Efficient Multi-Organ Segmentation Using SpatialConfiguration-Net with Low GPU Memory Requirements

TL;DR

This paper presents an efficient multi-organ segmentation method based on SpatialConfiguration-Net that incorporates spatial priors and is optimized for low GPU memory usage, suitable for clinical applications.

Contribution

The work introduces architectural modifications to SCN for reduced memory consumption and optimized inference, enhancing clinical applicability of multi-organ segmentation.

Findings

Achieved accurate multi-organ segmentation with low GPU memory requirements

Reduced inference time through optimized implementation

Maintained high prediction quality despite model modifications

Abstract

Even though many semantic segmentation methods exist that are able to perform well on many medical datasets, often, they are not designed for direct use in clinical practice. The two main concerns are generalization to unseen data with a different visual appearance, e.g., images acquired using a different scanner, and efficiency in terms of computation time and required Graphics Processing Unit (GPU) memory. In this work, we employ a multi-organ segmentation model based on the SpatialConfiguration-Net (SCN), which integrates prior knowledge of the spatial configuration among the labelled organs to resolve spurious responses in the network outputs. Furthermore, we modified the architecture of the segmentation model to reduce its memory footprint as much as possible without drastically impacting the quality of the predictions. Lastly, we implemented a minimal inference script for which we optimized both, execution time and required GPU memory.