标题： 基于随机森林的分布外检测用于鲁棒的肺癌分割 显示英文标题

标题： Random forest-based out-of-distribution detection for robust lung cancer segmentation

摘要： 从计算机断层扫描（CT）图像中准确检测和分割癌变病灶对于自动化治疗计划和癌症治疗反应评估至关重要。基于Transformer的模型通过自监督预训练可以在分布内（ID）数据上产生可靠准确的分割，但当应用于分布外（OOD）数据集时性能会下降。我们通过RF-Deep解决这一挑战，这是一种随机森林分类器，利用分割模型的预训练Transformer编码器的深度特征来检测OOD扫描并提高分割可靠性。分割模型包括一个Swin Transformer编码器，在10,432个未标记的3D CT扫描上通过掩码图像建模（SimMIM）进行预训练，涵盖癌性和非癌性情况，以及一个卷积解码器，在317个3D扫描上训练以分割肺癌。在包含一个ID数据集和四个OOD数据集的603个3D CT公共数据集上进行了独立测试，这些数据集包括有肺栓塞（PE）和新冠肺炎（COVID-19）的胸部CT，以及有肾癌和健康志愿者的腹部CT。RF-Deep在PE、新冠肺炎和腹部CT上分别以FPR95检测OOD病例为18.26%、27.66%和小于0.1%，始终优于现有的OOD方法。RF-Deep分类器提供了一种简单有效的方法，在ID和OOD场景中提高癌症分割的可靠性。 显示英文摘要

摘要： Accurate detection and segmentation of cancerous lesions from computed tomography (CT) scans is essential for automated treatment planning and cancer treatment response assessment. Transformer-based models with self-supervised pretraining can produce reliably accurate segmentation from in-distribution (ID) data but degrade when applied to out-of-distribution (OOD) datasets. We address this challenge with RF-Deep, a random forest classifier that utilizes deep features from a pretrained transformer encoder of the segmentation model to detect OOD scans and enhance segmentation reliability. The segmentation model comprises a Swin Transformer encoder, pretrained with masked image modeling (SimMIM) on 10,432 unlabeled 3D CT scans covering cancerous and non-cancerous conditions, with a convolution decoder, trained to segment lung cancers in 317 3D scans. Independent testing was performed on 603 3D CT public datasets that included one ID dataset and four OOD datasets comprising chest CTs with pulmonary embolism (PE) and COVID-19, and abdominal CTs with kidney cancers and healthy volunteers. RF-Deep detected OOD cases with a FPR95 of 18.26%, 27.66%, and less than 0.1% on PE, COVID-19, and abdominal CTs, consistently outperforming established OOD approaches. The RF-Deep classifier provides a simple and effective approach to enhance reliability of cancer segmentation in ID and OOD scenarios.