维尔姆斯肿瘤的 3D 重建具有多种优势，但由于手动分割极其耗时，因此并未系统地进行。我们研究的目的是开发一种人工智能工具来自动分割儿童肿瘤和肾脏。由两名专家对 14 张 CT 扫描进行手动分割。然后，使用 CNN U-Net 和根据 OV2ASSION 方法训练的相同 CNN U-Net 自动执行维尔姆斯肿瘤和肿瘤性肾脏的分割。根据自动分割的切片数量来估计专家节省的时间。当由两名专家手动执行分割时，个体间差异导致肿瘤的 Dice 指数为 0.95，肾脏的 Dice 指数为 0.87。使用 CNN U-Net 进行全自动分割，维尔姆斯肿瘤的 Dice 指数很差，为 0.69，肾脏的 Dice 指数为 0.27。使用 OV2ASSION 方法时，Dice 索引会根据手动分段部分的数量而变化。对于维尔姆斯肿瘤和肿瘤肾的分割，间隙为 1（手动执行 3 个切片中的 2 个）时，其值分别为 0.97 至 0.94；间隙为 10（手动执行 6 个切片中的 1 个切片）时，其值分别为 0.94 和 0.86。 ）。全自动分割仍然是医学图像处理领域的一个挑战。尽管可以使用已经开发的神经网络，例如 U-Net，但我们发现所获得的结果对于儿童肿瘤性肾脏或肾母细胞瘤的分割并不令人满意。我们开发了一种创新的 CNN U-Net 训练方法，可以像专家一样精确地分割肾脏及其肿瘤，同时将干预时间减少 80%。© 2024。作者。

3D reconstruction of Wilms' tumor provides several advantages but are not systematically performed because manual segmentation is extremely time-consuming. The objective of our study was to develop an artificial intelligence tool to automate the segmentation of tumors and kidneys in children.A manual segmentation was carried out by two experts on 14 CT scans. Then, the segmentation of Wilms' tumor and neoplastic kidney was automatically performed using the CNN U-Net and the same CNN U-Net trained according to the OV2ASSION method. The time saving for the expert was estimated depending on the number of sections automatically segmented.When segmentations were performed manually by two experts, the inter-individual variability resulted in a Dice index of 0.95 for tumor and 0.87 for kidney. Fully automatic segmentation with the CNN U-Net yielded a poor Dice index of 0.69 for Wilms' tumor and 0.27 for kidney. With the OV2ASSION method, the Dice index varied depending on the number of manually segmented sections. For the segmentation of the Wilms' tumor and neoplastic kidney, it varied respectively from 0.97 to 0.94 for a gap of 1 (2 out of 3 sections performed manually) to 0.94 and 0.86 for a gap of 10 (1 section out of 6 performed manually).Fully automated segmentation remains a challenge in the field of medical image processing. Although it is possible to use already developed neural networks, such as U-Net, we found that the results obtained were not satisfactory for segmentation of neoplastic kidneys or Wilms' tumors in children. We developed an innovative CNN U-Net training method that makes it possible to segment the kidney and its tumor with the same precision as an expert while reducing their intervention time by 80%.© 2024. The Author(s).