Department of Radiology, Qingdao Municipal Hospital, Qingdao University, Qingdao, China.
University College London, London, UK.
Biomed Res Int. 2022 Jun 17;2022:7512445. doi: 10.1155/2022/7512445. eCollection 2022.
Idiopathic scoliosis accounts for over 80% of all cases of scoliosis but has an unclear pathogenic mechanism. Many studies have introduced conventional image processing methods, but the results often fail to meet expectations. With the improvement and evolution of research in neural networks in the field of deep learning, many research efforts related to spinal reconstruction using the convolutional neural network (CNN) architecture of deep learning have shown promise.
To investigate the use of CNN for spine modeling.
The primary technique used in this study involves Mask Region-based CNN (R-CNN) image segmentation and object detection methods as applied to spine model positioning of radiographs. The methods were evaluated based on common evaluation criteria for vertebral segmentation and object detection. Evaluations were performed using the loss function, mask loss function, classification loss function, target box loss function, average accuracy, and average recall.
Many bony structures were directly identified in one step, including the lumbar spine (L1-L5) and thoracic spine (T1-T12) in frontal and lateral radiographs, thereby achieving initial positioning of the statistical spine model to provide spine model positioning for future reconstruction and classification prediction. An average detection box accuracy of 97.4% and an average segmentation accuracy of 96.8% were achieved for the prediction efficacy of frontal images, with good image visualization. Moreover, the results for lateral images were satisfactory considering the evaluation parameters and image visualization.
Mask R-CNN can be used for effective positioning in spine model studies for future reconstruction and classification prediction.
特发性脊柱侧凸占所有脊柱侧凸病例的 80%以上，但发病机制尚不清楚。许多研究已经引入了常规图像处理方法，但结果往往不尽如人意。随着深度学习领域神经网络研究的改进和发展，许多使用深度学习卷积神经网络（CNN）结构进行脊柱重建的相关研究都显示出了前景。
研究使用 CNN 进行脊柱建模。
本研究主要采用基于掩模的卷积神经网络（R-CNN）图像分割和对象检测方法，应用于 X 光片的脊柱模型定位。该方法基于椎体分割和对象检测的常用评估标准进行评估。使用损失函数、掩模损失函数、分类损失函数、目标框损失函数、平均准确率和平均召回率进行评估。
许多骨结构可以直接一步识别，包括前后位 X 光片中的腰椎（L1-L5）和胸椎（T1-T12），从而实现统计脊柱模型的初步定位，为未来的重建和分类预测提供脊柱模型定位。正面图像的预测效能达到平均检测框准确率 97.4%和平均分割准确率 96.8%，图像可视化效果良好。此外，考虑到评估参数和图像可视化效果，侧位图像的结果也令人满意。
Mask R-CNN 可用于脊柱模型研究中的有效定位，以进行未来的重建和分类预测。
