School of Biomedical Engineering, Western University, London, ON, Canada.
Digital Imaging Group of London, London, ON, Canada.
Med Image Anal. 2021 Jan;67:101861. doi: 10.1016/j.media.2020.101861. Epub 2020 Oct 10.
Accurate vertebral body (VB) detection and segmentation are critical for spine disease identification and diagnosis. Existing automatic VB detection and segmentation methods may cause false-positive results to the background tissue or inaccurate results to the desirable VB. Because they usually cannot take both the global spine pattern and the local VB appearance into consideration concurrently. In this paper, we propose a Sequential Conditional Reinforcement Learning network (SCRL) to tackle the simultaneous detection and segmentation of VBs from MR spine images. The SCRL, for the first time, applies deep reinforcement learning into VB detection and segmentation. It innovatively models the spatial correlation between VBs from top to bottom as sequential dynamic-interaction processes, thereby globally focusing detection and segmentation on each VB. Simultaneously, SCRL also perceives the local appearance feature of each desirable VB comprehensively, thereby achieving accurate detection and segmentation result. Particularly, SCRL seamlessly combines three parts: 1) Anatomy-Modeling Reinforcement Learning Network dynamically interacts with the image and focuses an attention-region on the VB; 2) Fully-Connected Residual Neural Network learns rich global context information of the VB including both the detailed low-level features and the abstracted high-level features to detect the accurate bounding-box of the VB based on the attention-region; 3) Y-shaped Network learns comprehensive detailed texture information of VB including multi-scale, coarse-to-fine features to segment the boundary of VB from the attention-region. On 240 subjects, SCRL achieves accurate detection and segmentation results, where on average the detection IoU is 92.3%, segmentation Dice is 92.6%, and classification mean accuracy is 96.4%. These excellent results demonstrate that SCRL can be an efficient aided-diagnostic tool to assist clinicians when diagnosing spinal diseases.
准确的椎体（VB）检测和分割对于脊柱疾病的识别和诊断至关重要。现有的自动 VB 检测和分割方法可能会导致背景组织出现假阳性结果，或者对期望的 VB 产生不准确的结果。因为它们通常不能同时考虑全局脊柱模式和局部 VB 外观。在本文中，我们提出了一种顺序条件强化学习网络（SCRL）来解决从 MR 脊柱图像中同时检测和分割 VB 的问题。SCRL 首次将深度学习强化学习应用于 VB 检测和分割。它创新性地将 VB 之间的空间相关性建模为从上到下的顺序动态交互过程，从而全局地将检测和分割集中在每个 VB 上。同时，SCRL 还全面感知每个期望 VB 的局部外观特征，从而实现准确的检测和分割结果。特别是，SCRL 无缝地结合了三个部分：1）解剖建模强化学习网络与图像动态交互，并将注意力区域集中在 VB 上；2）全连接残差神经网络学习 VB 的丰富全局上下文信息，包括详细的低级特征和抽象的高级特征，基于注意力区域检测 VB 的准确边界框；3）Y 形网络学习 VB 的全面详细纹理信息，包括多尺度、粗到细的特征，从注意力区域分割 VB 的边界。在 240 个受试者中，SCRL 实现了准确的检测和分割结果，平均检测 IoU 为 92.3%，分割 Dice 为 92.6%，分类平均准确率为 96.4%。这些优异的结果表明，SCRL 可以成为一种有效的辅助诊断工具，帮助临床医生诊断脊柱疾病。
