Objective Vertebral segmentation in computed tomography(CT)images remains an essential issue in medical image analysis,stemming from the variability in vertebral shapes,high complex deformations,and the inherent ambig...Objective Vertebral segmentation in computed tomography(CT)images remains an essential issue in medical image analysis,stemming from the variability in vertebral shapes,high complex deformations,and the inherent ambiguity in CT scans.The purpose of this study was to develop advanced methods to effectively address this challenging task.Methods We proposed an attention-driven asymmetric convolution deep learning(AACDL)framework for verte-bral segmentation.Specifically,our approach involved constructing a novel asymmetric convolutional U-shaped deep learning architecture to enhance the feature extraction capabilities by increasing its depth for capturing richer spatial details.Further,we constructed a pyramid global context module that integrates global context information through pyramid pooling to boost segmentation accuracy particularly in smaller anatomical regions.Sequential channel and spatial attention mechanisms were also implemented within the network to enable it to automatically concentrate on learning the most salient features and regions across different dimensions.Results The performance precision of our network was rigorously assessed using a suite of four benchmark metrics:the dice coefficient,mean intersection over union(mIoU),precision rate,and F1-score.When compared against the ground truth,our model delivered outstanding scores,attaining a dice coefficient of 82.79%,an mIoU of 90.72%,a precision rate of 90.19%,and an F1-score of 90.09%,each reflecting the commendable accuracy and reliability of our network’s segmentation output.Conclusion The proposed AACDL method might successfully realize accurate segmentation of vertebral CT images,thereby demonstrating significant potential for clinical applications with its robust performance metrics.Its ability to handle the complexities associated with vertebral segmentation may pave the way for enhanced diagnostic and treatment planning processes in healthcare settings.展开更多
Congenital pure kyphosis due to failure of vertebral body segmentation is a relatively rare entity, and surgical intervention is infrequent compared to that for failure of vertebral body formation [1] [2]. There are v...Congenital pure kyphosis due to failure of vertebral body segmentation is a relatively rare entity, and surgical intervention is infrequent compared to that for failure of vertebral body formation [1] [2]. There are very few reports of long-term follow-up of surgical treatment in patients with congenital pure kyphosis, and all the reported cases were diagnosed as failure of formation and had an age at the time of surgery of less than 18 years. It is important for orthopedic surgeons to follow the postoperative course of rare cases over 30 years. Here, we present a surgically treated case with ultra-long term follow-up of a 50-year-old patient with congenital pure kyphosis of the lumbar spine. Imaging of the lumbar spine showed six vertebrae and an unsegmented bar at L3-4 causing a pure kyphosis of 54°. The wedge-shaped block vertebra had 4 pedicles with the neural foramen between the pedicles without concomitant disc space, with compensatory thoracic hypokyphosis and lower lumbar hyperlordosis. One-stage correction and fusion surgery using anterior opening and posterior closing osteotomy was successfully performed. Both clinical and radiographic results were excellent and have been maintained for over 30 years postoperatively. The basic principle in the surgical treatment of adult spinal deformity is to achieve and maintain a good global sagittal balance over time. This case reaffirms the importance of spinopelvic harmony.展开更多
基金supported by the Special Project of Doctoral Research Innovation Team of Guangdong Polytechnic of Science and Technology(Grant No.XJBS202301).
文摘Objective Vertebral segmentation in computed tomography(CT)images remains an essential issue in medical image analysis,stemming from the variability in vertebral shapes,high complex deformations,and the inherent ambiguity in CT scans.The purpose of this study was to develop advanced methods to effectively address this challenging task.Methods We proposed an attention-driven asymmetric convolution deep learning(AACDL)framework for verte-bral segmentation.Specifically,our approach involved constructing a novel asymmetric convolutional U-shaped deep learning architecture to enhance the feature extraction capabilities by increasing its depth for capturing richer spatial details.Further,we constructed a pyramid global context module that integrates global context information through pyramid pooling to boost segmentation accuracy particularly in smaller anatomical regions.Sequential channel and spatial attention mechanisms were also implemented within the network to enable it to automatically concentrate on learning the most salient features and regions across different dimensions.Results The performance precision of our network was rigorously assessed using a suite of four benchmark metrics:the dice coefficient,mean intersection over union(mIoU),precision rate,and F1-score.When compared against the ground truth,our model delivered outstanding scores,attaining a dice coefficient of 82.79%,an mIoU of 90.72%,a precision rate of 90.19%,and an F1-score of 90.09%,each reflecting the commendable accuracy and reliability of our network’s segmentation output.Conclusion The proposed AACDL method might successfully realize accurate segmentation of vertebral CT images,thereby demonstrating significant potential for clinical applications with its robust performance metrics.Its ability to handle the complexities associated with vertebral segmentation may pave the way for enhanced diagnostic and treatment planning processes in healthcare settings.
文摘Congenital pure kyphosis due to failure of vertebral body segmentation is a relatively rare entity, and surgical intervention is infrequent compared to that for failure of vertebral body formation [1] [2]. There are very few reports of long-term follow-up of surgical treatment in patients with congenital pure kyphosis, and all the reported cases were diagnosed as failure of formation and had an age at the time of surgery of less than 18 years. It is important for orthopedic surgeons to follow the postoperative course of rare cases over 30 years. Here, we present a surgically treated case with ultra-long term follow-up of a 50-year-old patient with congenital pure kyphosis of the lumbar spine. Imaging of the lumbar spine showed six vertebrae and an unsegmented bar at L3-4 causing a pure kyphosis of 54°. The wedge-shaped block vertebra had 4 pedicles with the neural foramen between the pedicles without concomitant disc space, with compensatory thoracic hypokyphosis and lower lumbar hyperlordosis. One-stage correction and fusion surgery using anterior opening and posterior closing osteotomy was successfully performed. Both clinical and radiographic results were excellent and have been maintained for over 30 years postoperatively. The basic principle in the surgical treatment of adult spinal deformity is to achieve and maintain a good global sagittal balance over time. This case reaffirms the importance of spinopelvic harmony.
