Department of Radiology, Weill Cornell Medicine, New York, NY 10065, USA.
The Rogosin Institute, New York, NY 10065, USA.
Tomography. 2024 Jul 16;10(7):1148-1158. doi: 10.3390/tomography10070087.
Pancreatic cysts in autosomal dominant polycystic kidney disease (ADPKD) correlate with PKD2 mutations, which have a different phenotype than PKD1 mutations. However, pancreatic cysts are commonly overlooked by radiologists. Here, we automate the detection of pancreatic cysts on abdominal MRI in ADPKD.
Eight nnU-Net-based segmentation models with 2D or 3D configuration and various loss functions were trained on positive-only or positive-and-negative datasets, comprising axial and coronal T2-weighted MR images from 254 scans on 146 ADPKD patients with pancreatic cysts labeled independently by two radiologists. Model performance was evaluated on test subjects unseen in training, comprising 40 internal, 40 external, and 23 test-retest reproducibility ADPKD patients.
Two radiologists agreed on 52% of cysts labeled on training data, and 33%/25% on internal/external test datasets. The 2D model with a loss of combined dice similarity coefficient and cross-entropy trained with the dataset with both positive and negative cases produced an optimal dice score of 0.7 ± 0.5/0.8 ± 0.4 at the voxel level on internal/external validation and was thus used as the best-performing model. In the test-retest, the optimal model showed superior reproducibility (83% agreement between scan A and B) in segmenting pancreatic cysts compared to six expert observers (77% agreement). In the internal/external validation, the optimal model showed high specificity of 94%/100% but limited sensitivity of 20%/24%.
Labeling pancreatic cysts on T2 images of the abdomen in patients with ADPKD is challenging, deep learning can help the automated detection of pancreatic cysts, and further image quality improvement is warranted.
常染色体显性多囊肾病（ADPKD）患者的胰腺囊肿与 PKD2 基因突变相关，其表型与 PKD1 基因突变不同。然而，放射科医生通常会忽略胰腺囊肿。在此，我们对 ADPKD 患者腹部 MRI 上的胰腺囊肿进行自动检测。
使用 8 个基于 nnU-Net 的分割模型，具有 2D 或 3D 结构和各种损失函数，对仅阳性或阳性和阴性数据集进行训练，这些数据集由 146 名 ADPKD 患者的 254 次扫描的轴向和冠状 T2 加权 MR 图像组成，由两位放射科医生独立对胰腺囊肿进行标注。在未在训练中看到的测试对象上评估模型性能，包括 40 名内部、40 名外部和 23 名测试-重测可重复性 ADPKD 患者。
两位放射科医生在训练数据上标注的囊肿中有 52%达成一致，在内部和外部测试数据集上分别有 33%/25%达成一致。在具有正例和负例的数据集上使用联合骰子相似系数和交叉熵损失训练的 2D 模型在内部/外部验证时在体素水平上产生了最佳的骰子分数为 0.7 ± 0.5/0.8 ± 0.4，因此被用作表现最佳的模型。在测试-重测中，与 6 位专家观察者（83%的协议）相比，最优模型在胰腺囊肿的分割中显示出更高的可重复性（A 扫描和 B 扫描之间的 83%一致性）。在内部/外部验证中，最优模型显示出 94%/100%的高特异性，但敏感性有限，为 20%/24%。
在 ADPKD 患者的腹部 T2 图像上标注胰腺囊肿具有挑战性，深度学习可以帮助自动检测胰腺囊肿，并且需要进一步提高图像质量。
