ijerph-logo

Journal Browser

Journal Browser

Digital Pathology: From Technological Advances to Routine Clinical Application

A special issue of International Journal of Environmental Research and Public Health (ISSN 1660-4601). This special issue belongs to the section "Digital Health".

Deadline for manuscript submissions: closed (30 November 2023) | Viewed by 9049

Special Issue Editor

Department of Pathology, Aarhus University Hospital, DK-8200 Aarhus, Denmark
Interests: digital pathology; artificial intelligence; tumor microenvironment; immunohistochemistry; melanoma; diagnostic and prognostic biomarkers in oncology

Special Issue Information

Dear Colleagues,

Integration of diagnostic and prognostic tools based on artificial intelligence (AI) will possibly represent a milestone for the healthcare system within the next decade. Histopathology is, however, only at the very beginning of this digital revolution.

Even though image analysis of histochemical stains has been a reality for many years, most automated procedures remain unadopted to the pathologists’ daily practice. Possible explanations include hurdles in computer technology, tissue complexity, costs, and hands-on time of digital quantification of immunohistochemistry, and difficulties related to a shift from microscope to monitor, which heavily alters the workflow of the department.

Automated procedures in pathology are, nonetheless, highly desired to reduce the pathologists’ workload and to increase the accuracy and precision of their assessments, which often are deemed subjective with low reproducibility.

Very recently, deep learning, an AI subfield, has created rapid advances in the performance of image analysis. This has, for instance, made automated analysis of conventional, low-cost hematoxylin-eosin stains feasible. Thus, AI possibly has the potential to simplify and standardize automated procedures within and across pathology departments, which, in time, will lead to better, faster, and cheaper patientcare. Nonetheless, considerable development and validation work lies ahead before AI-based methods are ready for integration at the departments of pathology.

This Special Issue welcomes research papers within all fields of digital pathology that may accelerate the implementation of automated procedures, ranging from methodology to clinical validation studies. 

Dr. Patricia Switten Nielsen
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. International Journal of Environmental Research and Public Health is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2500 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • digital pathology
  • histopathology
  • artificial intelligence
  • machine learning
  • deep learning
  • biomarkers
  • biomedical imaging

Published Papers (4 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Other

19 pages, 3101 KiB  
Article
Computer-Assisted Annotation of Digital H&E/SOX10 Dual Stains Generates High-Performing Convolutional Neural Network for Calculating Tumor Burden in H&E-Stained Cutaneous Melanoma
by Patricia Switten Nielsen, Jeanette Baehr Georgsen, Mads Sloth Vinding, Lasse Riis Østergaard and Torben Steiniche
Int. J. Environ. Res. Public Health 2022, 19(21), 14327; https://0-doi-org.brum.beds.ac.uk/10.3390/ijerph192114327 - 02 Nov 2022
Cited by 3 | Viewed by 1253
Abstract
Deep learning for the analysis of H&E stains requires a large annotated training set. This may form a labor-intensive task involving highly skilled pathologists. We aimed to optimize and evaluate computer-assisted annotation based on digital dual stains of the same tissue section. H&E [...] Read more.
Deep learning for the analysis of H&E stains requires a large annotated training set. This may form a labor-intensive task involving highly skilled pathologists. We aimed to optimize and evaluate computer-assisted annotation based on digital dual stains of the same tissue section. H&E stains of primary and metastatic melanoma (N = 77) were digitized, re-stained with SOX10, and re-scanned. Because images were aligned, annotations of SOX10 image analysis were directly transferred to H&E stains of the training set. Based on 1,221,367 annotated nuclei, a convolutional neural network for calculating tumor burden (CNNTB) was developed. For primary melanomas, precision of annotation was 100% (95%CI, 99% to 100%) for tumor cells and 99% (95%CI, 98% to 100%) for normal cells. Due to low or missing tumor-cell SOX10 positivity, precision for normal cells was markedly reduced in lymph-node and organ metastases compared with primary melanomas (p < 0.001). Compared with stereological counts within skin lesions, mean difference in tumor burden was 6% (95%CI, −1% to 13%, p = 0.10) for CNNTB and 16% (95%CI, 4% to 28%, p = 0.02) for pathologists. Conclusively, the technique produced a large annotated H&E training set with high quality within a reasonable timeframe for primary melanomas and subcutaneous metastases. For these lesion types, the training set generated a high-performing CNNTB, which was superior to the routine assessments of pathologists. Full article
Show Figures

