Table 1.

Comparison with similar review articles.

Review title	Month and year	Scope and coverage	Comparison with our review
Vision transformers in Medical Computer Vision—A Contemplative Retrospection [20]	March 2022	The title is specific to ViTa; however, the full text has a very broad scope with discussions on deep learning, CNNsb, and ViT. It covers different applications in medical computer vision, including the classification of disease, segmentation of tissues, registration tasks in medical images, and image-to-text applications. It does not provide much text on brain cancer applications of ViT. Many recent studies of 2022 are left out as the preprint was released in March 2022. It does not provide a comparative study on the computational complexity of ViT-based models.	Our review is also specific to ViT. Our review is specific to brain cancer applications. Our review includes more recent studies on ViT. Our review provides a comparative study of the computational complexity of the ViT-based models.
Transformers in medical imaging: A survey [25]	January 2022	It is specific to ViT. It has a broad scope as different medical imaging applications are included. It does not include many recent studies on ViT for brain cancer imaging (as the preprint was released in January 2022).	Our review is also specific to ViT. Our review is specific to brain cancer applications. Our review includes more recent studies on ViT.
Transformers in Medical Image Analysis: A Review [23]	August 2022	It is specific to ViT. It has broad scope as different medical imaging applications are included. It provides a descriptive review of ViT techniques for different medical imaging modalities. It does not provide a quantitative analysis of the computational complexity of ViT-based methods.	Our review is also specific to ViT. Our review is specific to brain cancer applications. Our review provides a comparative study of the computational complexity of the ViT-based models.
Brain Tumor Diagnosis Using Machine Learning, Convolutional Neural Networks, Capsule Neural Networks and Vision Transformers, Applied to MRIc: A Survey [22]	July 2022	It covers applications specific to brain tumor segmentation. It has a broad scope, as it includes studies on CNNs, capsule networks, and ViT. It includes only 5 studies on ViT. Many recent studies are left out as it covers only 4 studies from 2022. It provides no quantitative analysis of computational complexity.	Our review is also specific to brain cancer and brain tumor. Our review covers more recent studies. Our review includes 22 studies on ViT for brain cancer application. Our review provides a comparative study of the computational complexity of the ViT-based models.
A survey of brain tumor segmentation and classification algorithms [24]	September 2021	It has a very broad scope as it covers traditional machine learning and deep learning methods. It covers studies until early 2021 only.	Our review is specific to ViT. Our review covers more recent studies.
Deep learning for brain tumor segmentation: a survey of state-of-the-art [21]	January 2021	It has a broad scope as it covers different deep learning methods. Many recent studies are left out.	Our review is specific to ViT. Our review covers more recent studies.

^aViT: vision transformer.

^bCNN: convolutional neural network.

^cMRI: magnetic resonance imaging.