College of Information Science and Technology, Taishan University, Taian, P. R. China.
College of Teacher and Education, Taishan University, Taian, P. R. China.
PLoS One. 2023 Feb 28;18(2):e0282107. doi: 10.1371/journal.pone.0282107. eCollection 2023.
Juxtapleural nodules were excluded from the segmented lung region in the Hounsfield unit threshold-based segmentation method. To re-include those regions in the lung region, a new approach was presented using scale-invariant feature transform and gradient vector flow models in this study. First, the scale-invariant feature transform method was utilized to detect all scale-invariant points in the binary lung region. The boundary points in the neighborhood of a scale-invariant point were collected to form the supportive boundary lines. Then, we utilized a Fourier descriptor to obtain a character representation of each supportive boundary line. Spectrum energy recognizes supportive boundaries that must be corrected. Third, the gradient vector flow-snake method was presented to correct the recognized supportive borders with a smooth profile curve, giving an ideal correction edge in those regions. Finally, the performance of the proposed method was evaluated through experiments on multiple authentic computed tomography images. The perfect results and robustness proved that the proposed method could correct the juxtapleural region precisely.
基于体素 Hounsfield 阈值的分割方法中排除了肋胸膜结节所在的肺区。为了重新将这些区域包含在肺区中，本研究提出了一种使用尺度不变特征变换和梯度矢量流模型的新方法。首先，利用尺度不变特征变换方法检测二值化肺区中的所有尺度不变点。收集尺度不变点邻域中的边界点，形成支持边界线。然后，我们利用傅里叶描述子获取每条支持边界线的特征表示。频谱能量识别需要修正的支持边界。第三，提出了梯度矢量流-蛇方法，用平滑的轮廓曲线修正识别出的支持边界，在这些区域给出理想的修正边缘。最后，通过对多幅真实 CT 图像的实验评估了所提出方法的性能。完美的结果和稳健性证明了该方法能够精确地修正肋胸膜区域。
