Digital Pathology: New Initiative in Pathology

Cho, William C.

doi:10.3390/biom12091314

Cited by 2 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…By reaching intraclass correlation coefficient values similar to those in the IKWG study, they proved that the artificial intelligence-based automated Ki-67 scoring method may be used to achieve good reproducibility compared to pathologists [9,10]. Furthermore, a comparative analysis of the visual assessment and automated digital image analysis of the Ki-67 index in breast cancer was performed by Zhong et al [11] and found a significant degree of consistency between both methods [11].…”

Section: Introductionmentioning

confidence: 74%

Use of a Novel Deep Learning Open-Source Model for Quantification of Ki-67 in Breast Cancer Patients in Pakistan: A Comparative Study between the Manual and Automated Methods

Zehra,

Jaffar,

Shams

et al. 2023

Diagnostics

View full text Add to dashboard Cite

Introduction: Breast cancer is the most common cancer in women; its early detection plays a crucial role in improving patient outcomes. Ki-67 is a biomarker commonly used for evaluating the proliferation of cancer cells in breast cancer patients. The quantification of Ki-67 has traditionally been performed by pathologists through a manual examination of tissue samples, which can be time-consuming and subject to inter- and intra-observer variability. In this study, we used a novel deep learning model to quantify Ki-67 in breast cancer in digital images prepared by a microscope-attached camera. Objective: To compare the automated detection of Ki-67 with the manual eyeball/hotspot method. Place and duration of study: This descriptive, cross-sectional study was conducted at the Jinnah Sindh Medical University. Glass slides of diagnosed cases of breast cancer were obtained from the Aga Khan University Hospital after receiving ethical approval. The duration of the study was one month. Methodology: We prepared 140 digital images stained with the Ki-67 antibody using a microscope-attached camera at 10×. An expert pathologist (P1) evaluated the Ki-67 index of the hotspot fields using the eyeball method. The images were uploaded to the DeepLiif software to detect the exact percentage of Ki-67 positive cells. SPSS version 24 was used for data analysis. Diagnostic accuracy was also calculated by other pathologists (P2, P3) and by AI using a Ki-67 cut-off score of 20 and taking P1 as the gold standard. Results: The manual and automated scoring methods showed a strong positive correlation as the kappa coefficient was significant. The p value was <0.001. The highest diagnostic accuracy, i.e., 95%, taking P1 as gold standard, was found for AI, compared to pathologists P2 and P3. Conclusions: Use of quantification-based deep learning models can make the work of pathologists easier and more reproducible. Our study is one of the earliest studies in this field. More studies with larger sample sizes are needed in future to develop a cohort.

show abstract

Section: Introductionmentioning

confidence: 74%

Use of a Novel Deep Learning Open-Source Model for Quantification of Ki-67 in Breast Cancer Patients in Pakistan: A Comparative Study between the Manual and Automated Methods

Zehra,

Jaffar,

Shams

et al. 2023

Diagnostics

View full text Add to dashboard Cite

show abstract

“…B. Mib1/Ki-67-Färbung). Heutzutage haben die meisten PathologInnen ihre Ausbildung unter Einsatz des konventionellen Lichtmikroskops abgeschlossen, daher stellt dieses nach wie vor den Goldstandard in der histopathologischen Diagnostik dar [ 17 , 18 ]. Um eine optimale digitale Transformation zu erreichen, ist daher eine enge Zusammenarbeit zwischen den PathologInnen und dem technischen Team unerlässlich.…”

Section: Umstellungsprozess Im Labor Und Bei Der Befundung Notwendigunclassified

Digital transformation of a routine histopathology lab

Iwuajoku,

Haas,

Ekici

et al. 2024

Pathologie

View full text Add to dashboard Cite

ZusammenfassungDie Digitalisierung des histopathologischen Eingangslabors ist ein wichtiger und entscheidender Schritt in der digitalen Transformation der Pathologie. Digitalisierung ermöglicht zahlreiche neue Optionen wie den Zugang zu großen Datensätzen für KI-gestützte Auswertungen, mobiles Arbeiten und Homeoffice für FachärztInnen sowie eine schnellere und vereinfachte Bereitstellung von Bildern und Daten für Forschungsarbeiten, Konferenzen und Tumorboards. Dennoch bedeutet die Umstellung zu einem vollständig digitalen Workflow auch erheblichen Aufwand im technischen und personellen Bereich und benötigt ein durchdachtes und flexibles Changemanagement, um Reibungsverluste gerade im personellen Bereich möglichst gering zu halten und wertvolles Potenzial talentierter, aber möglicherweise veränderungsscheuer Mitarbeiter nicht zu verlieren. Dieser Artikel fasst die Erfahrungswerte unseres Institutes im Hinblick auf technische und personelle Herausforderungen während der Transformation zur digitalen Pathologie zusammen und bietet einen umfassenden Überblick über potenziell problematische Schnittstellen bei der Umstellung des Routinebetriebes auf einen digitalen Workflow.

show abstract

Digital Pathology: New Initiative in Pathology

Abstract: Digital pathology (DP) is an emerging field of pathology that manages information generated from digitized specimen slides [...]

Cited by 2 publications

References 14 publications

Use of a Novel Deep Learning Open-Source Model for Quantification of Ki-67 in Breast Cancer Patients in Pakistan: A Comparative Study between the Manual and Automated Methods

Use of a Novel Deep Learning Open-Source Model for Quantification of Ki-67 in Breast Cancer Patients in Pakistan: A Comparative Study between the Manual and Automated Methods

Digital transformation of a routine histopathology lab

Contact Info

Product

Resources

About