Deng Sandong, Huang Yugang, Li Cong, Qian Jun, Wang Xiangdong
Department of Orthopedics, Affiliated Hengyang Hospital, Hunan Normal University (Hengyang Central Hospital), Hengyang, Hunan 421001, China.
Department of Radiology, Qianhai Life Insurance Guangzhou General Hospital, Guangzhou, Guangdong 511300, China.
J Bone Oncol. 2024 Nov 9;49:100648. doi: 10.1016/j.jbo.2024.100648. eCollection 2024 Dec.
Research on auxiliary diagnosis of primary bone tumors can enhance diagnostic accuracy, facilitate early detection, and enable personalized treatment, thereby reducing misdiagnosis and missed cases, ultimately leading to improved patient prognosis and survival rates. In this study, we established a whole slide imaging (WSI) database comprising histopathological samples from all categories of bone tumors and integrated multiple neural network architectures for machine learning models. We then evaluated the accuracy of these models in diagnosing primary bone tumors.
In this paper, the machine learning model based on the deep convolutional neural network (DC-NN) method was combined with imaging omics analysis to analyze and discuss its clinical value in diagnosing primary bone tumors. In addition, this paper proposed a screening method for differentially expressed genes. Based on the paired T-test method, the process first estimated the tumor purity in the experimental data of each sample case, then assessed the actual gene expression value of the experimental data of each sample case, and finally calculated the optimized paired T-test statistics, and screened differentially expressed genes according to the threshold value.
The selected model demonstrated excellent diagnostic accuracy in distinguishing between normal and tumor images, with overall accuracy of (99.8 ± 0.4) % for five rounds of testing using the DCNN model and positive and negative predictive values of (100.0 ± 0.0) % and (99.6 ± 0.8) %, respectively. The mean area under each dataset's curve (AUC) was (0.998 ± 0.004). Further, ten rounds of testing using the DCNN model showed an overall accuracy of (71.2 ± 1.6) % and a substantial positive predictive value of (91.9 ± 8.5) % in distinguishing benign from malignant bone tumors, with an average AUC of (0.62 ± 0.06) across datasets.
The deep learning model accurately classifies bone tumor histopathology based on the degree of infiltration, achieving diagnostic performance comparable to that of senior pathologists. These findings affirm the feasibility and effectiveness of histopathological diagnosis in bone tumors, providing a theoretical foundation for the application and advancement of machine learning-assisted histopathological diagnosis in this field.
原发性骨肿瘤的辅助诊断研究可提高诊断准确性，便于早期发现，并实现个性化治疗，从而减少误诊和漏诊病例，最终改善患者预后和生存率。在本研究中，我们建立了一个包含各类骨肿瘤组织病理学样本的全切片成像（WSI）数据库，并为机器学习模型整合了多种神经网络架构。然后，我们评估了这些模型在诊断原发性骨肿瘤方面的准确性。
本文将基于深度卷积神经网络（DC-NN）方法的机器学习模型与影像组学分析相结合，分析和探讨其在原发性骨肿瘤诊断中的临床价值。此外，本文提出了一种差异表达基因的筛选方法。基于配对T检验方法，该过程首先估计每个样本病例实验数据中的肿瘤纯度，然后评估每个样本病例实验数据的实际基因表达值，最后计算优化后的配对T检验统计量，并根据阈值筛选差异表达基因。
所选模型在区分正常图像和肿瘤图像方面表现出优异的诊断准确性，使用DCNN模型进行五轮测试的总体准确率为（99.8±0.4）%，阳性和阴性预测值分别为（100.0±0.0）%和（99.6±0.8）%。每个数据集曲线下的平均面积（AUC）为（0.998±0.004）。此外，使用DCNN模型进行十轮测试显示，在区分良性和恶性骨肿瘤方面，总体准确率为（71.2±1.6）%，实质性阳性预测值为（91.9±8.5）%，各数据集的平均AUC为（0.62±0.06）。
深度学习模型基于浸润程度对骨肿瘤组织病理学进行准确分类，其诊断性能与资深病理学家相当。这些发现证实了骨肿瘤组织病理学诊断的可行性和有效性，为该领域机器学习辅助组织病理学诊断的应用和发展提供了理论基础。
