1Department of Health Services Management, Graduate School, Kyung Hee University, Seoul,
Korea
2Department of Business Administration, College of Management, Kyung Hee University, Seoul,
Korea
*Corresponding author: Sangchan Park, https://orcid.org/0000-0003-4488-3258, Department of Business Administration, College of Management, Kyung Hee University, 26 Kyungheedae-ro, Dongdaemun-gu, Seoul 02447, Korea, Email: sangchan@khu.ac.kr
Received December 2, 2020 Accepted January 8, 2021
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (https://creativecommons.org/licenses/by-nc/4.0/) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
Digital pathology incorporates the acquisition, management, sharing, and interpretation of pathological information, including slides and data, in a digital environment. Digital slides are created using a scanning device to capture a high-resolution image on glass slides for analysis on a computer or a mobile device. Though digital pathology has drastically grown over the last 10 years and has created opportunities to support specialists, few have attempted to address its full-scale implementation in routine clinical practice. To incorporate new technologies in diagnostic processes, it is necessary to study their application, the value they provide to specialists, and their effects on improvements across the entire workflow, rather than studying a particular element. In this study, we aimed to identify what have the current digital pathology systems contributed to the pathological and diagnostic process. We retrieved articles published between 2010 and 2020 from the databases PubMed and Google Scholar. We explored how digital pathology systems can better utilize existing medical data and new technologies within the current diagnostic workflow. While the evidence concerning the efficacy and effectiveness of digital pathology is mounting, high-quality evidence regarding its impact on resource allocation and value for diagnosis is still needed to support clinical diagnosis and policy decision-making.
The need for efficient resource distribution and innovative technology to provide quality care is emerging, with an aging population and an increase in chronic diseases (Kairy et al., 2009). It is clear that the adoption of new technology is a major driver of health care quality innovation, but policymakers must reconcile the adaptation to innovative treatments and their affordability, while providing incentives for innovation (Organisation for Economic Co-operation and Development, 2017). Applying new technologies to the job is a burden not only on the institutions’ decision-makers, but also on employees. Decision-makers want to reduce the burden economically while maintaining the benefits of innovation, and employees expect new technologies to help them without disrupting their existing workflow (Davenport and Kalakota, 2019).
Digital pathology incorporates the acquisition, management, sharing, and interpretation of pathological information, including slides and data, in a digital environment. Digital pathology refers to converting and storing a pathology slides into the digital images using a digital scanner, and performing a pathological diagnosis using these digital images. Digital slides are created using a scanning device that digitally captures a high-resolution image of the contents on glass slides for analysis on a computer or mobile device (Digital Pathology Association, 2020).
Though digital pathology has drastically grown over the last 10 years and has created opportunities to support specialists, few have attempted to address its full-scale implementation in routine clinical practice (Ho et al., 2014). In the 1990s, the commercialization of scanner equipment capable of digitizing pathological images improved research across the field of digital pathology. The ability to process, analyze, and store large amounts of data through scanners allows for creating digitized pathological images as whole-slide images (WSIs) (Hartman et al., 2017).
For using new technologies to be used in diagnosis, it is necessary to study their application, value to specialists, and effects of improvement across the entire workflow rather than simply studying a single element. The purpose of this study was to outline and elaborate the proposed values of implementing the digital pathology system by exploring in the latest research.
MATERIALS AND METHODS
We reviewed literature on this topic published between 2010 and 2020 from the public databases PubMed and Google Scholar (Table 1). For the present study, we defined digital pathology as using WSI for remote consulting, diagnosis, teaching, and image analysis. We searched articles published in English on PubMed. The keywords used included digital pathology and workflow.
The selection criteria were as follows: (a) We included only case studies that included implementing digital pathology components. We selected and analyzed only case studies that involved applying new technology to the pathologic diagnosis workflow. Technical studies of digital pathology systems were excluded from this research. For example, we included studies using artificial intelligence for diagnosis but excluded studies reporting the development of artificial intelligence models from this research. (b) The technologies implementing for diagnostic workflow were included. Case studies not directly related to diagnosis were excluded. For example, laboratory automation and dyeing technology research were excluded.
RESULTS
Digital pathology was used only for educational or consulting purposes until their regulatory approval for clinical employment in routine pathological practice (L’Imperio et al., 2020). In studies in the United States and Europe, the regulatory approval of digital pathology research results has been reported, and the similarity of WSI diagnosis to the pathological diagnosis (using a conventional microscope) has been confirmed (L’Imperio et al., 2020).
