An experimental study of pathologist's navigation patterns in virtual microscopy

Abstract

In virtual microscopy, a sequential process of captures of microscopical fields, allows to construct a virtual slide which is visualized using a specialized software, called the virtual microscopy viewer. This tool allows useful exploration of images, composed of thousands of microscopical fields of view at different levels of magnification, emulating an actual microscopical examination. The aim of this study was to establish the main pathologist's navigation patterns when exploring virtual microscopy slides, using a graphical user interface, adapted to the pathologist's workflow. Four pathologists with a similar level of experience, graduated from the same pathology program, navigated six virtual slides. Different issues were evaluated, namely, the percentage of common visited image regions, the time spent at each and its coincidence level, that is to say, the region of interest location. In addition, navigation patterns were also assessed, i.e., mouse movement velocities and linearity of the diagnostic paths. Results suggest that regions of interest are determined by a complex combination of the visited area, the time spent at each visit and the coincidence level among pathologists. Additionally, linear trajectories and particular velocity patterns were found for the registered diagnostic paths.

Training a cell-level classifier for detecting basal-cell carcinoma by combining human visual attention maps with low-level handcrafted features

“…As previously stated, there is a wide body of evidence that abnormal tissue is characterized by nuclear patterns that can substantively inform the pathologists' decision. 6 These patterns are interpreted by expert pathologists in ways that cannot easily be captured by simple models. As a first step, our experiments used nuclear features extracted from H&E slides of BCC samples to train a classifier to identify whether or not a given FOV contained cancer.…”

“…5 Despite the large size of a sample, in general, pathologists require very little time to examine samples and reach a diagnosis. 6 They rapidly identify regions of potential diagnostic interest, i.e., areas that usually contain abnormal patterns that characterize a particular set of pathologies. 7,8 Although every case is different, it is widely acknowledged that diseases present certain characteristic patterns and pathologists are educated to recognize them, even under very noisy conditions.…”

“…Alternatively, this high-level expert domain knowledge might be captured by implicitly extracting information from the pathologist actions with the virtual microscope during a diagnosis task. 6,29,30 One manner consists of passively recording the pathologists navigations during a diagnostic task, a strategy perfectly suited for real clinical scenarios. In such an approach, the idea is to identify and characterize the most frequently visited areas, since very likely they contain relevant diagnosis information.…”

Black Box Integration of Computer-Aided Diagnosis into PACS Deserves a Second Chance: Results of a Usability Study Concerning Bone Age Assessment

“…In case of negatively formulated items (indicated by "NEG"), results were inverted Furthermore, all participants had more than 1 year of experience in the special field of pediatric radiology and roughly the same level of expertise concerning bone age assessment. It has been previously observed and reported that the level of clinical expertise alters the diagnostic process and the related pattern of examination [36,37]. While being closely linked to the diagnostic workflow, usability problems may occur only on a special level of expertise.…”

“…As an additional aspect associated with the examination patterns reported in the literature [36,37], the future design of CAD needs to improve usability by observing and then taking into account special workflow or examination patterns in order to align the radiologist's workflow and the CAD services offered.…”