Department of Artificial Intelligence, Chung-Ang University, Seoul, Korea.
AI/ML Research Innovation Center, Chung-Ang University, Seoul, Korea.
Sci Rep. 2023 Aug 10;13(1):13018. doi: 10.1038/s41598-023-40331-1.
This study aimed to propose a neural network (NN)-based method to evaluate thyroid-associated orbitopathy (TAO) patient activity using orbital computed tomography (CT). Orbital CT scans were obtained from 144 active and 288 inactive TAO patients. These CT scans were preprocessed by selecting eleven slices from axial, coronal, and sagittal planes and segmenting the region of interest. We devised an NN employing information extracted from 13 pipelines to assess these slices and clinical patient age and sex data for TAO activity evaluation. The proposed NN's performance in evaluating active and inactive TAO patients achieved a 0.871 area under the receiver operating curve (AUROC), 0.786 sensitivity, and 0.779 specificity values. In contrast, the comparison models CSPDenseNet and ConvNeXt were significantly inferior to the proposed model, with 0.819 (p = 0.029) and 0.774 (p = 0.04) AUROC values, respectively. Ablation studies based on the Sequential Forward Selection algorithm identified vital information for optimal performance and evidenced that NNs performed best with three to five active pipelines. This study establishes a promising TAO activity diagnosing tool with further validation.
本研究旨在提出一种基于神经网络（NN）的方法，利用眼眶计算机断层扫描（CT）评估甲状腺相关眼病（TAO）患者的活动度。共纳入 144 例活动期和 288 例非活动期 TAO 患者的眼眶 CT 扫描。对这些 CT 扫描进行预处理，在轴向、冠状和矢状位选择 11 个层面，并对感兴趣区域进行分割。我们设计了一个 NN，利用从 13 个管道提取的信息来评估这些层面以及临床患者年龄和性别数据，以评估 TAO 的活动度。所提出的 NN 在评估活动期和非活动期 TAO 患者的表现方面，获得了 0.871 的接收器操作曲线（AUROC）下面积、0.786 的敏感性和 0.779 的特异性。相比之下，对比模型 CSPDenseNet 和 ConvNeXt 明显逊于所提出的模型，AUROC 值分别为 0.819（p=0.029）和 0.774（p=0.04）。基于序列前向选择算法的消融研究确定了最优性能的重要信息，并证明神经网络在使用三到五个活动管道时表现最佳。这项研究建立了一个有前途的 TAO 活动诊断工具，需要进一步验证。
