Search

Volume Projection Imaging from ultrasound data is a promising technique to visualize spine features and diagnose Adolescent Idiopathic Scoliosis. In this paper, we present a novel multi-task framework to reduce the scan noise in volume projection images and to segment different spine features simultaneously, which provides an appealing alternative for intelligent scoliosis assessment in clinical applications. Our proposed framework consists of two streams: i) A noise removal stream based on generative adversarial networks, which aims to achieve effective scan noise removal in a weakly-supervised manner, i.e., without paired noisy-clean samples for learning; ii) A spine segmentation stream, which aims to predict accurate bone masks. To establish the interaction between these two tasks, we propose a selective feature-sharing strategy to transfer only the beneficial features, while filtering out the useless or harmful information. We evaluate our proposed framework on both scan noise removal and spine segmentation tasks. The experimental results demonstrate that our proposed method achieves promising performance on both tasks, which provides an appealing approach to facilitating clinical diagnosis. [ABSTRACT FROM AUTHOR]

Radiographic Cobb's angle is the gold standard for evaluation of spinal curvature, however, X-ray is ionising. In contrast, ultrasound is non-ionising and inexpensive. However, no study has reported the reliability and accuracy of ultrasound on sagittal curvature analysis. Ultrasound and X-ray scanning were conducted on 16 sets of spine phantoms with different deformities. Intra-rater and inter-rater reliability, correlations, mean absolute differences (MAD) and linear regression of ultrasound spinous process angles (USSPA), X-ray spinous process angles (XSPA) and X-ray Cobb's angles (XCA) together with the intra-operator reliability of USSPA were investigated. In addition, USSPA and XCA of five AIS subjects were obtained using the ultrasound system. In the phantom study, excellent intra-rater and inter-rater reproducibility for the three angles and excellent intra-operator reproducibility for USSPA were demonstrated. Good to moderate or better correlations were obtained among the angles. All three angles indicated positive linear relationships with MAD ≤ 6.0°. The results of the preliminary study demonstrated a high intra-reliability for the ultrasound measurements. The measured difference between the USSPA and XCA methods was 6.3° ± 5.4°. The results showed that ultrasound is feasible for measuring sagittal curvature and has the potential for monitoring the curve progression and evaluating sagittal spinal profiles. [ABSTRACT FROM AUTHOR]

• Established a dataset for spine segmentation of ultrasound scoliosis images. • Build a dual-task spine transverse vertebrae segmentation network based on U-Net. • An auxiliary shape regularization task is used to assist the semantic segmentation. • Fused the features of two-stream to enhance their representation abilities. • Imported ASPP structure which also fused features of auxiliar network. • Obtained a promising result and are the first team to segment them automatically. 3D ultrasound imaging has become one of the common diagnosis ways to assess scoliosis since it is radiation-free, real-time, and low-cost. Spine curvature angle measurement is an important step to assess scoliosis precisely. One way to calculate the angle is using the vertebrae features of the 2-D coronal images to identify the most tilted vertebrae. To do the measurement, the segmentation of the transverse vertebrae is an important step. In this paper, we propose a dual-task ultrasound transverse vertebrae segmentation network (D-TVNet) based on U-Net. First, we arrange an auxiliary shape regularization network to learn the contour segmentation of the bones. It improves the boundary segmentation and anti-interference ability of the U-Net by fusing some of the features of the auxiliary task and the main task. Then, we introduce the atrous spatial pyramid pooling (ASPP) module to the end of the down-sampling stage of the main task stream to improve the relative feature extraction ability. To further improve the boundary segmentation, we extendedly fuse the down-sampling output features of the auxiliary network in the ASPP. The experiment results show that the proposed D-TVNet achieves the best dice score of 86.68% and the mean dice score of 86.17% based on cross-validation, which is an improvement of 5.17% over the baseline U-Net. An automatic ultrasound spine bone segmentation network with promising results has been achieved. [ABSTRACT FROM AUTHOR]