The latest papers that discuss the effectiveness of digital pathology applied to diagnosis emphasized the content for workflow implementation and discussed quality and delivery, excluding cost, among the operational performance with respect to quality, cost, delivery. Hospitals that implemented digital pathology earlier have built up second-generation digital pathology and currently integrate artificial intelligence and image analysis (Hanna et al., 2020; Stathonikos et al., 2020).
Pathology departments follow diagnostic procedures that result in a diagnostic report. The report is the results of the final pathology examination, and the quality of the pathological diagnosis is determined by the accuracy, timely delivery, and completeness of the report (Nakhleh, 2006). Moreover, pathological work process involves long laboratory processing times owing to several standardized manual procedures. During the long work process, subsequent processes cannot be conducted until previous ones are complete. In this sense, it is necessary to identify the values provided by implementing a fully digital pathology workflow. (Griffin and Treanor, 2017; Serrano et al., 2010)
DISCUSSION
In this study, we attempted to identify what value has the current digital pathology systems contributed to the pathological and diagnostic processes in the last 10 years. As information technology is a strategic asset in companies (Müller et al., 2012), digital pathology can be deployed as an enabler of process innovation in healthcare. Digital pathology digitizes the existing pathology workflow, and artificial intelligence and algorithms can improve the accuracy and efficiency of pathological diagnosis.
From a process management perspective, it is necessary to establish a structured framework to improve its processes, based on the data, and measure the process performance (Pyon et al., 2009). To successfully implement algorithms into digital pathology not only highly accurate algorithms are required but also their organic integration with existing pathological workflows, user-centered interface design, and interoperability with existing laboratory information and electronic health record systems are required (Guo et al., 2016; Steiner et al., 2020).
Therefore, standardizing procedures and establishing performance measurements are necessary. Quality, cost, and delivery analysis will support process assessment with strategic organizational and operational improvements.
We hope that high-quality evidence regarding the impact on resource allocation and value for diagnosis is discussed to support clinical diagnosis and policy decision-making.
ACKNOWLEDGMENTS
The authors received no financial support for this article.
Notes
CONFLICT OF INTEREST
No potential conflict of interest relevant to this article was reported.
REFERENCES
Achi HE, Belousova T, Chen L, Wahed A, Wang I, Hu Z, Kanaan Z, Rios A, Nguyen AND. Automated diagnosis of lymphoma with digital pathology images using deep learning. Ann Clin Lab Sci. 2019;49:153–160.
Davenport T, Kalakota R. The potential for artificial intelligence in healthcare. Future Healthc J. 2019;6:94–98.
Digital Pathology Association [Internet]. Carmel (IN): Digital Pathology Association; [cited 2020 Dec 12]. Available from: https://digitalpathologyassociation.org/about-digital-pathology.
Griffin J, Treanor D. Digital pathology in clinical use: where are we now and what is holding us back? Histopathology. 2017;70:134–145.
Guo H, Birsa J, Farahani N, Hartman DJ, Piccoli A, O’Leary M, McHugh J, Nyman M, Stratman C, Kvarnstrom V, Yousem S, Pantanowitz L. Digital pathology and anatomic pathology laboratory information system integration to support digital pathology sign-out. J Pathol Infor. 2016;7:23
Hanna MG, Reuter VE, Ardon O, Kim D, Sirintrapun SJ, Schüffler PJ, Busam KJ, Sauter JL, Brogi E, Tan LK, Xu B, Bale T, Agaram NP, Tang LH, Ellenson LH, Philip J, Corsale L, Stamelos E, Friedlander MA, Ntiamoah P, Labasin M, England C, Klimstra DS, Hameed M. Validation of a digital pathology system including remote review during the COVID-19 pandemic. Mod Pathol. 2020;33:2115–2127.
Hartman DJ, Pantanowitz L, McHugh JS, Piccoli AL, OLeary MJ, Lauro GR. Enterprise implementation of digital pathology: feasibility, challenges, and opportunities. J Digit Imaging. 2017;30:555–560.
Ho J, Ahlers SM, Stratman C, Aridor O, Pantanowitz L, Fine JL, Kuzmishin JA, Montalto MC, Parwani AV. Can digital pathology result in cost savings? A financial projection for digital pathology implementation at a large integrated health care organization. J Pathol Inform. 2014;5:33
Kairy D, Lehoux P, Vincent C, Visintin M. A systematic review of clinical outcomes, clinical process, healthcare utilization and costs associated with telerehabilitation. Disabil Rehabil. 2009;31:427–447.
