准确分类原发性骨肿瘤对于指导治疗决策至关重要。美国国家综合癌症网络指南推荐多模态图像，为原发性骨肿瘤的综合评估提供不同视角。然而，在临床实践中，大多数患者的医学多模态图像往往是不完整的。本研究旨在利用患者来自 X 射线、CT 和 MRI 的不完整多模态图像以及临床特征来构建深度学习模型，将原发性骨肿瘤分类为良性、中间性或恶性。在这项回顾性研究中，共有 1305 名患者2010 年 1 月至 2022 年 12 月期间，来自两个中心的经组织病理学证实的原发性骨肿瘤（内部数据集，n = 1043；外部数据集，n = 262）被纳入。我们提出了原发性骨肿瘤分类变压器网络（PBTC-TransNet）融合模型对原发性骨肿瘤进行分类。计算受试者工作特征曲线下面积 (AUC)、准确性、灵敏度和特异性，以评估模型的分类性能。PBTC-TransNet 融合模型取得了令人满意的微平均 AUC 0.847（95% CI：0.832，0.862），内部和外部测试集的值为 0.782（95% CI：0.749，0.817）。对于良性、中间性和恶性原发性骨肿瘤的分类，该模型在内部/外部测试集上分别实现了 0.827/0.727、0.740/0.662 和 0.815/0.745 的 AUC。此外，在按成像方式分布分层的所有患者亚组中，PBTC-TransNet 融合模型在内部和外部测试集上的微平均 AUC 分别为 0.700 至 0.909 和 0.640 至 0.847。该模型在内部测试集上仅使用 X 射线的情况下，显示出最高的微平均 AUC 为 0.909，准确度为 84.3%，微平均灵敏度为 84.3%，微平均特异性为 92.1%。在外部测试集上，PBTC-TransNet 融合模型对于 X 射线  CT 患者获得了最高的微平均 AUC 0.847。我们成功开发并外部验证了基于 Transformer 的 PBTC-Transnet 融合模型，用于原发性肿瘤的有效分类骨肿瘤。该模型植根于不完整的多模态图像和临床特征，有效地反映了现实生活中的临床场景，从而增强了其强大的临床实用性。© 2024。作者。

Accurately classifying primary bone tumors is crucial for guiding therapeutic decisions. The National Comprehensive Cancer Network guidelines recommend multimodal images to provide different perspectives for the comprehensive evaluation of primary bone tumors. However, in clinical practice, most patients' medical multimodal images are often incomplete. This study aimed to build a deep learning model using patients' incomplete multimodal images from X-ray, CT, and MRI alongside clinical characteristics to classify primary bone tumors as benign, intermediate, or malignant.In this retrospective study, a total of 1305 patients with histopathologically confirmed primary bone tumors (internal dataset, n = 1043; external dataset, n = 262) were included from two centers between January 2010 and December 2022. We proposed a Primary Bone Tumor Classification Transformer Network (PBTC-TransNet) fusion model to classify primary bone tumors. Areas under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were calculated to evaluate the model's classification performance.The PBTC-TransNet fusion model achieved satisfactory micro-average AUCs of 0.847 (95% CI: 0.832, 0.862) and 0.782 (95% CI: 0.749, 0.817) on the internal and external test sets. For the classification of benign, intermediate, and malignant primary bone tumors, the model respectively achieved AUCs of 0.827/0.727, 0.740/0.662, and 0.815/0.745 on the internal/external test sets. Furthermore, across all patient subgroups stratified by the distribution of imaging modalities, the PBTC-TransNet fusion model gained micro-average AUCs ranging from 0.700 to 0.909 and 0.640 to 0.847 on the internal and external test sets, respectively. The model showed the highest micro-average AUC of 0.909, accuracy of 84.3%, micro-average sensitivity of 84.3%, and micro-average specificity of 92.1% in those with only X-rays on the internal test set. On the external test set, the PBTC-TransNet fusion model gained the highest micro-average AUC of 0.847 for patients with X-ray + CT.We successfully developed and externally validated the transformer-based PBTC-Transnet fusion model for the effective classification of primary bone tumors. This model, rooted in incomplete multimodal images and clinical characteristics, effectively mirrors real-life clinical scenarios, thus enhancing its strong clinical practicability.© 2024. The Author(s).