School of Healthcare Sciences, Manchester Metropolitan University, Manchester, United Kingdom.
Crime and Well-Being Big Data Centre, Manchester Metropolitan University, Manchester, United Kingdom; Elements Technology Platforms Ltd., Cheshire, United Kingdom.
Ultrasound Med Biol. 2019 May;45(5):1164-1175. doi: 10.1016/j.ultrasmedbio.2019.01.018. Epub 2019 Mar 8.
Diagnosis of motor neurone disease (MND) includes detection of small, involuntary muscle excitations, termed fasciculations. There is need to improve diagnosis and monitoring of MND through provision of objective markers of change. Fasciculations are visible in ultrasound image sequences. However, few approaches that objectively measure their occurrence have been proposed; their performance has been evaluated in only a few muscles; and their agreement with the clinical gold standard for fasciculation detection, intramuscular electromyography, has not been tested. We present a new application of adaptive foreground detection using a Gaussian mixture model (GMM), evaluating its accuracy across five skeletal muscles in healthy and MND-affected participants. The GMM provided good to excellent accuracy with the electromyography ground truth (80.17%-92.01%) and was robust to different ultrasound probe orientations. The GMM provides objective measurement of fasciculations in each of the body segments necessary for MND diagnosis and hence could provide a new, clinically relevant disease marker.
运动神经元病（MND）的诊断包括检测小的、无意识的肌肉兴奋，称为肌束震颤。需要通过提供变化的客观标志物来改善 MND 的诊断和监测。肌束震颤在超声图像序列中可见。然而，已经提出了几种客观测量它们发生的方法；它们的性能仅在少数几块肌肉中进行了评估；并且它们与肌束震颤检测的临床金标准——肌内电图的一致性尚未得到测试。我们提出了一种使用高斯混合模型（GMM）进行自适应前景检测的新应用，评估了其在健康和 MND 受影响参与者的五个骨骼肌中的准确性。GMM 与肌电图的真实情况具有良好到优秀的准确性（80.17%-92.01%），并且对不同的超声探头方向具有鲁棒性。GMM 为 MND 诊断所需的每个身体部位的肌束震颤提供了客观测量，因此可以提供新的、与临床相关的疾病标志物。
