This research embarked on a comparative exploration of the holistic
segmentation capabilities of Convolutional Neural Networks (CNNs) in both 2D
and 3D formats, focusing on cystic fibrosis (CF) lesions. The study utilized
data from two CF reference centers, covering five major CF structural changes.
Initially, it compared the 2D and 3D models, highlighting the 3D model's
superior capability in capturing complex features like mucus plugs and
consolidations. To improve the 2D model's performance, a loss adapted to fine
structures segmentation was implemented and evaluated, significantly enhancing
its accuracy, though not surpassing the 3D model's performance. The models
underwent further validation through external evaluation against pulmonary
function tests (PFTs), confirming the robustness of the findings. Moreover,
this study went beyond comparing metrics; it also included comprehensive
assessments of the models' interpretability and reliability, providing valuable
insights for their clinical application.

该研究比较了卷积神经网络在 2D 和 3D 格式中对囊性纤维化病变的整体分割能力，并重点研究了 5 个主要囊性纤维化结构变化。通过对比 2D 和 3D 模型，发现 3D 模型在捕捉粘液栓和肺实变等复杂特征方面具有优势。通过实验引入了适用于细结构分割的损失函数并评估，显著提高了 2D 模型的准确性，但未超过 3D 模型的性能。模型经过外部评估计算肺功能测试，证实了研究结果的稳健性。此外，研究还包括了对模型的可解释性和可靠性的综合评估，为其临床应用提供了宝贵的见解。