The accurate detection of suspicious regions in medical images is an error-prone and time-consuming process required by many routinely performed diagnostic procedures. To support clinicians during this difficult task, several automated solutions were proposed relying on complex methods with many hyperparameters. In this study, we investigate the feasibility of DEtection TRansformer (DETR) models for volumetric medical object detection. In contrast to previous works, these models directly predict a set of objects without relying on the design of anchors or manual heuristics such as non-maximum-suppression to detect objects. We show by conducting extensive experiments with three models, namely DETR, Conditional DETR, and DINO DETR on four data sets (CADA, RibFrac, KiTS19, and LIDC) that these set prediction models can perform on par with or even better than currently existing methods. DINO DETR, the best-performing model in our experiments demonstrates this by outperforming a strong anchor-based one-stage detector, Retina U-Net, on three out of four data sets.

翻译：医学图像中可疑区域的精确检测是许多常规诊断程序中既易出错又耗时的过程。为支持临床医生完成这一艰巨任务，已有多种基于复杂方法（含大量超参数）的自动化解决方案被提出。本研究探讨了检测变形金刚（DETR）模型在三维医学目标检测中的可行性。与先前工作不同，这些模型直接预测目标集合，无需依赖锚框设计或非极大值抑制等人工启发式方法进行目标检测。通过在四个数据集（CADA、RibFrac、KiTS19和LIDC）上对三种模型（DETR、Conditional DETR和DINO DETR）进行广泛实验，我们证明这些集合预测模型能够达到甚至优于现有方法的性能。表现最优的DINO DETR模型在四个数据集中有三个数据集上超越了基于锚框的强基线单阶段检测器Retina U-Net。