A Brain Organoid-Based Mitosis Dataset for Automatic Analysis of Brain Diseases
Hameed, Nisa
Hameed, Nisa
Author
Supervisor
Department
Machine Learning
Embargo End Date
2025-05-21
Type
Thesis
Date
2024
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Research in neurodevelopmental and genetic disorders encompasses a broad range of topics aimed at understanding the underlying mechanisms, identifying risk factors, developing diagnostic tools, and exploring potential treatments for disorders that affect brain development that are influenced by genetic factors. Analysing neurobiological mechanisms in embryonic brain help to study the processes involved in brain development in embryos and how disruptions contribute to genetic brain diseases. Recent advances have enabled the study of human brain development using brain organoids derived from stem cells. Quantifying cellular processes like mitosis in these organoids offers insights into neurodevelopmental disorders, but the manual analysis is time-consuming, and existing datasets lack specific details for brain organoid studies. In this work a new dataset BOrg, is introduced to study mitotic events in the embryonic development of the brain using confocal microscopy images of brain organoids. BOrg utilizes an efficient annotation pipeline with sparse point annotations and techniques that minimize expert effort, overcoming limitations of standard deep learning approaches on sparse data. Benchmark state-of-the-art object detection and cell counting models are adapted on BOrg for detecting and analyzing mitotic cells across prophase, metaphase, anaphase, and telophase stages. Results demonstrate that these adapted models show modest improvement in mitosis analysis efficiency and accuracy for brain organoid research compared to original methods. BOrg facilitates the development of automated tools to quantify statistics like mitosis rates, aiding mechanistic studies of neurodevelopmental processes and disorders.
Citation
N. Hameed, "A Brain Organoid-Based Mitosis Dataset for Automatic Analysis of Brain Diseases", MS. Thesis, Machine Learning, MBZUAI, Abu Dhabi, UAE, 2024