Automatic Spine Ultrasound Segmentation for Scoliosis Visualization and Measurement.
Automatic Spine Ultrasound Segmentation for Scoliosis Visualization and Measurement.
复制标题
DOI：
10.1109/tbme.2020.2980540
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
Fichtinger G
中科院分区：
文献类型：
--
作者：
Ungi T;Greer H;Sunderland KR;Wu V;Baum ZMC;Schlenger C;Oetgen M;Cleary K;Aylward SR;Fichtinger G
集成跟踪超声和AI方法，为脊柱侧凸测量提供更安全、更容易获得的X射线替代方案。我们提出了自动超声分割三维脊柱可视化和脊柱侧凸测量，以解决使用超声脊柱成像的困难。我们使用来自8名健康成年志愿者的数据训练了一个卷积神经网络，用于超声扫描的脊柱分割。我们在8名儿科患者身上测试了经过训练的网络。我们评估了图像分割和三维体积重建用于脊柱侧凸测量的效果。正如预期的那样，当经过训练的网络从健康志愿者转换为患者时，模糊分割指标减少了。回忆率从0.72下降到0.64（下降8.2%），精确率从0.31下降到0.27（下降3.7%）。然而，在找到预测图的最佳阈值后，二进制分割指标在患者数据上表现得更好。回忆率从0.98下降到0.97（下降1.6%），精确率从0.10下降到0.06（下降4.5%）。分割预测图被重建为三维体积，并测量所有患者的脊柱侧凸。这些重建中的测量花费不到1分钟，与X射线相比，最大误差为2.2°。自动脊柱分割使得脊柱侧凸测量在跟踪超声扫描中既有效又准确。自动分割可以克服跟踪超声的局限性，到目前为止，这种局限性阻碍了它在脊柱侧凸测量中作为X射线的替代品。
Integrate tracked ultrasound and AI methods to provide a safer and more accessible alternative to X-ray for scoliosis measurement. We propose automatic ultrasound segmentation for 3-dimensional spine visualization and scoliosis measurement to address difficulties in using ultrasound for spine imaging. We trained a convolutional neural network for spine segmentation on ultrasound scans using data from eight healthy adult volunteers. We tested the trained network on eight pediatric patients. We evaluated image segmentation and 3-dimensional volume reconstruction for scoliosis measurement. As expected, fuzzy segmentation metrics reduced when trained networks were translated from healthy volunteers to patients. Recall decreased from 0.72 to 0.64 (8.2% decrease), and precision from 0.31 to 0.27 (3.7% decrease). However, after finding optimal thresholds for prediction maps, binary segmentation metrics performed better on patient data. Recall decreased from 0.98 to 0.97 (1.6% decrease), and precision from 0.10 to 0.06 (4.5% decrease). Segmentation prediction maps were reconstructed to 3-dimensional volumes and scoliosis was measured in all patients. Measurement in these reconstructions took less than 1 minute and had a maximum error of 2.2° compared to X-ray. automatic spine segmentation makes scoliosis measurement both efficient and accurate in tracked ultrasound scans. Automatic segmentation may overcome the limitations of tracked ultrasound that so far prevented its use as an alternative of X-ray in scoliosis measurement.