Seg4Reg+: Consistency Learning between Spine Segmentation and Cobb Angle Regression

TL;DR

Seg4Reg+ introduces a multi-task framework that jointly optimizes spine segmentation and Cobb angle regression, leveraging consistency learning and attention regularization to improve scoliosis assessment accuracy.

Contribution

The paper presents a novel multi-task learning approach with attention regularization and triangle consistency learning for improved spine segmentation and Cobb angle estimation.

Findings

Outperforms state-of-the-art methods on AASCE dataset.

Effective use of CAMs for supervision and region-of-interest enhancement.

Joint optimization improves both segmentation and regression accuracy.

Abstract

Automated methods for Cobb angle estimation are of high demand for scoliosis assessment. Existing methods typically calculate the Cobb angle from landmark estimation, or simply combine the low-level task (e.g., landmark detection and spine segmentation) with the Cobb angle regression task, without fully exploring the benefits from each other. In this study, we propose a novel multi-task framework, named Seg4Reg+, which jointly optimizes the segmentation and regression networks. We thoroughly investigate both local and global consistency and knowledge transfer between each other. Specifically, we propose an attention regularization module leveraging class activation maps (CAMs) from image-segmentation pairs to discover additional supervision in the regression network, and the CAMs can serve as a region-of-interest enhancement gate to facilitate the segmentation task in turn. Meanwhile, we design a novel triangle consistency learning to train the two networks jointly for global optimization. The evaluations performed on the public AASCE Challenge dataset demonstrate the effectiveness of each module and superior performance of our model to the state-of-the-art methods.