胸部-腹部CT扫描中的肾脏异常分割
Kidney abnormality segmentation in thorax-abdomen CT scans
AI总结：
本研究提出一种基于改进3D U-Net和nnUNet集成的深度学习方法，用于分割肾实质和肾脏异常，在肾实质分割上优于人类观察者，但在异常分割上仍有提升空间。
摘要：
在本研究中，我们引入了一种深度学习方法，用于分割肾实质和肾脏异常，以支持临床医生识别和量化诸如囊肿、病变、肿块、转移和原发性肿瘤等肾脏异常。我们的端到端分割方法在215张对比增强的胸部-腹部CT扫描上进行了训练，其中一半的扫描包含一种或多种异常。我们首先实现了原始3D U-Net网络的自己版本，并加入了四个额外组件：端到端多分辨率方法、一组任务特定的数据增强、使用top-$k$的修改损失函数以及空间dropout。此外，我们设计了一种定制的后处理策略。消融研究表明，这四项修改中的每一项都提高了肾脏异常分割性能，其中三项提高了肾实质分割。随后，我们在我们的数据集上训练了nnUNet框架。通过将优化的3D U-Net和nnUNet与我们专门的后处理进行集成，我们获得了略微优越的结果。我们表现最佳的模型在两个测试集（20张无异常扫描和30张有异常扫描）中分割肾实质的Dice得分分别为0.965和0.947，优于独立的人类观察者（得分分别为0.944和0.925）。在包含异常的30张测试扫描中分割肾脏异常时，表现最佳的方法达到了0.585的Dice得分，而独立的第二位人类观察者达到了0.664的得分，表明计算机化方法仍有进一步改进的潜力。所有训练数据均根据CC-BY 4.0许可证在https://doi.org/10.5281/zenodo.8014289上向研究社区提供。
英文摘要：
In this study, we introduce a deep learning approach for segmenting kidney parenchyma and kidney abnormalities to support clinicians in identifying and quantifying renal abnormalities such as cysts, lesions, masses, metastases, and primary tumors. Our end-to-end segmentation method was trained on 215 contrast-enhanced thoracic-abdominal CT scans, with half of these scans containing one or more abnormalities. We began by implementing our own version of the original 3D U-Net network and incorporated four additional components: an end-to-end multi-resolution approach, a set of task-specific data augmentations, a modified loss function using top-$k$, and spatial dropout. Furthermore, we devised a tailored post-processing strategy. Ablation studies demonstrated that each of the four modifications enhanced kidney abnormality segmentation performance, while three out of four improved kidney parenchyma segmentation. Subsequently, we trained the nnUNet framework on our dataset. By ensembling the optimized 3D U-Net and the nnUNet with our specialized post-processing, we achieved marginally superior results. Our best-performing model attained Dice scores of 0.965 and 0.947 for segmenting kidney parenchyma in two test sets (20 scans without abnormalities and 30 with abnormalities), outperforming an independent human observer who scored 0.944 and 0.925, respectively. In segmenting kidney abnormalities within the 30 test scans containing them, the top-performing method achieved a Dice score of 0.585, while an independent second human observer reached a score of 0.664, suggesting potential for further improvement in computerized methods. All training data is available to the research community under a CC-BY 4.0 license on https://doi.org/10.5281/zenodo.8014289
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。
