arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2307.04541cs.CVcs.AI
收藏

面向开放集医疗诊断的大间隔稀疏嵌入学习

Learning Large Margin Sparse Embeddings for Open Set Medical Diagnosis

Beihang University(北京航空航天大学);School of Biological Science and Medical Engineering(生物与医学工程学院);Hefei Innovation Research Institute, Beihang University(北京航空航天大学合肥创新研究院)

Mingyuan Liu, Lu Xu, Jicong Zhang

AI总结:

针对医疗诊断中开放集识别的挑战,提出融合自适应尺度间隔损失与开放空间抑制的OMCL方法,同时发布两个医疗OSR基准数据集,实验表明该方法在多项指标上优于现有最优方法。

摘要:

在深度学习的推动下,计算机辅助诊断取得了巨大进展。然而,在受控实验室环境之外,算法可能面临多重挑战。开放集识别(Open Set Recognition, OSR)便是其中一项重要挑战,其核心问题是测试阶段可能出现训练过程中未见过的类别。在医疗领域,这一问题可能源于训练数据集收集不完整,以及不断出现的新型或罕见疾病。开放集识别要求算法不仅能正确分类已知类别,还能识别未知类别并将其提交给专家做进一步诊断。\n为解决开放集识别问题,我们假设已知类别会密集占据嵌入空间的小部分区域,而其余稀疏区域可被识别为未知类别。基于这一假设,我们提出了融合两种机制的Open Margin Cosine Loss(OMCL,开放间隔余弦损失)。第一种机制名为Margin Loss with Adaptive Scale(MLAS,自适应尺度间隔损失),通过引入角度间隔增强类内紧凑性与类间可分性,并搭配自适应缩放因子提升泛化能力;第二种机制名为Open-Space Suppression(OSS,开放空间抑制),利用提出的特征空间描述符将稀疏嵌入空间识别为未知类别,从而实现分类器的开放化。\n此外,由于医疗领域的开放集识别仍处于起步阶段,我们提出了两个公开基准数据集用于方法对比。大量消融实验和特征可视化结果验证了各设计模块的有效性。与当前最优方法相比,MLAS在ACC(准确率)、AUROC(受试者工作特征曲线下面积)和OSCR(开放集分类率)指标上均取得了更优性能。

英文摘要:

Fueled by deep learning, computer-aided diagnosis achieves huge advances. However, out of controlled lab environments, algorithms could face multiple challenges. Open set recognition (OSR), as an important one, states that categories unseen in training could appear in testing. In medical fields, it could derive from incompletely collected training datasets and the constantly emerging new or rare diseases. OSR requires an algorithm to not only correctly classify known classes, but also recognize unknown classes and forward them to experts for further diagnosis. To tackle OSR, we assume that known classes could densely occupy small parts of the embedding space and the remaining sparse regions could be recognized as unknowns. Following it, we propose Open Margin Cosine Loss (OMCL) unifying two mechanisms. The former, called Margin Loss with Adaptive Scale (MLAS), introduces angular margin for reinforcing intra-class compactness and inter-class separability, together with an adaptive scaling factor to strengthen the generalization capacity. The latter, called Open-Space Suppression (OSS), opens the classifier by recognizing sparse embedding space as unknowns using proposed feature space descriptors. Besides, since medical OSR is still a nascent field, two publicly available benchmark datasets are proposed for comparison. Extensive ablation studies and feature visualization demonstrate the effectiveness of each design. Compared with state-of-the-art methods, MLAS achieves superior performances, measured by ACC, AUROC, and OSCR.

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。

↑