arXiv：cs.LG· Simon Hadush Nrea (Mekelle University, Mekelle, Ethiopia), Filimon Gidey Gebremichael (Mekelle University, Mekelle, Ethiopia), Gebrekirstos Hagos Gebrekirstos (Clinical Oncologist London School of Hygiene and Tropical Medicine London, UK), Yaecob Girmay Gezahegn (Mekelle University, Mekelle, Ethiopia)·· 4 小时前AI 评分34
HCMAN：面向低资源临床环境的乳腺癌早期检测混合跨模态注意力网络
Hybrid Cross-Modal Attention Network for Early Breast Cancer Detection in Low-Resource Clinical Settings
AI 导读
研究提出混合跨模态注意力网络（HCMAN），将乳腺钼靶图像与结构化临床数据通过Transformer跨模态注意力机制融合，用于乳腺癌早期检测。基于埃塞俄比亚四家转诊医院1024名患者的2560张钼靶图像数据集，模型达到97.8%准确率、97.2%灵敏度、98.3%特异性和0.987的AUC，显著优于仅用图像的基线。
正文
Abstract:Breast cancer is the leading cause of cancer-related mortality among women in Sub-Saharan Africa, where delayed diagnosis results from limited radiology expertise and fragmented clinical data systems. Although deep learning models have demonstrated strong performance in mammographic analysis, most rely solely on imaging data and are trained on Western populations, limiting their applicability in African healthcare settings. This paper presents a Hybrid Cross-Modal Attention Network (HCMAN) that integrates mammogram images with structured clinical data using transformer-based cross-modal attention mechanisms. The model was developed and validated using a locally collected dataset of 2,560 mammogram images from 1,024 patients across four Ethiopian referral hospitals, with biopsy-confirmed ground truth labels. The proposed framework achieves 97.8% accuracy, 97.2% sensitivity, 98.3% specificity, and an AUC of 0.987, significantly outperforming image-only baselines. The system demonstrates robustness to low-quality images typical of resource-limited settings, with only 3.2% performance degradation compared to 8.7% for image-only models. Cross-modal attention analysis reveals clinically appropriate behavior: higher reliance on clinical features for ambiguous cases such as dense breasts and young patients. The model's lightweight architecture enables deployment on standard hospital workstations (<2 seconds inference on CPU). This work advances sustainable, context-aware AI solutions for equitable breast cancer diagnostics in Africa.
| Comments: | 5 double pages numbers, conference paper presented at AI4SD 2026 (this https URL) |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.07243 [cs.CV] |
| (or arXiv:2610.07243v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07243 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Simon Hadush Nrea [view email]
[v1]
Mon, 5 Oct 2026 18:44:51 UTC (442 KB)
来源：arXiv：cs.LG · arxiv.org