Department of Biostatistics and Informatics, Colorado School of Public Health, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA; Department of Pediatric Plastic and Reconstructive Surgery, Children's Hospital Colorado, University of Colorado Anschutz Medical Campus, 13123 E 16th Ave, Aurora, CO 80045, USA.
Department of Biostatistics and Informatics, Colorado School of Public Health, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA.
Comput Methods Programs Biomed. 2023 Oct;240:107689. doi: 10.1016/j.cmpb.2023.107689. Epub 2023 Jun 25.
Accurate and repeatable detection of craniofacial landmarks is crucial for automated quantitative evaluation of head development anomalies. Since traditional imaging modalities are discouraged in pediatric patients, 3D photogrammetry has emerged as a popular and safe imaging alternative to evaluate craniofacial anomalies. However, traditional image analysis methods are not designed to operate on unstructured image data representations such as 3D photogrammetry.
We present a fully automated pipeline to identify craniofacial landmarks in real time, and we use it to assess the head shape of patients with craniosynostosis using 3D photogrammetry. To detect craniofacial landmarks, we propose a novel geometric convolutional neural network based on Chebyshev polynomials to exploit the point connectivity information in 3D photogrammetry and quantify multi-resolution spatial features. We propose a landmark-specific trainable scheme that aggregates the multi-resolution geometric and texture features quantified at every vertex of a 3D photogram. Then, we embed a new probabilistic distance regressor module that leverages the integrated features at every point to predict landmark locations without assuming correspondences with specific vertices in the original 3D photogram. Finally, we use the detected landmarks to segment the calvaria from the 3D photograms of children with craniosynostosis, and we derive a new statistical index of head shape anomaly to quantify head shape improvements after surgical treatment.
We achieved an average error of 2.74 ± 2.70 mm identifying Bookstein Type I craniofacial landmarks, which is a significant improvement compared to other state-of-the-art methods. Our experiments also demonstrated a high robustness to spatial resolution variability in the 3D photograms. Finally, our head shape anomaly index quantified a significant reduction of head shape anomalies as a consequence of surgical treatment.
Our fully automated framework provides real-time craniofacial landmark detection from 3D photogrammetry with state-of-the-art accuracy. In addition, our new head shape anomaly index can quantify significant head phenotype changes and can be used to quantitatively evaluate surgical treatment in patients with craniosynostosis.
准确且可重复地检测颅面标志对于自动定量评估头发育异常至关重要。由于传统的成像方式不适合儿科患者，因此 3D 摄影测量技术已成为一种流行且安全的替代成像方法，可用于评估颅面异常。然而，传统的图像分析方法并不是为处理 3D 摄影测量等非结构化图像数据表示而设计的。
我们提出了一个完全自动化的流水线，可实时识别颅面标志，并使用该流水线通过 3D 摄影测量技术评估颅缝早闭患者的头型。为了检测颅面标志，我们提出了一种基于切比雪夫多项式的新型几何卷积神经网络，以利用 3D 摄影测量中的点连接信息并量化多分辨率空间特征。我们提出了一种特定于标志的可训练方案，该方案汇总了在 3D 摄影测量中每个顶点量化的多分辨率几何和纹理特征。然后，我们嵌入了一个新的概率距离回归器模块，该模块利用每个点的集成特征来预测标志位置，而无需假设与原始 3D 摄影测量中的特定顶点对应。最后，我们使用检测到的标志从患有颅缝早闭的儿童的 3D 摄影测量中分割颅骨，并得出一个新的头型异常统计指数，以量化手术后头型的改善情况。
我们实现了平均误差为 2.74±2.70mm 的 Bookstein Type I 颅面标志识别，与其他最先进的方法相比有显著提高。我们的实验还证明了该方法对 3D 摄影测量中空间分辨率变化具有很高的鲁棒性。最后，我们的头型异常指数量化了手术治疗后头型异常的显著减少。
我们的全自动框架提供了具有最先进精度的实时 3D 摄影测量颅面标志检测。此外，我们的新头型异常指数可以量化显著的头型表型变化，并可用于定量评估颅缝早闭患者的手术治疗效果。
