Department of General Medicine, "Carol Davila" University of Medicine and Pharmacy, 050474 Bucharest, Romania.
Orthopaedics and Trauma Surgery Department, "St. Pantelimon" Hospital, 021659 Bucharest, Romania.
Medicina (Kaunas). 2022 May 4;58(5):636. doi: 10.3390/medicina58050636.
: Malignant bone tumors represent a major problem due to their aggressiveness and low survival rate. One of the determining factors for improving vital and functional prognosis is the shortening of the time between the onset of symptoms and the moment when treatment starts. The objective of the study is to predict the malignancy of a bone tumor from magnetic resonance imaging (MRI) using deep learning algorithms. : The cohort contained 23 patients in the study (14 women and 9 men with ages between 15 and 80). Two pretrained ResNet50 image classifiers are used to classify T1 and T2 weighted MRI scans. To predict the malignancy of a tumor, a clinical model is used. The model is a feed forward neural network whose inputs are patient clinical data and the output values of T1 and T2 classifiers. : For the training step, the accuracies of 93.67% for the T1 classifier and 86.67% for the T2 classifier were obtained. In validation, both classifiers obtained 95.00% accuracy. The clinical model had an accuracy of 80.84% for training phase and 80.56% for validation. The receiver operating characteristic curve (ROC) of the clinical model shows that the algorithm can perform class separation. : The proposed method is based on pretrained deep learning classifiers which do not require a manual segmentation of the MRI images. These algorithms can be used to predict the malignancy of a tumor and on the other hand can shorten the time of their diagnosis and treatment process. While the proposed method requires minimal intervention from an imagist, it needs to be tested on a larger cohort of patients.
: 恶性骨肿瘤因其侵袭性和低存活率而成为一个主要问题。改善生存和功能预后的一个决定性因素是缩短症状出现和开始治疗之间的时间。本研究的目的是使用深度学习算法从磁共振成像（MRI）预测骨肿瘤的恶性程度。 : 该队列包含 23 名研究患者（14 名女性和 9 名男性，年龄在 15 岁至 80 岁之间）。使用两个预先训练的 ResNet50 图像分类器对 T1 和 T2 加权 MRI 扫描进行分类。为了预测肿瘤的恶性程度，使用了一个临床模型。该模型是一个前馈神经网络，其输入是患者的临床数据和 T1 和 T2 分类器的输出值。 : 在训练步骤中，T1 分类器的准确率为 93.67%，T2 分类器的准确率为 86.67%。在验证中，两个分类器的准确率均为 95.00%。临床模型的训练阶段准确率为 80.84%，验证阶段准确率为 80.56%。临床模型的接收者操作特征曲线（ROC）表明，该算法可以进行分类。 : 所提出的方法基于预先训练的深度学习分类器，不需要对 MRI 图像进行手动分割。这些算法可用于预测肿瘤的恶性程度，另一方面可以缩短其诊断和治疗过程的时间。虽然该方法需要影像科医生的最小干预，但需要在更大的患者队列中进行测试。
