整合局部细节与全局上下文：用于骨肿瘤诊断的双输入多任务学习框架

中文摘要 AI 辅助

原发性骨肿瘤是罕见但临床上具有侵袭性的肿瘤，其影像学诊断面临异质性形态、细微病灶边缘和重叠骨结构等挑战。为解决现有单视图模型的局限性，我们提出了一种双输入多任务学习框架，据我们所知，该框架首次在病灶裁剪区域与全幅X光片之间应用双向跨模态注意力，以联合进行分割和亚型分类。利用多机构骨肿瘤X光影像数据集（BTXRD，n=3,746），我们采用基于YOLO的检测器生成感兴趣区域，并将其与全幅图像配对作为双流DenseNet121架构的输入。通过一种新颖的跨模态注意力融合策略整合特征，并辅以层次化多尺度特征融合进行优化，有效平衡了细粒度病灶细节与全局解剖上下文。在留出的患者级测试集上评估，该模型展现出优于单输入基线的性能，总体Dice相似系数达到0.896，宏平均分类F1分数为0.928。值得注意的是，该系统对恶性骨肉瘤表现出卓越的敏感性（AUC 0.999），验证了双流上下文建模在支持放射科医生进行准确、早期决策方面的潜力。

英文摘要

Primary bone tumors are rare but clinically aggressive neoplasms whose diagnosis from radiographs is challenged by heterogeneous morphology, subtle lesion margins, and overlapping bone structures. To address the limitations of existing single-view models, we present a dual-input, multi-task learning framework that, to our knowledge, is the first to apply bidirectional cross-modal attention between a lesion crop and the full radiograph for joint segmentation and subtype classification. Using the multi-institutional Bone Tumor X-ray Radiograph Dataset (BTXRD, n=3,746), we employ a YOLO-based detector to generate regions of interest, which are paired with full images as inputs to a dual-stream DenseNet121 architecture. Features are integrated via a novel cross-modal attention fusion strategy, refined by Hierarchical Multi-scale Feature Fusion, effectively balancing fine-grained lesion detail with global anatomical context. Evaluated on a held-out patient-level test split, the model demonstrates superior performance over single-input baselines, achieving an overall Dice Similarity Coefficient of 0.896 and a macro-averaged classification F1-score of 0.928. Notably, the system exhibits exceptional sensitivity for malignant osteosarcoma (AUC 0.999), validating the potential of dual-stream context modeling to support radiologists in accurate, early decision-making.

发表机构

• Ahsanullah University of Science and Technology（阿赫桑努拉科技大学）
• University of Dhaka（达卡大学）
• Qatar University（卡塔尔大学）
• Hamad Medical Corporation（哈马德医疗公司）

机构由 AI 辅助整理，请以论文原文为准。