减少轮廓标注，提升准确率：用于卵巢超声分类的病灶引导感兴趣区深度学习方法
Less Contouring, More Accuracy: Lesion-Guided ROI Deep Learning for Ovarian Ultrasound Classification
浏览论文内容
中文总结 AI 辅助
本研究提出病灶引导ROI深度学习方法，在卵巢超声分类任务中，以MaxViT-Tiny架构在两个公开数据集上实现优异性能，且标注负担远低于基于病灶轮廓的方法，兼顾诊断精度与标注效率。
中文摘要 AI 辅助
经阴道超声进行卵巢病灶分类仍存在挑战，原因在于影像特征重叠且依赖专家解读。本研究探究病灶引导感兴趣区（ROI）深度学习能否在达到有竞争力诊断性能的同时，降低像素级病灶分割带来的标注负担。研究评估两个公开卵巢超声数据集：用于八分类的多模态卵巢肿瘤超声（MMOTU）数据集，以及用于二分类的卵巢超声数据集（OUD）。在统一框架下比较四种策略：基于全局图像的深度学习、基于病灶引导ROI的深度学习、基于病灶轮廓的深度学习，以及结合机器学习分类器的基于轮廓的放射组学。评估四种深度学习架构：MaxViT-Tiny、Swin Transformer、EfficientNet-B7和ResNet18。放射组学模型采用支持向量机、k近邻和人工神经网络分类器构建，对样本量较小的OUD数据集应用基于方差分析的特征选择。病灶引导ROI策略取得整体最优性能，其中MaxViT-Tiny在MMOTU数据集上准确率达93.10%、AUC为0.99，在OUD数据集上准确率达97.56%、AUC为0.99。基于轮廓的方法准确率相近，但标注工作量显著更高。这些发现表明，病灶引导ROI深度学习可在诊断性能与标注效率间实现有效平衡，为可扩展的AI辅助卵巢超声分析提供实用方案。
英文摘要
Ovarian lesion classification using transvaginal ultrasound remains challenging due to overlapping imaging characteristics and the dependence on expert interpretation. This study investigates whether lesion-guided region-of-interest (ROI) deep learning can achieve competitive diagnostic performance while reducing the annotation burden associated with pixel-level lesion segmentation. Two publicly available ovarian ultrasound datasets were evaluated: the Multi-Modality Ovarian Tumor Ultrasound (MMOTU) dataset for eight-class classification and the Ovarian Ultrasound Dataset (OUD) for binary classification. Four strategies were compared under a unified framework: global image-based deep learning, lesion-guided ROI-based deep learning, lesion contour-based deep learning, and contour-based radiomics with machine learning classifiers. Four deep learning architectures, MaxViT-Tiny, Swin Transformer, EfficientNet-B7, and ResNet18, were evaluated. Radiomics models were developed using support vector machine, k-nearest neighbors, and artificial neural network classifiers, with ANOVA-based feature selection applied for the lower-sample OUD dataset. The lesion-guided ROI strategy achieved the strongest overall performance, with MaxViT-Tiny obtaining 93.10% accuracy and an AUC of 0.99 on MMOTU and 97.56% accuracy and an AUC of 0.99 on OUD. The contour-based approach achieved comparable accuracy but required substantially higher annotation effort. These findings demonstrate that lesion-guided ROI deep learning provides an effective balance between diagnostic performance and annotation efficiency, offering a practical approach for scalable AI-assisted ovarian ultrasound analysis
发表机构
- Danube Private University (DPU)（多瑙河私立大学）
- Austrian Centre for Medical Innovation and Technology (ACMIT)（奥地利医学创新与技术中心）
- Medical University of Vienna（维也纳医科大学）
- Urmia University of Medical Science（乌尔米亚医科大学）
机构由 AI 辅助整理，请以论文原文为准。
