Deep Learning-Based Automatic Segmentation for Reconstructing Vertebral Anatomy of Healthy Adolescents and Patients With Adolescent Idiopathic Scoliosis (AIS) Using MRI Data

Abstract

MRI is a non-ionising imaging modality that could be used as an alternative to Xray-based imaging methods to accurately assess the 3D morphology of the vertebral anatomy of scoliosis patients. However, a major caveat in utilising MRI is the significant amount of time required to manually segment the anatomy of interest. To overcome this limitation, we implemented a fully automatic method for the 3D segmentation of thoracic vertebrae, including vertebral body and posterior elements, of healthy adolescents and patients with Adolescent Idiopathic Scoliosis (AIS) using MRI data. 62 MRI scans were obtained from 3 healthy volunteers and 25 patients with AIS. A state-of-the-art deep-learning network for segmentation was trained using image patches of the apical vertebra (T7, T8, T9 or T10) extracted from 20 AIS patient MRIs. Ad-hoc data augmentation was adopted to represent the unlabeled vertebral levels in the dataset (T5-T6, T11-T12). The vertebral levels T5-T12 were then segmented for the remaining MRI datasets by feeding to the network the MRI patches generated by translating a window of fixed size and stride onto the MRI volume. The mean dice score coefficient for the AIS patient vertebral levels T5-T12 was of 87%±4.3%, which was comparable to the performance achieved by two experts. On average, 93% and 97% of the MRI segmented slices were considered clinically acceptable morphological reconstructions of AIS and healthy volunteer vertebrae, respectively. The proposed method can be considered as the first step towards more routine MRIbased imaging of AIS osseous deformities, reducing the cumulative exposure of young patients to ionising radiation.