Work

ResNet's Rise in Histopathology: Bibliometric and Descriptive Analysis of Highly Cited Studies

Year: 2026
Type: article
Abstract: ABS TRACT Objective: This study aims to conduct a comprehensive bibliometric analysis of the top 50 most cited scientific publications on the application of ResNet architectures in histopathology, mapping the research landscape, identifying key contributors, and analyzing emerging trends among the most influential works.Material and Methods: We systematically retrieved 615 publications from Web of Science using a targeted search strategy on September 27, 2025.After applying inclusion criteria (article document type, English language), the top 50 most cited publications according to WoS citations were selected for analysis using bibliometric methods.VOSviewer (version 1.6.20),python programming language and specialized bibliometric tools were employed for data extraction and analysis, including publication trends, citation analysis, co-authorship networks, and keyword mapping.Results: The analysis revealed that the top 50 most cited papers represent a rapidly growing field with significant academic impact.The most cited paper (Bándi et al., 2019) received 347 citations.Among these highly cited publications, China and the United States were the most productive countries, while IEEE Access was the most prolific journal.Deep learning, breast cancer, and transfer learning emerged as the most frequent keywords.Network analysis identified 5 distinct research clusters with strong international collaborations within this elite group of publications.Conclusion: The top 50 most cited ResNet applications in histopathology demonstrate substantial impact on digital pathology research, particularly in cancer diagnosis and classification.These highly influential works show strong interdisciplinary collaboration between computer science and medical imaging specialists, with promising future directions in explainable artificial intelligence and multi-modal data integration.
Author: Serdar YANIK
Language: English
Open Access status: hybrid
OpenAlex ID: W7204237103
FWCI:
Cites: 25
Cited by:
Related to: 10