Multi-Scale Context-Guided Lumbar Spine Disease Identification with Coarse-to-fine Localization and Classification

TL;DR

This paper introduces CCF-Net, a multi-scale context-guided network with coarse-to-fine localization and classification for lumbar spine disease identification, achieving high accuracy with fewer parameters and data.

Contribution

The work proposes a novel multi-scale, context-guided network that effectively reduces parameters and data requirements while improving localization and classification accuracy.

Findings

Multi-scale context-guided module improves performance by over 5%.

Coarse-to-fine localization reduces computational cost.

High accuracy achieved with fewer parameters and less data.

Abstract

Accurate and efficient lumbar spine disease identification is crucial for clinical diagnosis. However, existing deep learning models with millions of parameters often fail to learn with only hundreds or dozens of medical images. These models also ignore the contextual relationship between adjacent objects, such as between vertebras and intervertebral discs. This work introduces a multi-scale context-guided network with coarse-to-fine localization and classification, named CCF-Net, for lumbar spine disease identification. Specifically, in learning, we divide the localization objective into two parallel tasks, coarse and fine, which are more straightforward and effectively reduce the number of parameters and computational cost. The experimental results show that the coarse-to-fine design presents the potential to achieve high performance with fewer parameters and data requirements. Moreover, the multi-scale context-guided module can significantly improve the performance by 6.45% and 5.51% with ResNet18 and ResNet50, respectively. Our code is available at https://github.com/czifan/CCFNet.pytorch.