Autopet Challenge 2023：基于 nnUNet 的全身 3D PET-CT 肿瘤分割
Autopet Challenge 2023: nnUNet-based whole-body 3D PET-CT Tumour Segmentation
AI总结：
本文将 nnUNet 用于全身 PET-CT 肿瘤分割，并通过训练与后处理策略实验，在内部测试集上达到 69% Dice，模型已提交 autoPET 2023 挑战赛。
摘要：
氟代脱氧葡萄糖正电子发射断层成像（FDG-PET）与计算机断层扫描（CT）相结合，在肿瘤学中对于识别实体肿瘤和监测其进展至关重要。然而，精确且一致的病灶分割仍然具有挑战性，因为手动分割耗时，并且受观察者内部和观察者之间差异的影响。尽管自动化分割方法展现出前景，但它们往往难以处理健康代谢活动区域的假阳性分割，尤其是在面对全身如此复杂多样的肿瘤时。本文探索了 nnUNet 在全身 PET-CT 扫描肿瘤分割中的应用，并针对最优训练和后处理策略开展了不同实验。我们的最佳模型在内部测试集上取得了 69% 的 Dice 分数，假阴性和假阳性体积分别为 6.27 mL 和 5.78 mL。该模型作为 autoPET 2023 挑战赛的一部分提交。我们的代码可在 https://github.com/anissa218/autopet_nnunet 获取。
英文摘要：
Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) combined with Computed Tomography (CT) scans are critical in oncology to the identification of solid tumours and the monitoring of their progression. However, precise and consistent lesion segmentation remains challenging, as manual segmentation is time-consuming and subject to intra- and inter-observer variability. Despite their promise, automated segmentation methods often struggle with false positive segmentation of regions of healthy metabolic activity, particularly when presented with such a complex range of tumours across the whole body. In this paper, we explore the application of the nnUNet to tumour segmentation of whole-body PET-CT scans and conduct different experiments on optimal training and post-processing strategies. Our best model obtains a Dice score of 69\% and a false negative and false positive volume of 6.27 and 5.78 mL respectively, on our internal test set. This model is submitted as part of the autoPET 2023 challenge. Our code is available at: https://github.com/anissa218/autopet\_nnunet
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。
