AUTHOR=Yanzhen Ming , Song Chen , Wanping Li , Zufang Yang , Wang Alan 

TITLE=Exploring approaches to tackle cross-domain challenges in brain medical image segmentation: a systematic review

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 18 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2024.1401329

DOI=10.3389/fnins.2024.1401329

ISSN=1662-453X

ABSTRACT=ackground: Brain medical image segmentation is a critical task in medical image processing, playing a significant role in theprediction and diagnosis of diseases such as stroke, Alzheimer's disease, and brain tumors.
Objectives: The primary objective of this review is to summarize and evaluate the strategies for addressing the cross-domain
problem in brain image segmentation, and identify their limitations.
Methods: This review adheres to the standards of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses
(PRISMA) for data processing and analysis. We retrieved relevant papers from PubMed, Web of Science, and IEEE databases from
January 2018 to December 2023, extracting information about the medical domain, imaging modalities, methods for addressing
cross-domain issues, experimental designs, and datasets from the selected papers. Results: A total of 71 studies were included and
analyzed in this review. The methods for tackling the cross-domain problem include Transfer Learning, Normalization,
Unsupervised Learning, Transformer models, and Convolutional Neural Networks (CNNs). On the ATLAS dataset, domain-adaptive
methods showed an overall improvement of approximately 3 percent in stroke lesion segmentation tasks compared to
non-adaptive methods. However, based on the methods used in MICCAI 2017 for white matter segmentation tasks, the current
datasets and experimental methods are diverse, making it difficult to intuitively compare the advantages and disadvantages of
the methods.
Conclusion: Although various techniques have been applied to address the cross-domain problem in brain image segmentation,
there is currently a lack of unified dataset collections and experimental standards. For instance, many studies are still based on
n-fold cross-validation, while methods directly based on cross-validation across sites or datasets are relatively scarce.
Furthermore, due to the diverse types of medical images in the field of brain segmentation, it is not straightforward to make
simple and intuitive comparisons of performance. These challenges need to be addressed in future research.