Spine image analysis is based on the accurate segmentation and vertebrae recognition of the spine. Several deep learning models have been proposed for spine segmentation and vertebrae recognition, but they are very computationally demanding. In this research, a novel deep learning model is introduced for spine segmentation and vertebrae recognition using CT images. The proposed model works in two steps: (1) A cascaded hierarchical atrous spatial pyramid pooling residual attention U-Net (CHASPPRAU-Net), which is a modified version of U-Net, is used for the segmentation of the spine. Cascaded spatial pyramid pooling layers, along with residual blocks, are used for feature extraction, while the attention module is used for focusing on regions of interest. (2) A 3D mobile residual U-Net (MRU-Net) is used for vertebrae recognition. MobileNetv2 includes residual and attention modules to accurately extract features from the axial, sagittal, and coronal views of 3D spine images. The features from these three views are concatenated to form a 3D feature map. After that, a 3D deep learning model is used for vertebrae recognition. The VerSe 20 and VerSe 19 datasets were used to validate the proposed model. The model achieved more accurate results in spine segmentation and vertebrae recognition than the state-of-the-art methods.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10453471PMC
http://dx.doi.org/10.3390/diagnostics13162658DOI Listing

Publication Analysis

Top Keywords

vertebrae recognition
28
segmentation vertebrae
20
deep learning
16
spine segmentation
16
spine
8
learning model
8
proposed model
8
spatial pyramid
8
pyramid pooling
8
residual attention
8

Similar Publications

A 41-year-old man with a history of obesity, hypertension, and smoking suffered from numbness and weakness in both lower limbs. He was diagnosed with ossification of the posterior longitudinal ligament and ligamentum flavum in the cervical and thoracic spine by X-rays, CT, and MRI. The patient underwent laminectomies at T2 and T3 levels, along with posterior fusion from T1 to T4, to address an upper thoracic spine lesion causing sensory deficits up to T5 and gait disturbances.

View Article and Find Full Text PDF

Objectives: Three-dimensional (3D) ultrasound imaging can overcome the limitations of conventional two-dimensional (2D) ultrasound imaging in structural observation and measurement. However, conducting volumetric ultrasound imaging for large-sized organs still faces difficulties including long acquisition time, inevitable patient movement, and 3D feature recognition. In this study, we proposed a real-time volumetric free-hand ultrasound imaging system optimized for the above issues and applied it to the clinical diagnosis of scoliosis.

View Article and Find Full Text PDF
Article Synopsis
  • Spondylo-thoracic dysplasia (STD) is a rare congenital condition that affects the vertebrae and thoracic area, often leading to serious respiratory issues and a high risk of early death in neonates.
  • The text details the case of a one-day-old male newborn with severe respiratory distress and various physical anomalies, including scoliosis and rib deformities, identified through clinical examinations and imaging studies.
  • The baby was diagnosed with STD, received conservative management, and survived past the neonatal period, offering insights into this particular variant of the condition.
View Article and Find Full Text PDF

Background: Aneurysmal subarachnoid hemorrhage (aSAH) is often associated with acute high-pressure hydrocephalus. Less commonly, an acute low-pressure hydrocephalus (ALPH) variant can develop and contribute to increased morbidity. ALPH is particularly challenging to diagnose and manage, as patients present with symptoms of increased intracranial pressure (ICP) despite the absence of corroborating evidence from ICP measurements.

View Article and Find Full Text PDF

AQP3-liposome@GelMA promotes overloaded-induced degenerated disc regeneration via IBSP/ITG αVβ3/AKT pathway.

Int J Biol Macromol

December 2024

Department of Orthopedics, The Third Affiliated Hospital of Chongqing Medical University, Chongqing 401120, China; Tissue Repairing and Biotechnology Research Center, The Third Affiliated Hospital of Chongqing Medical University, Chongqing 401120, China. Electronic address:

Article Synopsis
  • Medical treatments for intervertebral disc degeneration (IDD) focus mainly on symptom relief, while effective regeneration therapies are still needed.
  • Recent findings show a negative correlation between AQP3 levels and disc degeneration, indicating its importance in maintaining disc health.
  • The study introduces a novel liposome-encapsulated AQP3 in GelMA (AQP3-lipo@GelMA) that improves cell recognition and enhances the repair of degenerated discs, showing promise for clinical use.
View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!