A cross-border community for researchers with openness, equality and inclusion
Authors: Dwarakanath Samhitha, PES University P G Rahul, PES University Vanamala HR, PES university R Rakshith, PES UniversityRao HS Rakshitha, PES University
In this work, we propose an innovative approach to present a 3D model of the heart in Augmented Reality (AR) and Virtual Reality (VR). Leveraging the image congenital heart disease dataset, we perform a novel procedure of eight-class heart segmentation using the UNET architecture. In tandem with the UNET architecture, we use ResNet34, Inceptionv3 and VGG16 as the backbones. Among these combinations, the most favourable results were obtained when utilizing ResNet34 as the backbone. The 3D volume of the heart is constructed using the Marching Cubes and Ray Casting algorithms. To enhance the understanding of the heart’s intricacies, we use the Oculus Meta Quest 2 headset for immersive visualization of the 3D model.
Keywords: Augmented Reality (AR),Medical Image Segmentation,Volumetric Rendering,Virtual Reality (VR)
Published in: IEEE Transactions on Antennas and Propagation( Volume: 71, Issue: 4, April 2023)
Page(s): 2908 - 2921
Date of Publication: 2908 - 2921
DOI: 10.1109/TAP.2023.3240032
Publisher: UNITED SOCIETIES OF SCIENCE
