病变检测是肿瘤学正电子发射断层扫描 (PET) 中最重要的临床任务之一。设计用于在检测任务中复制人类观察者（HO）的拟人模型观察者（MO）是评估基于任务的图像质量的重要工具。通道化霍特林观察者（CHO）是最受欢迎的拟人化 MO。最近，主要基于卷积神经网络（CNN）的深度学习 MO（DLMO）已针对各种成像模式进行了研究。然而，关于 DLMO 用于 PET 的研究还很少。该研究的目的是研究 DLMO 是否能够比传统 MO（例如 CHO）更好地预测 HO，在使用具有真实图像的 PET 图像进行二选一强制选择（2AFC）检测任务中。实现了两种类型的 DLMO：(1) CNN DLMO，以及 (2) 结合了 CNN 和 Swin Transformer (SwinT) 编码器的 CNN-SwinT DLMO。根据临床数据重建无病变 PET 图像，并通过添加模拟病变正弦图数据重建有病变图像。在 2AFC 检测任务中，由四名放射科医生和四名图像科学家组成的 8 个 HO 标记了存在病变和不存在病变的 PET 图像对。总共使用 2268 对存在病变和不存在病变的图像进行训练，324 对用于验证，324 对用于测试。在相同的训练测试范例中对 CNN DLMO、CNN-SwinT DLMO、具有内部噪声的 CHO 和非预白化匹配滤波器 (NPWMF) 进行了比较。为了进行比较，在 9 倍交叉验证实验中计算了六个定量指标，包括预测准确性、均方误差 (MSE) 和相关系数，这些指标衡量 MO 预测 HO 的效果。在准确性和 MSE 指标方面， CNN DLMO和CNN-SwinT DLMO表现出比CHO和NPWMF更好的性能，并且CNN-SwinT DLMO在评估的MO中表现出最好的性能。在PET病变检测中，DLMO比CHO等传统MO能够更准确地预测HO。与仅使用 CNN 相比，结合 SwinT 和 CNN 编码器可以提高 DLMO 预测性能。© 2024 美国医学物理学家协会。

Lesion detection is one of the most important clinical tasks in positron emission tomography (PET) for oncology. An anthropomorphic model observer (MO) designed to replicate human observers (HOs) in a detection task is an important tool for assessing task-based image quality. The channelized Hotelling observer (CHO) has been the most popular anthropomorphic MO. Recently, deep learning MOs (DLMOs), mostly based on convolutional neural networks (CNNs), have been investigated for various imaging modalities. However, there have been few studies on DLMOs for PET.The goal of the study is to investigate whether DLMOs can predict HOs better than conventional MOs such as CHO in a two-alternative forced-choice (2AFC) detection task using PET images with real anatomical variability.Two types of DLMOs were implemented: (1) CNN DLMO, and (2) CNN-SwinT DLMO that combines CNN and Swin Transformer (SwinT) encoders. Lesion-absent PET images were reconstructed from clinical data, and lesion-present images were reconstructed with adding simulated lesion sinogram data. Lesion-present and lesion-absent PET image pairs were labeled by eight HOs consisting of four radiologists and four image scientists in a 2AFC detection task. In total, 2268 pairs of lesion-present and lesion-absent images were used for training, 324 pairs for validation, and 324 pairs for test. CNN DLMO, CNN-SwinT DLMO, CHO with internal noise, and non-prewhitening matched filter (NPWMF) were compared in the same train-test paradigm. For comparison, six quantitative metrics including prediction accuracy, mean squared errors (MSEs) and correlation coefficients, which measure how well a MO predicts HOs, were calculated in a 9-fold cross-validation experiment.In terms of the accuracy and MSE metrics, CNN DLMO and CNN-SwinT DLMO showed better performance than CHO and NPWMF, and CNN-SwinT DLMO showed the best performance among the MOs evaluated.DLMO can predict HOs more accurately than conventional MOs such as CHO in PET lesion detection. Combining SwinT and CNN encoders can improve the DLMO prediction performance compared to using CNN only.© 2024 American Association of Physicists in Medicine.