Cargando…

An analysis of pathologists’ viewing processes as they diagnose whole slide digital images

Although pathologists have their own viewing habits while diagnosing, viewing behaviors leading to the most accurate diagnoses are under-investigated. Digital whole slide imaging has enabled investigators to analyze pathologists’ visual interpretation of histopathological features using mouse and vi...

Descripción completa

Detalles Bibliográficos
Autores principales: Ghezloo, Fatemeh, Wang, Pin-Chieh, Kerr, Kathleen F., Brunyé, Tad T., Drew, Trafton, Chang, Oliver H., Reisch, Lisa M., Shapiro, Linda G., Elmore, Joann G.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9576972/
https://www.ncbi.nlm.nih.gov/pubmed/36268085
http://dx.doi.org/10.1016/j.jpi.2022.100104
_version_ 1784811650322268160
author Ghezloo, Fatemeh
Wang, Pin-Chieh
Kerr, Kathleen F.
Brunyé, Tad T.
Drew, Trafton
Chang, Oliver H.
Reisch, Lisa M.
Shapiro, Linda G.
Elmore, Joann G.
author_facet Ghezloo, Fatemeh
Wang, Pin-Chieh
Kerr, Kathleen F.
Brunyé, Tad T.
Drew, Trafton
Chang, Oliver H.
Reisch, Lisa M.
Shapiro, Linda G.
Elmore, Joann G.
author_sort Ghezloo, Fatemeh
collection PubMed
description Although pathologists have their own viewing habits while diagnosing, viewing behaviors leading to the most accurate diagnoses are under-investigated. Digital whole slide imaging has enabled investigators to analyze pathologists’ visual interpretation of histopathological features using mouse and viewport tracking techniques. In this study, we provide definitions for basic viewing behavior variables and investigate the association of pathologists' characteristics and viewing behaviors, and how they relate to diagnostic accuracy when interpreting whole slide images. We use recordings of 32 pathologists’ actions while interpreting a set of 36 digital whole slide skin biopsy images (5 sets of 36 cases; 180 cases total). These viewport tracking data include the coordinates of a viewport scene on pathologists’ screens, the magnification level at which that viewport was viewed, as well as a timestamp. We define a set of variables to quantify pathologists' viewing behaviors such as zooming, panning, and interacting with a consensus reference panel’s selected region of interest (ROI). We examine the association of these viewing behaviors with pathologists’ demographics, clinical characteristics, and diagnostic accuracy using cross-classified multilevel models. Viewing behaviors differ based on clinical experience of the pathologists. Pathologists with a higher caseload of melanocytic skin biopsy cases and pathologists with board certification and/or fellowship training in dermatopathology have lower average zoom and lower variance of zoom levels. Viewing behaviors associated with higher diagnostic accuracy include higher average and variance of zoom levels, a lower magnification percentage (a measure of consecutive zooming behavior), higher total interpretation time, and higher amount of time spent viewing ROIs. Scanning behavior, which refers to panning with a fixed zoom level, has marginally significant positive association with accuracy. Pathologists’ training, clinical experience, and their exposure to a range of cases are associated with their viewing behaviors, which may contribute to their diagnostic accuracy. Research in computational pathology integrating digital imaging and clinical informatics opens up new avenues for leveraging viewing behaviors in medical education and training, potentially improving patient care and the effectiveness of clinical workflow.
format Online
Article
Text
id pubmed-9576972
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-95769722022-10-19 An analysis of pathologists’ viewing processes as they diagnose whole slide digital images Ghezloo, Fatemeh Wang, Pin-Chieh Kerr, Kathleen F. Brunyé, Tad T. Drew, Trafton Chang, Oliver H. Reisch, Lisa M. Shapiro, Linda G. Elmore, Joann G. J Pathol Inform Original Research Article Although pathologists have their own viewing habits while diagnosing, viewing behaviors leading to the most accurate diagnoses are under-investigated. Digital whole slide imaging has enabled investigators to analyze pathologists’ visual interpretation of histopathological features using mouse and viewport tracking techniques. In this study, we provide definitions for basic viewing behavior variables and investigate the association of pathologists' characteristics and viewing behaviors, and how they relate to diagnostic accuracy when interpreting whole slide images. We use recordings of 32 pathologists’ actions while interpreting a set of 36 digital whole slide skin