Method and system for human vision model guided medical image quality assessment

US8086007B2 · kind B2 · utility

Assignee

• Siemens Aktiengesellschaft · DE

Inventors

• Michelle Xiao-Hong Yan · Princeton, US
• Ti-chiun Chang · Plainsboro, US
• Markus Lendl · Ottensoos, DE
• Stefan Boehm · Oberasbach, DE
• Tong Fang · Morganville, US
• Peter Durlak · Erlangen, DE

Key dates

• Filing date: Oct 3, 2008
• Grant date: Dec 27, 2011
• Expiry date: Jul 21, 2030

Classification

• Technology area (CPC G): Physics
• CPC primary: G06V2201/03
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

A method and system for image quality assessment is disclosed. The image quality assessment method is a no-reference method for objectively assessing the quality of medical images. This method is guided by the human vision model in order to accurately reflect human perception. A region of interest (ROI) of medical image is divided into non-overlapping blocks of equal size. Each of the blocks is categorized as a smooth block, a texture block, or an edge block. A perceptual sharpness measure, which is weighted by local contrast, is calculated for each of the edge blocks. A perceptual noise level measure, which is weighted by background luminance, is calculated for each of the smooth blocks. A sharpness quality index is determined based on the perceptual sharpness measures of all of the edge blocks, and a noise level quality index is determined based on the perceptual noise level measures of all of the smooth blocks. An overall image quality index can be determined by using task specific machine learning of samples of annotated images. The image quality assessment method can be used in applications, such as video/image compression and storage in healthcare and homeland security, and b…