Brain Injury Localization in Electromagnetic Imaging using Symmetric Crossing Lines Method
Zhu, G.; Bialkowski, A.; Crozier, S.; Guo, L.; Nguyen, P.; Stancombe, A.; Abbosh, A.
Show abstract
To avoid death or disability, patients with brain injury should undertake a diagnosis at the earliest time and accept frequent monitoring after starting any medical intervention. This paper presents a novel approach to localize brain injury using the intersection of pairs of signals from symmetrical antennas based on the hypothesis that healthy brains are approximately symmetric that the bleeding targets will lead to significantly different amplitude and phase changes if one of pair of transmit signals cross targets. The scattered signals (S-parameters) are acquired using 100 realistic brain models and 150 experimental data measurements. Firstly, three pair of horizontal antennas are used to detect target crossing which line and in which hemisphere in low frequency bands and estimate the size using high frequency bands. Then, an intersection of two pairs of antennas are identified the position of the target. Finally, a heat map is used to visualise the stroke brain. The results indicate that crossing pairs of antenna signals from the hemisphere with a blood mass exhibit significantly different signal amplitude in the graph features compared to those without the target (p<0.003). The experiments show that our novel localization algorithm can achieve an accuracy of 0.85{+/-}0.08 Dice similarity coefficient based on 150 experimental measurements using an elliptical container, which is suitable for brain injury localization.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Development of a Coupled Simulation Toolkit for Computational Radiation Biology Based on Geant4 and CompuCell3D 93%
- Impact of Focused Ultrasound on the Cellular Network of Liver Tissue: A New Perspective for Thermal Lesion Detection 93%
- Deciphering Oxygen Distribution and Hypoxia Profiles in the Tumor Microenvironment: A Data-Driven Mechanistic Modeling Approach 93%
Similar papers in this journal
- A Robust Spike Sorting Method based on the Joint Optimization of Linear Discrimination Analysis and Density Peaks 94%
- Radius-Optimized Efficient Template Matching for Lesion Detection from Brain Images 94%
- Segmentation of Pancreatic Ductal Adenocarcinoma (PDAC) and surrounding vessels in CT images using deep convolutional neural networks and Texture Descriptors 94%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.