Ryu Susie, Kim Jun Hong, Choi Yoon Jeong, Lee Joon Sang
Division of Obstructive Sleep Apnea Syndrome Diagnosis, School of Mechanical Engineering, College of Engineering, Yonsei University, Seoul, Republic of Korea.
Department of Orthodontics, The Institute of Craniofacial Deformity, Yonsei University College of Dentistry, Seoul, Republic of Korea; Department of Surgery, Division of Plastic and Reconstructive Surgery, Pediatric Craniofacial and Airway Orthodontics and Dental Sleep Medicine, Stanford University School of Medicine, Palo Alto, CA, USA.
Comput Biol Med. 2025 Feb;185:109568. doi: 10.1016/j.compbiomed.2024.109568. Epub 2024 Dec 19.
Computed tomography (CT) of the head and neck is crucial for diagnosing internal structures. The demand for substituting traditional CT with cone beam CT (CBCT) exists because of its cost-effectiveness and reduced radiation exposure. However, CBCT cannot accurately depict airway shapes owing to image noise. This study proposes a strategy utilizing a cycle-consistent generative adversarial network (cycleGAN) for denoising CBCT images with various loss functions and augmentation strategies, resulting in the generation of denoised synthetic CT (sCT) images. Furthermore, through a rule-based approach, we were able to automatically segment the upper airway in sCT images with high accuracy. Additionally, we conducted an analysis of the impact of finely segmented nasal cavities on airflow using computational fluid dynamics (CFD).
We trained the cycleGAN model using various loss functions and compared the quality of the sCT images generated by each model. We improved the artifact removal performance by incorporating CT images with added Gaussian noise augmentation into the training dataset. We developed a rule-based automatic segmentation methodology using threshold and watershed algorithms to compare the accuracy of airway segmentation for noise-reduced sCT and original CBCT. Furthermore, we validated the significance of the nasal cavity by conducting CFD based on automatically segmented shapes obtained from sCT.
The generated sCT images exhibited improved quality, with the mean absolute error decreasing from 161.60 to 100.54, peak signal-to-noise ratio increasing from 22.33 to 28.65, and structural similarity index map increasing from 0.617 to 0.865. Furthermore, by comparing the airway segmentation performances of CBCT and sCT using our proposed automatic rule-based algorithm, the Dice score improved from 0.849 to 0.960. Airway segmentation performance is closely associated with the accuracy of fluid dynamics simulations. Detailed airway segmentation is crucial for altering flow dynamics and contributes significantly to diagnostics.
Our deep learning methodology enhances the image quality of CBCT to provide anatomical information to medical professionals and enables precise and accurate biomechanical analysis. This allows clinicians to obtain precise quantitative metrics and facilitates accurate assessment.
头颈部计算机断层扫描（CT）对于诊断内部结构至关重要。由于其成本效益和较低的辐射暴露，存在用锥形束CT（CBCT）替代传统CT的需求。然而，由于图像噪声，CBCT无法准确描绘气道形状。本研究提出一种利用循环一致生成对抗网络（cycleGAN）的策略，通过各种损失函数和增强策略对CBCT图像进行去噪，从而生成去噪后的合成CT（sCT）图像。此外，通过基于规则的方法，我们能够在sCT图像中高精度地自动分割上气道。另外，我们使用计算流体动力学（CFD）分析了精细分割的鼻腔对气流的影响。
我们使用各种损失函数训练cycleGAN模型，并比较每个模型生成的sCT图像的质量。我们通过将添加高斯噪声增强的CT图像纳入训练数据集来提高伪影去除性能。我们开发了一种基于规则的自动分割方法，使用阈值和分水岭算法来比较降噪后的sCT和原始CBCT的气道分割准确性。此外，我们基于从sCT获得的自动分割形状进行CFD，以验证鼻腔的重要性。
生成的sCT图像质量得到改善，平均绝对误差从161.60降至100.54，峰值信噪比从22.33增至28.65，结构相似性指数图从0.617增至0.865。此外，通过使用我们提出的基于规则的自动算法比较CBCT和sCT的气道分割性能，骰子系数从0.849提高到0.960。气道分割性能与流体动力学模拟的准确性密切相关。详细的气道分割对于改变流动动力学至关重要，并且对诊断有显著贡献。
我们的深度学习方法提高了CBCT的图像质量，为医学专业人员提供解剖学信息，并实现精确准确的生物力学分析。这使临床医生能够获得精确的定量指标，并有助于准确评估。
