arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.19822cs.CVcs.AI
收藏

通过跨模态合成与梯度蒸馏实现高效的子宫内膜癌筛查

Efficient endometrial carcinoma screening via cross-modal synthesis and gradient distillation

School of Medical Information and Engineering, Southwest Medical University(西南医科大学医学信息与工程学院);School of Computer Science and Engineering, University of Electronic Science and Technology of China(电子科技大学计算机科学与工程学院);Department of Ultrasound, Affiliated Hospital of Southwest Medical University(西南医科大学附属医院超声科);Department of Functional Examination Unit, Zibo Hospital of Traditional Chinese Medicine(淄博中医药医院功能检查科);Key Laboratory of Medical Electrophysiology, Ministry of Education& Medical Electrophysiological Key Laboratory of Sichuan Province, Institute of Cardiovascular Research, Southwest Medical University(教育部医学电生理重点实验室、四川省医学电生理重点实验室、西南医科大学心血管研究所);Department of Radiology, the First Affiliated Hospital of Chongqing Medical University(重庆医科大学第一附属医院放射科);Department of Cardiology, Affiliated Hospital of Southwest Medical University(西南医科大学附属医院心内科);International Research Center for Complexity Sciences, Hangzhou International Innovation Institute, Beihang University(北京航空航天大学杭州国际创新研究院复杂科学研究中心);Institute of Intelligent Chinese Medicine, Chongqing University of Chinese Medicine(重庆中医药大学智能中药研究院);Basic Medicine Research Innovation Center for Cardiometabolic Diseases, Ministry of Education, Southwest Medical University(教育部心脑血管疾病基础医学研究创新中心、西南医科大学)

Dongjing Shan, Yamei Luo, Jiqing Xuan, Lu Huang, Jin Li, Mengchu Yang, Zeyu Chen, Fajin Lv, Yong Tang, Chunxiang Zhang

AI总结:

本文提出一种高效的两阶段深度学习框架,通过跨模态合成与梯度蒸馏技术,在低计算成本下实现高灵敏度和特异度的子宫内膜癌筛查。

摘要:

早期检测子宫肌层侵袭对于确定子宫内膜癌(EC)的分期和挽救生命管理至关重要,这是一种全球普遍的恶性肿瘤。阴道超声是资源有限初级保健环境中主要的可及筛查方法;然而,其诊断可靠性受到低组织对比度、高操作者依赖性和阳性病理样本严重缺乏的严重阻碍。现有的人工智能解决方案难以克服这一严重的类别不平衡和侵袭的细微成像特征,特别是在初级保健诊所严格的计算限制下。在这里,我们提出了一种自动化、高度高效的两阶段深度学习框架,解决了EC筛查中的数据和计算瓶颈。为了缓解病理数据稀缺,我们开发了一种结构引导的跨模态生成网络,从未配对的磁共振成像(MRI)数据中合成多样、高保真的超声图像,严格保留临床关键的解剖连接点。此外,我们引入了一种轻量级的筛查网络,利用梯度蒸馏,将高容量教师模型的判别知识转移到动态引导稀疏注意力聚焦于任务关键区域。在由7951名参与者组成的大型多中心队列上评估,我们的模型实现了99.5%的灵敏度、97.2%的特异度和曲线下面积为0.987的最小计算成本(0.289 GFLOPs),显著优于专家超声检查员的平均诊断准确性。我们的方法表明,结合跨模态合成增强与知识驱动的高效建模可以民主化初级保健环境中专家级别的实时癌症筛查。

英文摘要:

Early detection of myometrial invasion is critical for the staging and life-saving management of endometrial carcinoma (EC), a prevalent global malignancy. Transvaginal ultrasound serves as the primary, accessible screening modality in resource-constrained primary care settings; however, its diagnostic reliability is severely hindered by low tissue contrast, high operator dependence, and a pronounced scarcity of positive pathological samples. Existing artificial intelligence solutions struggle to overcome this severe class imbalance and the subtle imaging features of invasion, particularly under the strict computational limits of primary care clinics. Here we present an automated, highly efficient two-stage deep learning framework that resolves both data and computational bottlenecks in EC screening. To mitigate pathological data scarcity, we develop a structure-guided cross-modal generation network that synthesizes diverse, high-fidelity ultrasound images from unpaired magnetic resonance imaging (MRI) data, strictly preserving clinically essential anatomical junctions. Furthermore, we introduce a lightweight screening network utilizing gradient distillation, which transfers discriminative knowledge from a high-capacity teacher model to dynamically guide sparse attention towards task-critical regions. Evaluated on a large, multicenter cohort of 7,951 participants, our model achieves a sensitivity of 99.5\%, a specificity of 97.2\%, and an area under the curve of 0.987 at a minimal computational cost (0.289 GFLOPs), substantially outperforming the average diagnostic accuracy of expert sonographers. Our approach demonstrates that combining cross-modal synthetic augmentation with knowledge-driven efficient modeling can democratize expert-level, real-time cancer screening for resource-constrained primary care settings.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