biopsy images (5 sets of 36 cases; 180 cases total). These viewport tracking data include the coordinates of a viewport scene on pathologists’ screens, the magnification level at which that viewport was viewed, as well as a timestamp. We define a set of variables to quantify pathologists' viewing behaviors such as zooming, panning, and interacting with a consensus reference panel’s selected region of interest (ROI). We examine the association of these viewing behaviors with pathologists’ demographics, clinical characteristics, and diagnostic accuracy using cross-classified multilevel models. Viewing behaviors differ based on clinical experience of the pathologists. Pathologists with a higher caseload of melanocytic skin biopsy cases and pathologists with board certification and/or fellowship training in dermatopathology have lower average zoom and lower variance of zoom levels. Viewing behaviors associated with higher diagnostic accuracy include higher average and variance of zoom levels, a lower magnification percentage (a measure of consecutive zooming behavior), higher total interpretation time, and higher amount of time spent viewing ROIs. Scanning behavior, which refers to panning with a fixed zoom level, has marginally significant positive association with accuracy. Pathologists’ training, clinical experience, and their exposure to a range of cases are associated with their viewing behaviors, which may contribute to their diagnostic accuracy. Research in computational pathology integrating digital imaging and clinical informatics opens up new avenues for leveraging viewing behaviors in medical education and training, potentially improving patient care and the effectiveness of clinical workflow. Elsevier 2022-05-21 /pmc/articles/PMC9576972/ /pubmed/36268085 http://dx.doi.org/10.1016/j.jpi.2022.100104 Text en © 2022 The Authors https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Original Research Article
Ghezloo, Fatemeh
Wang, Pin-Chieh
Kerr, Kathleen F.
Brunyé, Tad T.
Drew, Trafton
Chang, Oliver H.
Reisch, Lisa M.
Shapiro, Linda G.
Elmore, Joann G.
An analysis of pathologists’ viewing processes as they diagnose whole slide digital images
title An analysis of pathologists’ viewing processes as they diagnose whole slide digital images
title_full An analysis of pathologists’ viewing processes as they diagnose whole slide digital images
title_fullStr An analysis of pathologists’ viewing processes as they diagnose whole slide digital images
title_full_unstemmed An analysis of pathologists’ viewing processes as they diagnose whole slide digital images
title_short An analysis of pathologists’ viewing processes as they diagnose whole slide digital images
title_sort analysis of pathologists’ viewing processes as they diagnose whole slide digital images
topic Original Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9576972/
https://www.ncbi.nlm.nih.gov/pubmed/36268085
http://dx.doi.org/10.1016/j.jpi.2022.100104
work_keys_str_mv AT ghezloofatemeh ananalysisofpathologistsviewingprocessesastheydiagnosewholeslidedigitalimages
AT wangpinchieh ananalysisofpathologistsviewingprocessesastheydiagnosewholeslidedigitalimages
AT kerrkathleenf ananalysisofpathologistsviewingprocessesastheydiagnosewholeslidedigitalimages
AT brunyetadt ananalysisofpathologistsviewingprocessesastheydiagnosewholeslidedigitalimages
AT drewtrafton ananalysisofpathologistsviewingprocessesastheydiagnosewholeslidedigitalimages
AT changoliverh ananalysisofpathologistsviewingprocessesastheydiagnosewholeslidedigitalimages
AT reischlisam ananalysisofpathologistsviewingprocessesastheydiagnosewholeslidedigitalimages
AT shapirolindag ananalysisofpathologistsviewingprocessesastheydiagnosewholeslidedigitalimages
AT elmorejoanng ananalysisofpathologistsviewingprocessesastheydiagnosewholeslidedigitalimages
AT ghezloofatemeh analysisofpathologistsviewingprocessesastheydiagnosewholeslidedigitalimages
AT wangpinchieh analysisofpathologistsviewingprocessesastheydiagnosewholeslidedigitalimages
AT kerrkathleenf analysisofpathologistsviewingprocessesastheydiagnosewholeslidedigitalimages
AT brunyetadt analysisofpathologistsviewingprocessesastheydiagnosewholeslidedigitalimages
AT drewtrafton analysisofpathologistsviewingprocessesastheydiagnosewholeslidedigitalimages
AT changoliverh analysisofpathologistsviewingprocessesastheydiagnosewholeslidedigitalimages
AT reischlisam analysisofpathologistsviewingprocessesastheydiagnosewholeslidedigitalimages
AT shapirolindag analysisofpathologistsviewingprocessesastheydiagnosewholeslidedigitalimages
AT elmorejoanng analysisofpathologistsviewingprocessesastheydiagnosewholeslidedigitalimages