AuraTracer智迹闻
中文

EVENT DOSSIER

Explainable Multimodal Deep Learning Integrating Imaging and Clinical Data for Oral Potentially Malignant Disorder Detection

2026-09-07 12:00 Science 🔥 40.2 heat score
1sources
1days unfolding
40.2heat score
2mentions
SummaryAI generated

On September 7, 2026, arXiv cs.CV published a study proposing an interpretable multi-modal deep learning method. This method integrates medical images and clinical data, aiming to improve the detection of potentially malignant oral lesions (OPMD).

Related eventsRELATED EVENTS
Key entitiesKEY ENTITIES
M2-OPMDNetarXiv:2609.04512v1

Coverage · reports per dayLANGUAGE SPLIT

Entity relations
M2-OPMDNet × arXiv:2609…1

SignalsSIGNALS

Keyword heat
  • M2-OPMDNet1
  • arXiv:2609.04512v11

All reports (1)SOURCES

A arXiv cs.CV en 2026-09-07 12:00

Explainable Multimodal Deep Learning Integrating Imaging and Clinical Data for Oral Potentially Malignant Disorder Detection

研究人员开发了 M2-OPMDNet 框架,该模型整合白光和自荧光口腔图像与结构化临床数据用于口腔潜在恶性病变检测。研究团队设计了定制问卷以标准化采集风险因素,并评估了多种图像编码器在前瞻性数据集上的表现。通过 SHAP 方法分析模型可解释性,结果显示 M2-OPMDNet 的 AUC 达到 0.952,优于单模态方法且在视觉细微病变检测上表现更佳。结构临床变量对风险评估有实质性贡献并补充了图像特征。该结果证明结合白光和自荧光成像与结构化临床数据的可解释多模态学习能提供准确、透明且基于临床的检测结果,M2-OPMDNet 为口腔癌筛查和决策支持提供了可扩展框架。