Liu Caolin, Zou Qingqing, Wang Menghong, Yang Qinmei, Song Liwen, Lu Zixiao, Feng Qianjin, Zhao Yinghua
Department of Radiology, Third Affiliated Hospital of Southern Medical University (Academy of Orthopedics of Guangdong Province), Guangzhou 510630, China.
School of Biomedical Engineering, Southern Medical University (Guangdong Provincial Key Laboratory of Medical Image Processing), Guangzhou 510515, China.
Nan Fang Yi Ke Da Xue Xue Bao. 2024 Dec 20;44(12):2412-2420. doi: 10.12122/j.issn.1673-4254.2024.12.18.
We retrospectively collected CT scan data from 276 patients with pathologically confirmed primary bone tumors from 4 medical centers in Guangdong Province between January, 2010 and August, 2021. A convolutional neural network (CNN) was employed as the deep learning architecture. The optimal baseline deep learning model (R-Net) was determined through transfer learning, and an optimized model (S-Net) was obtained through algorithmic improvements. Multivariate logistic regression analysis was used to screen the clinical features such as sex, age, mineralization location, and pathological fractures, which were then connected with the imaging features to construct the deep learning fusion model (SC-Net). The diagnostic performance of the SC-Net model and machine learning models were compared with radiologists' diagnoses, and their classification performance was evaluated using the area under the receiver operating characteristic curve (AUC) and F1 score.
In the external test set, the fusion model (SC-Net) achieved the best performance with an AUC of 0.901 (95% : 0.803-1.00), an accuracy of 83.7% (95% : 69.3%-93.2%) and an F1 score of 0.857, and outperformed the S-Net model with an AUC of 0.818 (95% : 0.694-0.942), an accuracy of 76.7% (95% : 61.4%-88.2%), and an F1 score of 0.828. The overall classification performance of the fusion model (SC-Net) exceeded that of radiologists' diagnoses.
The deep learning fusion model based on multi-center CT images and clinical features is capable of accurate classification of osseous and chondroid matrix mineralization and may potentially improve the accuracy of clinical diagnoses of osteogenic versus chondrogenic primary bone tumors.
我们回顾性收集了2010年1月至2021年8月期间广东省4家医疗中心276例经病理确诊的原发性骨肿瘤患者的CT扫描数据。采用卷积神经网络（CNN）作为深度学习架构。通过迁移学习确定最佳基线深度学习模型（R-Net），并通过算法改进获得优化模型（S-Net）。使用多变量逻辑回归分析筛选性别、年龄、矿化部位和病理性骨折等临床特征，然后将其与影像特征相结合构建深度学习融合模型（SC-Net）。将SC-Net模型和机器学习模型的诊断性能与放射科医生的诊断结果进行比较，并使用受试者操作特征曲线下面积（AUC）和F1分数评估其分类性能。
在外部测试集中，融合模型（SC-Net）表现最佳，AUC为0.901（95%：0.803 - 1.00），准确率为83.7%（95%：69.3% - 93.2%），F1分数为0.857，优于S-Net模型，其AUC为0.818（95%：0.694 - 0.942），准确率为76.7%（95%：61.4% - 88.2%），F1分数为0.828。融合模型（SC-Net）的总体分类性能超过了放射科医生的诊断结果。
基于多中心CT图像和临床特征的深度学习融合模型能够准确分类骨和软骨样基质矿化，可能会提高原发性骨肿瘤成骨与软骨生成临床诊断的准确性。
