Operational Learning-based Boundary Estimation in Electromagnetic Medical Imaging
This addresses the challenge of improving imaging performance without complicating systems or being affected by movement, specifically for electromagnetic medical imaging applications.
The paper tackles the problem of estimating object boundaries in electromagnetic medical imaging by proposing a learning-based method that uses reflection coefficients from the same imaging data, eliminating the need for additional sensors. The result is a model that achieves an average dissimilarity of 0.012 in Hu-moment for head boundary detection in clinical trials.
Incorporating boundaries of the imaging object as a priori information to imaging algorithms can significantly improve the performance of electromagnetic medical imaging systems. To avoid overly complicating the system by using different sensors and the adverse effect of the subject's movement, a learning-based method is proposed to estimate the boundary (external contour) of the imaged object using the same electromagnetic imaging data. While imaging techniques may discard the reflection coefficients for being dominant and uninformative for imaging, these parameters are made use of for boundary detection. The learned model is verified through independent clinical human trials by using a head imaging system with a 16-element antenna array that works across the band 0.7-1.6 GHz. The evaluation demonstrated that the model achieves average dissimilarity of 0.012 in Hu-moment while detecting head boundary. The model enables fast scan and image creation while eliminating the need for additional devices for accurate boundary estimation.