Department of Diagnostic Imaging, Graduate School of Medicine, Hokkaido University, N15 W7, Kita-Ku, Sapporo, Hokkaido, 060-8638, Japan.
Department of Diagnostic and Interventional Radiology, Hokkaido University Hospital, N14 W5, Kita-Ku, Sapporo, Hokkaido, 060-8648, Japan.
Jpn J Radiol. 2024 May;42(5):450-459. doi: 10.1007/s11604-023-01527-7. Epub 2024 Jan 27.
To develop a convolutional neural network (CNN) model to diagnose skull-base invasion by nasopharyngeal malignancies in CT images and evaluate the model's diagnostic performance.
We divided 100 malignant nasopharyngeal tumor lesions into a training (n = 70) and a test (n = 30) dataset. Two head/neck radiologists reviewed CT and MRI images and determined the positive/negative skull-base invasion status of each case (training dataset: 29 invasion-positive and 41 invasion-negative; test dataset: 13 invasion-positive and 17 invasion-negative). Preprocessing involved extracting continuous slices of the nasopharynx and clivus. The preprocessed training dataset was used for transfer learning with Residual Neural Networks 50 to create a diagnostic CNN model, which was then tested on the preprocessed test dataset to determine the invasion status and model performance. Original CT images from the test dataset were reviewed by a radiologist with extensive head/neck imaging experience (senior reader: SR) and another less-experienced radiologist (junior reader: JR). Gradient-weighted class activation maps (Grad-CAMs) were created to visualize the explainability of the invasion status classification.
The CNN model's diagnostic accuracy was 0.973, significantly higher than those of the two radiologists (SR: 0.838; JR: 0.595). Receiver operating characteristic curve analysis gave an area under the curve of 0.953 for the CNN model (versus 0.832 and 0.617 for SR and JR; both p < 0.05). The Grad-CAMs suggested that the invasion-negative cases were present predominantly in bone marrow, while the invasion-positive cases exhibited osteosclerosis and nasopharyngeal masses.
This CNN technique would be useful for CT-based diagnosis of skull-base invasion by nasopharyngeal malignancies.
开发一种卷积神经网络（CNN）模型，以在 CT 图像中诊断鼻咽癌的颅底侵犯，并评估该模型的诊断性能。
我们将 100 例恶性鼻咽肿瘤病变分为训练集（n=70）和测试集（n=30）。两位头颈部放射科医生对 CT 和 MRI 图像进行了回顾，并确定了每个病例的颅底侵犯阳性/阴性状态（训练集：29 例侵犯阳性，41 例侵犯阴性；测试集：13 例侵犯阳性，17 例侵犯阴性）。预处理包括提取鼻咽和斜坡的连续切片。使用 Residual Neural Networks 50 对预处理的训练数据集进行迁移学习，以创建诊断 CNN 模型，然后在预处理的测试数据集上对其进行测试，以确定侵犯状态和模型性能。测试数据集的原始 CT 图像由一位具有丰富头颈部成像经验的放射科医生（高级读者：SR）和另一位经验较少的放射科医生（初级读者：JR）进行了回顾。创建了梯度加权类激活图（Grad-CAMs），以可视化侵犯状态分类的可解释性。
CNN 模型的诊断准确性为 0.973，明显高于两位放射科医生（SR：0.838；JR：0.595）。受试者工作特征曲线分析显示，CNN 模型的曲线下面积为 0.953（SR 和 JR 分别为 0.832 和 0.617；均 p<0.05）。Grad-CAMs 表明，侵犯阴性病例主要存在于骨髓中，而侵犯阳性病例则表现为骨质硬化和鼻咽肿块。
该 CNN 技术将有助于基于 CT 对鼻咽癌的颅底侵犯进行诊断。
