Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou.
Department of Radiology, Huashan Hospital Affiliated to Fudan University.
J Comput Assist Tomogr. 2024;48(3):480-490. doi: 10.1097/RCT.0000000000001565. Epub 2023 Nov 27.
This study aimed to investigate the effectiveness and practicality of using models like convolutional neural network and transformer in detecting and precise segmenting meningioma from magnetic resonance images.
The retrospective study on T1-weighted and contrast-enhanced images of 523 meningioma patients from 3 centers between 2010 and 2020. A total of 373 cases split 8:2 for training and validation. Three independent test sets were built based on the remaining 150 cases. Six convolutional neural network detection models trained via transfer learning were evaluated using 4 metrics and receiver operating characteristic analysis. Detected images were used for segmentation. Three segmentation models were trained for meningioma segmentation and were evaluated via 4 metrics. In 3 test sets, intraclass consistency values were used to evaluate the consistency of detection and segmentation models with manually annotated results from 3 different levels of radiologists.
The average accuracies of the detection model in the 3 test sets were 97.3%, 93.5%, and 96.0%, respectively. The model of segmentation showed mean Dice similarity coefficient values of 0.884, 0.834, and 0.892, respectively. Intraclass consistency values showed that the results of detection and segmentation models were highly consistent with those of intermediate and senior radiologists and lowly consistent with those of junior radiologists.
The proposed deep learning system exhibits advanced performance comparable with intermediate and senior radiologists in meningioma detection and segmentation. This system could potentially significantly improve the efficiency of the detection and segmentation of meningiomas.
本研究旨在探讨卷积神经网络和转换器等模型在检测和精确分割磁共振图像中的脑膜瘤方面的有效性和实用性。
回顾性研究了 2010 年至 2020 年间来自 3 个中心的 523 例脑膜瘤患者的 T1 加权和增强图像。总共将 373 例病例分为 8:2 进行训练和验证。基于其余 150 例病例构建了三个独立的测试集。使用 4 项指标和受试者工作特征分析评估了通过迁移学习训练的六个卷积神经网络检测模型。使用检测图像进行分割。针对脑膜瘤分割训练了三个分割模型，并通过 4 项指标进行评估。在三个测试集中，使用组内一致性值评估了检测和分割模型与来自 3 个不同级别放射科医生的手动标注结果的一致性。
三个测试集中检测模型的平均准确率分别为 97.3%、93.5%和 96.0%。分割模型的平均 Dice 相似系数值分别为 0.884、0.834 和 0.892。组内一致性值表明，检测和分割模型的结果与中级和高级放射科医生的结果高度一致，与初级放射科医生的结果低度一致。
所提出的深度学习系统在脑膜瘤检测和分割方面表现出与中级和高级放射科医生相当的先进性能。该系统有可能显著提高脑膜瘤检测和分割的效率。
