CSIRO Mathematical and Infonnrmation Sciences, New South Wales 1670, Australia.
Med Phys. 2010 Jan;37(1):63-73. doi: 10.1118/1.3264662.
A system is presented for automated estimation of progression of interstitial lung disease in serial thoracic CT scans.
The system compares corresponding 2D axial sections from baseline and follow-up scans and concludes whether this pair of sections represents regression, progression, or unchanged disease status. The correspondence between serial CT scans is achieved by intrapatient volumetric image registration. The system classification function is trained with two different feature sets. Features in the first set represent the intensity distribution of a difference image between the baseline and follow-up CT sections. Features in the second set represent dissimilarities computed between the baseline and follow-up images filtered with a bank of general purpose texture filters.
In an experiment on 74 scan pairs, the system classification accuracies were 76.1% and 79.5% for the two feature sets, respectively, while the accuracies of two observer radiologist were 78.5% and 82%, respectively. The agreements of the system with the reference standard, measured by weighted kappa statistics, were 0.611 and 0.683 for the two feature sets, respectively.
The system employing the second feature set showed good agreement with the reference standard, and its accuracy approached that of two radiologists.
提出了一种用于在连续胸部 CT 扫描中自动评估间质性肺病进展的系统。
该系统比较基线和随访扫描的相应 2D 轴向截面，并得出这一对截面表示疾病状态是消退、进展还是不变。连续 CT 扫描之间的对应关系通过患者内容积图像配准来实现。系统分类功能使用两个不同的特征集进行训练。第一个特征集中的特征表示基线和随访 CT 切片之间的差异图像的强度分布。第二个特征集中的特征表示使用一组通用纹理滤波器对基线和随访图像进行滤波后的差异。
在 74 对扫描的实验中，两个特征集的系统分类准确率分别为 76.1%和 79.5%，而两位观察者放射科医生的准确率分别为 78.5%和 82%。使用加权kappa 统计量衡量系统与参考标准的一致性，两个特征集的一致性分别为 0.611 和 0.683。
使用第二个特征集的系统与参考标准具有良好的一致性，其准确率接近两位放射科医生。
