improve Interpretation Process
- Artificial Intelligence (AI) Program Accurately Predicts Lung Cancer Risk from CT Images
- Image Management Platform Streamlines Treatment Plans
- AI-Based Technology for Ultrasound Image Analysis Receives FDA Approval
- AI Technology for Detecting Breast Cancer Receives CE Mark Approval
- Digital Pathology Software Improves Workflow Efficiency
- Patient-Centric Portal Facilitates Direct Imaging Access
- New Workstation Supports Customer-Driven Imaging Workflow