CT-3DFlow：利用 3D Normalizing Flows 进行病理性肺部 CT 扫描的无监督检测
CT-3DFlow : Leveraging 3D Normalizing Flows for Unsupervised Detection of Pathological Pulmonary CT scans
AI总结：
提出基于 3D Normalizing Flows 的 CT-3DFlow 模型，在健康肺部 CT 图块上无监督训练，通过聚合图块级对数似然偏差实现患者级病理检测，性能优于现有方法。
摘要：
无监督病理检测可通过仅在健康数据上训练模型并在推理时测量与训练集的偏差来实现，例如使用基于 CNN 的特征提取和单类分类器，或基于重建分数的方法如 AEs、GANs 和 Diffusion models。Normalizing Flows (NF) 能够通过可逆架构直接学习训练样本的概率分布。我们在名为 CT-3DFlow 的新型 3D NF 模型中利用这一特性，专门用于胸部 CT 数据的患者级肺部病理检测。该模型在健康 3D 肺部 CT 图块上进行无监督训练，并将其对数似然分布的偏差检测为异常。我们将患者 CT 扫描中的图块级似然值聚合，以提供患者级的“正常”/“异常”预测。使用专家在独立胸部 CT 测试数据集上的标注评估分布外检测性能，表现优于其他最先进方法。
英文摘要：
Unsupervised pathology detection can be implemented by training a model on healthy data only and measuring the deviation from the training set upon inference, for example with CNN-based feature extraction and one-class classifiers, or reconstruction-score-based methods such as AEs, GANs and Diffusion models. Normalizing Flows (NF) have the ability to directly learn the probability distribution of training examples through an invertible architecture. We leverage this property in a novel 3D NF-based model named CT-3DFlow, specifically tailored for patient-level pulmonary pathology detection in chest CT data. Our model is trained unsupervised on healthy 3D pulmonary CT patches, and detects deviations from its log-likelihood distribution as anomalies. We aggregate patches-level likelihood values from a patient's CT scan to provide a patient-level 'normal'/'abnormal' prediction. Out-of-distribution detection performance is evaluated using expert annotations on a separate chest CT test dataset, outperforming other state-of-the-art methods.
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。
