Abstract
The quality of an image produced by the Whole Slide Imaging (WSI) scanners is of critical importance for using the image in clinical diagnosis. Therefore, it is very important to monitor and ensure the quality of images. Since subjective image quality assessments by pathologists are very time-consuming, expensive and difficult to reproduce, we propose a method for objective assessment based on clinically relevant and perceptual image parameters: sharpness, contrast, brightness, uniform illumination and color separation; derived from a survey of pathologists. We developed techniques to quantify the parameters based on content-dependent absolute pixel performance and to manipulate the parameters in a predefined range resulting in images with content-independent relative quality measures. The method does not require a prior reference model. A subjective assessment of the image quality is performed involving 69 pathologists and 372 images (including 12 optimal quality images and their distorted versions per parameter at 6 different levels). To address the inter-reader variability, a representative rating is determined as a one-tailed 95% confidence interval of the mean rating. The results of the subjective assessment support the validity of the proposed objective image quality assessment method to model the readers’ perception of image quality. The subjective assessment also provides thresholds for determining the acceptable level of objective quality per parameter. The images for both the subjective and objective quality assessment are based on the HercepTest TM slides scanned by the Philips Ultra Fast Scanners, developed at Philips Digital Pathology Solutions. However, the method is applicable also to other types of slides and scanners.
Highlights
The quality of the digital pathology images has a direct influence on the accuracy of the diagnosis and on the readers’ performance and reliability [1,2]
The images produced by the Whole Slide Imaging (WSI) scanners should represent an accurate and consistent quality
We propose a method to objectively assess image quality, which is independent of image content and corresponds to the perceptual or subjective image quality
Summary
The quality of the digital pathology images has a direct influence on the accuracy of the diagnosis and on the readers’ performance and reliability [1,2]. The proposed image quality assessment method is applicable to various purposes: (i) dynamically monitor the scanner performance (e.g., focus) and slide quality (e.g., color intensity of the stains); (ii) assist in the design and implementation of algorithms, which require iterative testing and optimization (e.g. data compression and computer aided detection/diagnosis); (iii) impartial evaluation and benchmarking of the imaging systems (e.g., scanners and microscopes), and software tools (e.g., codecs and filters). The existing works do not address the correlation between the subjective and objective measurement of image quality and their significance in clinical diagnosis. The assessment protocol is reviewed and approved by the IRB before the start of the study The images for both the subjective and objective quality assessments are based on the HercepTestTM [9] slides scanned by the Ultra Fast Scanners, developed at Philips Digital Pathology Solutions. The weights represent the contribution of the individual parameters in the overall quality computation, where the sum of the weights equals to 1
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
