用于阴道镜CIN分级和Swede评分预测的双交叉注意力框架及新多中心数据集
A Dual Cross-Attention Framework for Colposcopic CIN Grading and Swede Score Prediction Using a New Multi-Center Dataset
浏览论文内容
中文总结 AI 辅助
提出双流交叉注意力框架，结合新多中心数据集，实现CIN分级与Swede评分预测，性能优于现有方法，助力资源有限环境下的AI辅助筛查。
中文摘要 AI 辅助
宫颈癌是全球重大健康挑战，疾病负担不成比例地落在低收入和中等收入国家（LMICs），原因是缺乏训练有素的专家以及基于阴道镜检查的筛查具有主观性。为解决这一挑战，我们提出了一种新颖的深度学习框架，用于宫颈上皮内瘤变（CIN）的自动分级和临床Swede评分的预测。我们还引入了BUET多中心阴道镜数据集，这是一个新颖的多中心队列，专为Swede评分预测和CIN分级而设计和标注。我们提出的双流交叉注意力架构通过显式融合配对的多模态宫颈图像来评估比较性组织反应，模拟了专家阴道镜医师的视觉推理。此外，我们引入了一种自定义复合损失函数，以解决五个Swede评分组件中严重的类别不平衡和评分不一致问题。所提出的框架在三级CIN分级中达到了71.85%的准确率和86.23%的AUC-ROC，优于现有方法。对于Swede评分组件预测，该架构实现了75.7%至88.4%的AUC-ROC值，复合损失函数带来了一致的F1分数提升。最后，总预测Swede评分（范围在0到10之间）的平均绝对误差（MAE）为1.489。结果表明，所提出的方法可以为开发AI辅助阴道镜筛查工具铺平道路，以支持资源有限的医疗环境中的基于风险的分诊。数据集和源代码公开可用（网址：this https URL）。
英文摘要
Cervical cancer is a major global health challenge, with disease burden falling disproportionately on low- and middle-income countries (LMICs) due to a shortage of trained specialists and the subjective nature of colposcopy-based screening. To address this challenge, we propose a novel deep learning framework for the automated grading of Cervical Intraepithelial Neoplasia (CIN) and the prediction of clinical Swede scores. We also introduce the BUET Multi-Center Colposcopy Dataset, a novel, multi-center cohort designed and annotated for Swede score prediction and CIN grading. Our proposed dual-stream cross-attention architecture mimics the visual reasoning of an expert colposcopist by explicitly fusing paired multimodal cervigrams to evaluate comparative tissue responses. Furthermore, we introduce a custom composite loss function to address severe class imbalances and scoring inconsistencies across the five Swede score components. The proposed framework achieved 71.85% accuracy and an 86.23% AUC-ROC for three-class CIN grading, outperforming existing methods. For Swede score component prediction, the architecture achieved AUC-ROC values ranging from 75.7% to 88.4%, with the composite loss function yielding consistent F1-score improvements. Finally, the total predicted Swede Score, which ranges between 0 and 10, shows a Mean Absolute Error (MAE) of 1.489. The results show that the proposed method can pave the way towards developing AI-assisted colposcopy screening tools to support risk-based triage in resource-limited healthcare settings. The dataset and source code are publicly available(url: https://github.com/mHealthBuet/BUET-colposcopy)
发表机构
- Bangladesh University of Engineering and Technology (BUET)（孟加拉国工程技术大学）
- Johns Hopkins University（约翰斯·霍普金斯大学）
- Dhaka Medical College（达卡医学院）
机构由 AI 辅助整理，请以论文原文为准。