Krupinski EA, Silverstein LD, Hashmi SF, Graham AR, Weinstein RS, Roehrig H. Observer performance using virtual pathology slides: impact of LCD color reproduction accuracy. J Digit Imaging. 2012;25:738–743.
L’Imperio V, Brambilla V, Cazzaniga G, Ferrario F, Nebuloni M, Pagni F. Digital pathology for the routine diagnosis of renal diseases: a standard model. J Nephrol. 2020. Jul. 18. [Epub]. https://doi.org/10.1007/s40620-020-00805-1.
Müller S, Møller E, Nygaard T. IT-enabled process innovation: a literature review. In : AMCIS 2012 Proceedings; 2012 Aug 9–12; Seattle, Washington: Americas Conference on Information Systems; 2012. 4:p. 2716–2733.
Nakhleh RE. What is quality in surgical pathology? J Clin Pathol. 2006;59:669–672.
Organisation for Economic Co-operation and Development (OECD). New health technologies: managing access, value and sustainability [Internet]. Paris: OECD Publishing; 2017. [2020 Dec 12]. Available from: https://doi.org/10.1787/9789264266438-en.
Pyon CU, Lee MJ, Park SC. Decision support system for service quality management using customer knowledge in public service organization. Expert Syst Appl. 2009;36:8227–8238.
Randell R, Ambepitiya T, Mello-Thoms C, Ruddle RA, Brettle D, Thomas RG, Treanor D. Effect of display resolution on time to diagnosis with virtual pathology slides in a systematic search task. J Digit Imaging. 2015;28:68–76.
Romero Lauro G, Cable W, Lesniak A, Tseytlin E, McHugh J, Parwani A, Pantanowitz L. Digital pathology consultations-a new era in digital imaging, challenges and practical applications. J Digit Imaging. 2013;26:668–677.
Serrano L, Hegge P, Sato B, Richmond B, Stahnke L. Using LEAN principles to improve quality, patient safety, and workflow in histology and anatomic pathology. Adv Anat Pathol. 2010;17:215–221.
Stathonikos N, Nguyen TQ, van Diest PJ. Rocky road to digital diagnostics: implementation issues and exhilarating experiences. J Clin Pathol. 2020. Sep. 28. jclinpath-2020206715[Epub]. https://doi.org/10.1136/jclinpath-2020-206715.
Steiner DF, Nagpal K, Sayres R, Foote DJ, Wedin BD, Pearce A, Cai CJ, Winter SR, Symonds M, Yatziv L, Kapishnikov A, Brown T, Flament-Auvigne I, Tan F, Stumpe MC, Jiang PP, Liu Y, Chen PC, Corrado GS, Terry M, Mermel CH. Evaluation of the use of combined artificial intelligence and pathologist assessment to review and grade prostate biopsies. JAMA Network Open. 2020;3:e2023267
Torres R, Olson E, Homer R, Martin DT, Levene MJ, Perincheri S, Sprenkle PC, Humphrey PA. Initial evaluation of rapid, direct-to-digital prostate biopsy pathology. Arch Pathol Lab Med. 2020. Sep. 29. [Epub]. https://doi.org/10.5858/arpa.2020-0037-OA.
Wilbur DC, Brachtel EF, Gilbertson JR, Jones NC, Vallone JG, Krishnamurthy S. Whole slide imaging for human epidermal growth factor receptor 2 immunohistochemistry interpretation: accuracy, precision, and reproducibility studies for digital manual and paired glass slide manual interpretation. J Pathol Inform. 2015;6:22
Zembowicz A, Ahmad A, Lyle SR. A comprehensive analysis of a web-based dermatopathology second opinion consultation practice. Arch Pathol Lab Med. 2011;135:379–383.
Table 1
Effects of the application of digital pathology workflow
108 Cases, comprised of 254 individual parts and 1,196 slides
Telepathology (remote sign out)
Operational feasibility supporting remote review and reporting of pathology specimens, and evaluation of remote access performance and usability for remote sign out.
A set of 250 breast biopsy virtual slide regions of interest (half malignant, half benign) were shown to six pathologists.
A calibration, characterization, and profiling protocol for color-critical medical imaging applications
There was no significant impact on diagnostic accuracy with the color-managed/calibrated display, however, observe a significant impact on interpretation speed.
PDF Links
PubReader
ePub Link
XML Download
Full text via DOI
Download Citation 
Print 
