Scientometric Analysis and Visualization of Research on Breast Mitosis Cells Detection

Goh, Weng Yee (2023) Scientometric Analysis and Visualization of Research on Breast Mitosis Cells Detection. Final Year Project (Bachelor), Tunku Abdul Rahman University of Management and Technology.

Text Full Text - Goh Weng Yee.pdf Restricted to Registered users only Download (1MB)

Abstract

Breast cancer is one of the leading causes of cancer-related deaths in women worldwide. Accurate detection of mitosis in breast cancer cells is critical for diagnosis and treatment planning. Although numerous research articles on mitosis cell detection have been available for effective scholarly communication, most studies have focused on reviewing the techniques and results of mitosis cell detection. Therefore, this study aimed to conduct a scientometric analysis and visualisation of research on breast mitosis cell detection over the past 20 years (2002-2021). The study employed bibliometric techniques to identify patterns and trends, as well as state-of-the-art methods in this field. The methodology used in this scientometric analysis and visualisation of research on breast mitosis cell detection involved a systematic search of search engines such as Scopus, Elsevier, Springer, and IEEE for articles published between 2002 and 2021. The search was conducted using a set of pre-defined search terms related to breast mitosis cell detection. After applying inclusion and exclusion criteria, a total of 49 articles were included in the analysis. Quantitative and qualitative analysis techniques were used to analyse the data. Self-assessment was performed to ensure the quality of this study. The study analysed the scientometric trends in breast mitosis cell detection research. Asia contributed 60% of the organisations, with China being the most connected region and a key hub for collaboration. The Journal of Pathology Informatics and Elsevier had the highest contribution in the journal and publisher, respectively. The number of publications fluctuated over the 20-year period analysed. The Scopus "Subject Area" index revealed that Medicine: Health Informatics was the most common subject area. The co-occurrence map showed "mitosis detection" and "breast cancer" as the top two keywords. Deep learning-based methods are gaining popularity in the field. The co-authorship network analysis identified clusters of authors with a limited scope of collaborations. The study also discussed three approaches for mitosis detection: handcrafted features-based methods, deep learning-based methods, and fusion methods. The novelty of the study lies in its comprehensive scientometric analysis and visualisation of research on breast mitosis cell detection. The study covers a range of aspects, including geographic distribution, publication trends, subject area profiling, keyword analysis, and co-authorship network analysis. By examining the distribution of contributing organisations and journals, the study provides insights into the collaboration patterns in this research field. Furthermore, the study offers a qualitative analysis of the different approaches used for mitosis detection and their performance, which provides a better understanding of the state-of-the-art in this field. Overall, the study provides a valuable contribution to the literature on breast mitosis cell detection research, and its findings can inform future research directions in this area.