@Article{Platisa2017JMI,
  author      = {Platiša, Ljiljana and Van Brantegem, Leen and Kumcu, Asli and Ducatelle, Richard and Philips, Wilfried},
  title       = {Influence of study design on digital pathology image quality evaluation: the need to define a clinical task},
  journal     = {Journal of Medical Imaging},
  year        = {2017},
  volume      = {4},
  number      = {2},
  pages       = {1--12},
  abstract    = {Despite the current rapid advance in technologies for whole slide imaging, there is still no scientific consensus on the recommended methodology for image quality assessment of digital pathology slides. For medical images in general, it has been recommended to assess image quality in terms of doctors' success rates in performing a specific clinical task while using the images (clinical image quality, cIQ). However, digital pathology is a new modality, and already identifying the appropriate task is difficult. In an alternative common approach, humans are asked to do a simpler task such as rating overall image quality (perceived image quality, pIQ), but that involves the risk of nonclinically relevant findings due to an unknown relationship between the pIQ and cIQ. In this study, we explored three different experimental protocols: 
(1) conducting a clinical task (detecting inclusion bodies), (2) rating image similarity and preference, and (3) rating the overall image quality. 
Additionally, within protocol 1, overall quality ratings were also collected (task-aware pIQ). The experiments were done by diagnostic veterinary pathologists in the context of evaluating the quality of hematoxylin and eosin-stained digital pathology slides of animal tissue samples under several common image alterations: additive noise, blurring, change in gamma, change in color saturation, and JPG compression. While the size of our experiments was small and prevents drawing strong conclusions, the results suggest the need to define a clinical task. Importantly, the pIQ data collected under protocols 2 and 3 did not always rank the image alterations the same as their cIQ from protocol 1, warning against using conventional pIQ to predict cIQ. At the same time, there was a correlation between the cIQ and task-aware pIQ ratings from protocol 1, suggesting that the clinical experiment context (set by specifying the clinical task) may affect human visual attention and bring focus to their criteria of image quality. Further research is needed to assess whether and for which purposes (e.g., preclinical testing) task-aware pIQ ratings could substitute cIQ for a given clinical task.},
  doi         = {10.1117/1.JMI.4.2.021108},
  isbn        = {2329-4302},
  keywords    = {digital pathology, image quality, human observer, signal detection, image compression},
  url         = {https://www.spiedigitallibrary.org/journals/journal-of-medical-imaging/volume-4/issue-02/021108/Influence-of-study-design-on-digital-pathology-image-quality-evaluation/10.1117/1.JMI.4.2.021108},
}