article · Journal of Imaging
Brain tumours represent a significant cause of mortality across both adult and child populations. Typical region-growing segmentation methods rely on manual or semi-manual seed point selection, which impairs segmentation accuracy. To address this, an enhanced region-growing technique automates seed point initialisation. The method strips the skull from magnetic resonance images using thresholding and partitions the remaining image into eight blocks. The five blocks displaying the highest mean intensities are identified as initial seed points, generating five potential regions of interest. These regions are evaluated against ground-truth data using metrics such as dice similarity score, intersection over union, and accuracy to identify the optimal segment. Testing on the BRATS2015 dataset achieved dice similarity scores of 0.89 across 15 images, 0.90 across 12 images, and 0.80 across 800 images, yielding an overall average dice similarity score of 0.86.
Accurate segmentation of brain tumours from magnetic resonance scans is vital for understanding tumour boundaries and aiding medical analysis. Conventional region-growing methods depend on human input to select starting points, which can introduce inconsistency. Automating this seed selection helps streamline image processing and provides consistent segmentation results that compare well with deep learning benchmarks.
This method offers an automated processing approach that could be integrated into diagnostic radiology software or clinical decision-support tools for healthcare specialists analysing brain scans. Because the system was evaluated on a benchmark research dataset using up to 800 images, it represents applied and tested research that would require further clinical validation and workflow integration before deployment in real-world healthcare settings.
AI-generated from the published abstract. Always read the original work before citing.
A brain tumor is one of the foremost reasons for the rise in mortality among children and adults. A brain tumor is a mass of tissue that propagates out of control of the normal forces that regulate growth inside the brain. A brain tumor appears when one type of cell changes from its normal characteristics and grows and multiplies abnormally. The unusual growth of cells within the brain or inside the skull, which can be cancerous or non-cancerous has been the reason for the death of adults in developed countries and children in under developing countries like Ethiopia. The studies have shown that the region growing algorithm initializes the seed point either manually or semi-manually which as a result affects the segmentation result. However, in this paper, we proposed an enhanced region-growing algorithm for the automatic seed point initialization. The proposed approach's performance was compared with the state-of-the-art deep learning algorithms using the common dataset, BRATS2015. In the proposed approach, we applied a thresholding technique to strip the skull from each input brain image. After the skull is stripped the brain image is divided into 8 blocks. Then, for each block, we computed the mean intensities and from which the five blocks with maximum mean intensities were selected out of the eight blocks. Next, the five maximum mean intensities were used as a seed point for the region growing algorithm separately and obtained five different regions of interest (ROIs) for each skull stripped input brain image. The five ROIs generated using the proposed approach were evaluated using dice similarity score (DSS), intersection over union (IoU), and accuracy (Acc) against the ground truth (GT), and the best region of interest is selected as a final ROI. Finally, the final ROI was compared with different state-of-the-art deep learning algorithms and region-based segmentation algorithms in terms of DSS. Our proposed approach was validated in three different experimental setups. In the first experimental setup where 15 randomly selected brain images were used for testing and achieved a DSS value of 0.89. In the second and third experimental setups, the proposed approach scored a DSS value of 0.90 and 0.80 for 12 randomly selected and 800 brain images respectively. The average DSS value for the three experimental setups was 0.86.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3390/jimaging7020022
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
