Purpose: The last two decades have witnessed a dramatic development of minimally invasive surgery (MIS). Robotic-assisted surgery is currently the latest step in the evolution of MIS. MIS was initially developed for adult surgery, but its use has progressively been extended to pediatrics. As for all new technologies, an objective evaluation is essential to adopt the robot in the practice of pediatrics. Materials and Methods: This article reviews the spectrum of evidence regarding the feasibility, safety, benefits, and limitations of abdominal and urological robot-assisted surgery in children. This analysis was performed using the PubMed database, using key words such as “robot,” “robotic surgery,” “robot-assisted,” “da Vinci,” and “computer-enhanced surgery” combined with “child,” “children,” “infants,” and “pediatric.” Results: In total, 88 studies met the selection criteria for our review. Only 10 studies comparing robotic surgery with open or conventional laparoscopic surgery are available for abdominal or urological pediatric procedures. Fundoplication for gastroesophageal reflux and pyeloplasty for hydronephrosis represent the most frequent procedures performed with robotic assistance in children. Conclusions: Robotic surgery is suitable in the pediatric practice, which necessitates fine dissections and sutures in narrow anatomical spaces. The initial results of robotic surgery in the field of pediatrics are encouraging. Further prospective and comparative studies, especially between robotic and laparoscopic approaches, are required to confirm these preliminary results.

Background: 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. Methods: 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. Results: 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). Conclusion: 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%.