Spatiotemporal Manifold Prediction Model for Anterior Vertebral Body Growth Modulation Surgery in Idiopathic Scoliosis

TL;DR

This paper presents a statistical framework using a discriminant manifold and spatiotemporal regression to predict surgical outcomes of AVBGM in adolescent scoliosis patients, aiding preoperative decision-making.

Contribution

It introduces a novel manifold-based predictive model that captures spine correction trajectories and differentiates responders from non-responders prior to surgery.

Findings

Accurately predicted spine correction with 2.1-degree error

Constructed a discriminant manifold for patient response classification

Generated models comparable to biomechanical simulations

Abstract

Anterior Vertebral Body Growth Modulation (AVBGM) is a minimally invasive surgical technique that gradually corrects spine deformities while preserving lumbar motion. However the selection of potential surgical patients is currently based on clinical judgment and would be facilitated by the identification of patients responding to AVBGM prior to surgery. We introduce a statistical framework for predicting the surgical outcomes following AVBGM in adolescents with idiopathic scoliosis. A discriminant manifold is first constructed to maximize the separation between responsive and non-responsive groups of patients treated with AVBGM for scoliosis. The model then uses subject-specific correction trajectories based on articulated transformations in order to map spine correction profiles to a group-average piecewise-geodesic path. Spine correction trajectories are described in a piecewise-geodesic fashion to account for varying times at follow-up exams, regressing the curve via a quadratic optimization process. To predict the evolution of correction, a baseline reconstruction is projected onto the manifold, from which a spatiotemporal regression model is built from parallel transport curves inferred from neighboring exemplars. The model was trained on 438 reconstructions and tested on 56 subjects using 3D spine reconstructions from follow-up exams, with the probabilistic framework yielding accurate results with differences of 2.1 +/- 0.6deg in main curve angulation, and generating models similar to biomechanical simulations.