A Improved Hybrid Attention Recurrent Residual U-Net approach for the segmentation of ultrasound spine images

Scoliosis is characterized by a three-dimensional deformation of the spine with a curvature exceeding 10°in the coronal plane. Conventionally, the gold standard for scoliosis diagnosis and spinal curvature measurement relies on X-ray imaging and the calculation of Cobb Angles. However, the ionizing radiation associated with X-rays poses potential risks, including the development of cancer. Moreover, the frequent use of X-rays for monitoring scoliosis progression or treatment outcomes increases the cumulative risk of these adverse effects. In contrast, ultrasound imaging emerges as a promising alternative. It is devoid of ionizing radiation, cost-effective, and highly portable, offering the potential for increased scoliosis screening and detection. Nonetheless, ultrasound spine imaging encounters challenges, notably low contrast and speckled noise, which compromise image quality. In this research endeavour, the application of cutting-edge deep learning techniques to address ultrasound image challenges was studied. A novel deep learning model comprising some of these techniques is proposed, known as the Hybrid Attention Recurrent Residual U-Net (Hybrid R2AU-Net). It is specifically designed for segmenting spine structures in ultrasound spine images. The outcomes of this study were highly encouraging. The Hybrid R2AU-Net outperformed alternative deep learning models, delivering superior results with an average Dice Score of 85.2%, an average Jaccard Index of 74.3%, and a Detection Rate of 92.4%. These remarkable achievements underscore the potential of the Hybrid R2AU-Net to be seamlessly integrated into an automated scoliosis diagnosis system, promising a more radiation-free and efficient approach to scoliosis management.