3D Bounding Box Detection in Volumetric Medical Image Data: A Systematic Literature Review

TL;DR

This systematic review analyzes recent methods for 3D bounding box detection in volumetric medical images, highlighting the shift towards deep learning techniques like CNNs over traditional manual feature methods.

Contribution

It provides a comprehensive overview of current approaches, comparing 2D and 3D methods, and guides researchers in selecting effective bounding box detection strategies.

Findings

Deep learning methods dominate recent research

CNNs outperform manual feature engineering approaches

The review offers a practical overview for method selection

Abstract

This paper discusses current methods and trends for 3D bounding box detection in volumetric medical image data. For this purpose, an overview of relevant papers from recent years is given. 2D and 3D implementations are discussed and compared. Multiple identified approaches for localizing anatomical structures are presented. The results show that most research recently focuses on Deep Learning methods, such as Convolutional Neural Networks vs. methods with manual feature engineering, e.g. Random-Regression-Forests. An overview of bounding box detection options is presented and helps researchers to select the most promising approach for their target objects.