面向医学影像中细微异常的节俭无监督检测
Towards frugal unsupervised detection of subtle abnormalities in medical imaging
AI总结：
针对医学影像中无标注的细微异常检测，提出基于混合概率分布的节俭无监督方法，通过增量计算推断量实现高效学习，并在帕金森病脑扫描中验证了与疾病进展一致的异常检测。
摘要：
在异常未被标注的背景下，医学影像中的异常检测是一项具有挑战性的任务。该问题可通过无监督异常检测（UAD）方法解决，这些方法识别与正常轮廓参考模型不匹配的特征。人工神经网络已广泛用于UAD，但通常无法在准确性和计算需求之间实现最优权衡。作为替代方案，我们研究了混合概率分布，其多功能性已被广泛认可适用于各种数据和任务，同时不需要过多的设计工作或调参。它们的表达能力使其成为构建复杂多元参考模型的良好候选。它们更少的参数数量使其更易于解释和高效学习。然而，标准估计程序（如期望最大化算法）由于需要高内存使用，难以扩展到大数据量。为解决此问题，我们提出增量计算推断量。这种在线方法在挑战性任务中得到了验证，即在新诊断帕金森病患者随访的MR脑扫描中检测细微异常。所识别的结构异常与疾病进展一致，如Hoehn和Yahr量表所示。
英文摘要：
Anomaly detection in medical imaging is a challenging task in contexts where abnormalities are not annotated. This problem can be addressed through unsupervised anomaly detection (UAD) methods, which identify features that do not match with a reference model of normal profiles. Artificial neural networks have been extensively used for UAD but they do not generally achieve an optimal trade-o$\hookleftarrow$ between accuracy and computational demand. As an alternative, we investigate mixtures of probability distributions whose versatility has been widely recognized for a variety of data and tasks, while not requiring excessive design e$\hookleftarrow$ort or tuning. Their expressivity makes them good candidates to account for complex multivariate reference models. Their much smaller number of parameters makes them more amenable to interpretation and e cient learning. However, standard estimation procedures, such as the Expectation-Maximization algorithm, do not scale well to large data volumes as they require high memory usage. To address this issue, we propose to incrementally compute inferential quantities. This online approach is illustrated on the challenging detection of subtle abnormalities in MR brain scans for the follow-up of newly diagnosed Parkinsonian patients. The identified structural abnormalities are consistent with the disease progression, as accounted by the Hoehn and Yahr scale.
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。