Figure 1

15 pages, 16690 KiB  
Article
Global Research Trends of Artificial Intelligence on Histopathological Images: A 20-Year Bibliometric Analysis
by Wentong Zhou, Ziheng Deng, Yong Liu, Hui Shen, Hongwen Deng and Hongmei Xiao
Int. J. Environ. Res. Public Health 2022, 19(18), 11597; https://0-doi-org.brum.beds.ac.uk/10.3390/ijerph191811597 - 15 Sep 2022
Cited by 4 | Viewed by 2578
Abstract
Cancer has become a major threat to global health care. With the development of computer science, artificial intelligence (AI) has been widely applied in histopathological images (HI) analysis. This study analyzed the publications of AI in HI from 2001 to 2021 by bibliometrics, [...] Read more.
Cancer has become a major threat to global health care. With the development of computer science, artificial intelligence (AI) has been widely applied in histopathological images (HI) analysis. This study analyzed the publications of AI in HI from 2001 to 2021 by bibliometrics, exploring the research status and the potential popular directions in the future. A total of 2844 publications from the Web of Science Core Collection were included in the bibliometric analysis. The country/region, institution, author, journal, keyword, and references were analyzed by using VOSviewer and CiteSpace. The results showed that the number of publications has grown rapidly in the last five years. The USA is the most productive and influential country with 937 publications and 23,010 citations, and most of the authors and institutions with higher numbers of publications and citations are from the USA. Keyword analysis showed that breast cancer, prostate cancer, colorectal cancer, and lung cancer are the tumor types of greatest concern. Co-citation analysis showed that classification and nucleus segmentation are the main research directions of AI-based HI studies. Transfer learning and self-supervised learning in HI is on the rise. This study performed the first bibliometric analysis of AI in HI from multiple indicators, providing insights for researchers to identify key cancer types and understand the research trends of AI application in HI. Full article
Show Figures

Figure 1

19 pages, 1195 KiB  
Article
Prior to Implementation of Digital Pathology—Assessment of Expectations among Staff by Means of Normalization Process Theory
by Minne L. N. Mikkelsen, Marianne H. Frederiksen, Niels Marcussen, Bethany Williams and Kristian Kidholm
Int. J. Environ. Res. Public Health 2022, 19(12), 7253; https://0-doi-org.brum.beds.ac.uk/10.3390/ijerph19127253 - 14 Jun 2022
Cited by 5 | Viewed by 1701
Abstract
The Region of Southern Denmark is the first in Denmark to implement digital pathology (DIPA), starting at the end of 2020. The DIPA process involves changes in workflow, and the pathologist will have to diagnose based on digital whole slide imaging instead of [...] Read more.
The Region of Southern Denmark is the first in Denmark to implement digital pathology (DIPA), starting at the end of 2020. The DIPA process involves changes in workflow, and the pathologist will have to diagnose based on digital whole slide imaging instead of through the traditional use of the conventional light microscope and glass slides. In addition, in the laboratory, the employees will have to implement one more step to their workflow—scanning of tissue. The aim of our study was to assess the expectations and readiness among employees and management towards the implementation of DIPA, including their thoughts and motivations for starting to use DIPA. We used a mixed-method approach. Based on the findings derived from 18 semi-structured interviews with employees from the region’s departments of pathology, we designed a questionnaire, including questions from the normalization measure development tool. The questionnaires were e-mailed to 181 employees. Of these employees, 131 responded to the survey. Overall, they reported feeling sufficiently tech-savvy to be able to use DIPA, and they had high expectations as well as motivation and readiness for the upcoming changes. However, the employees were skeptical regarding the allocation of resources, and few were aware of reports about the effects of DIPA. Based on the findings, it seems to be important to provide not only a thorough introduction to the new intervention and the changes it will entail, but also to continue to ensure that the staff know how it works and why it is necessary to implement. Full article
Show Figures

Figure 1

Other

Jump to: Research

11 pages, 784 KiB  
Perspective
Perspectives on Complexity, Chaos and Thermodynamics in Environmental Pathology
by Maurizio Manera
Int. J. Environ. Res. Public Health 2021, 18(11), 5766; https://0-doi-org.brum.beds.ac.uk/10.3390/ijerph18115766 - 27 May 2021
Cited by 4 | Viewed by 2638
Abstract
Though complexity science and chaos theory have become a common scientific divulgation theme, medical disciplines, and pathology in particular, still rely on a deterministic, reductionistic approach and still hesitate to fully appreciate the intrinsic complexity of living beings. Herein, complexity, chaos and thermodynamics [...] Read more.
Though complexity science and chaos theory have become a common scientific divulgation theme, medical disciplines, and pathology in particular, still rely on a deterministic, reductionistic approach and still hesitate to fully appreciate the intrinsic complexity of living beings. Herein, complexity, chaos and thermodynamics are introduced with specific regard to biomedical sciences, then their interconnections and implications in environmental pathology are discussed, with particular regard to a morphopathological, image analysis-based approach to biological interfaces. Biomedical disciplines traditionally approach living organisms by dissecting them ideally down to the molecular level in order to gain information about possible molecule to molecule interactions, to derive their macroscopic behaviour. Given the complex and chaotic behaviour of living systems, this approach is extremely limited in terms of obtainable information and may lead to misinterpretation. Environmental pathology, as a multidisciplinary discipline, should grant privilege to an integrated, possibly systemic approach, prone to manage the complex and chaotic aspects characterizing living organisms. Ultimately, environmental pathology should be interested in improving the well-being of individuals and the population, and ideally the health of the entire ecosystem/biosphere and should not focus merely on single diseases, diseased organs/tissues, cells and/or molecules. Full article
Show Figures

Figure 1

Back to TopTop