Abstract—We analyzed recently published literature from the last five years to identify methods for 3D bounding box detection in volumetric medical image data. A tabular comparison presents the relevant papers and their findings. Various approaches, falling under four identified main categories are described and illustrated. Object detection by means of a 3D bounding box can often be implemented in both 2D and 3D. The advantages and disadvantages of both implementations are discussed. The overview of methods and implementations helps researchers in selecting the most promising approach for their given circumstances. The results show that current research is focused on Deep Learning methods e.g., Convolutional Neural Networks.
Index Terms—literature review, medical imaging, 3D bounding box, object detection, volumetric image data
Cite: Daria Kern and Andre Mastmeyer, "3D Bounding Box Detection in Volumetric Medical Image Data: A Systematic Literature Review," Journal of Image and Graphics, Vol. 10, No. 1, pp. 17-27, March 2022.
Copyright © 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.
Copyright © 2012-2023 Journal of Image and Graphics, All Rights Reserved