Purpose: The aim of this study was to evaluate the diagnostic value and accuracy of navigated intraoperative ultrasound (iUS) in pediatric oncological neurosurgery as compared to intraoperative magnetic resonance imaging (iMRI). Methods: A total of 24 pediatric patients undergoing tumor debulking surgery with iUS, iMRI, and neuronavigation were included in this study. Prospective acquisition of iUS images was done at two time points during the surgical procedure: (1) before resection for tumor visualization and (2) after resection for residual tumor assessment. Dice similarity coefficients (DSC), Hausdorff distances 95th percentiles (HD95) and volume differences, sensitivity, and specificity were calculated for iUS segmentations as compared to iMRI. Results: A high correlation (R = 0.99) was found for volume estimation as measured on iUS and iMRI before resection. A good spatial accuracy was demonstrated with a median DSC of 0.72 (IQR 0.14) and a median HD95 percentile of 4.98 mm (IQR 2.22 mm). The assessment after resection demonstrated a sensitivity of 100% and a specificity of 84.6% for residual tumor detection with navigated iUS. A moderate accuracy was observed with a median DSC of 0.58 (IQR 0.27) and a median HD95 of 5.84 mm (IQR 4.04 mm) for residual tumor volumes. Conclusion: We found that iUS measurements of tumor volume before resection correlate well with those obtained from preoperative MRI. The accuracy of residual tumor detection was reliable as compared to iMRI, indicating the suitability of iUS for directing the surgeon’s attention to areas suspect for residual tumor. Therefore, iUS is considered as a valuable addition to the neurosurgical armamentarium. Trial registration number and date: PMCLAB2023.476, February 12th 2024.
Automatic bone surface segmentation represents an advanced alternative for conventional patient registration methods in surgical navigation technologies. In pediatrics, such technologies require tailored approaches to ensure optimal performance—specifically in patients under the age of ten, whose immature bones have less distinct bone characteristics. In this study, we developed a segmentation model tailored for pediatric patients. We captured 4309 ultrasound images from the bones in the extremities, pelvis and thorax of 16 pediatric patients. The dataset was manually annotated by a technical physician and sample-wise validated by a pediatric radiologist. A UNeXt deep learning model was trained for automatic segmentation. The segmentation performance was evaluated using the mean centerline Dice score and the mean surface distance. A mean centerline Dice score of 0.85 (SD: 0.13) and a mean surface distance of 0.78 mm (SD: 1.15 mm) were achieved. No important differences in performance were observed for patients younger than the age of ten compared to older patients. Our results demonstrate that the segmentation model detects the bone surface with sufficient accuracy, enabling precise and effective patient registration. The model performs sufficiently across different pediatric age groups, making it a viable tool for integration into ultrasound-based patient registration in image-guided pediatric surgery.
BACKGROUND AND OBJECTIVES: Intraoperative ultrasound (iUS) is increasingly used in pediatric brain tumor surgery. However, accurate tumor tissue identification and localization within the patient with iUS remains challenging. Automatic tumor segmentation may overcome these difficulties by providing quicker, more consistent, and reliable image analysis. This study evaluated the feasibility of automatic 3-dimensional segmentation of pediatric brain tumors using navigated iUS. METHODS: A retrospective analysis was conducted on 109 navigated iUS acquisitions from 60 pediatric patients who underwent neurosurgical tumor resection. 3-dimensional nnU-Net was trained on 79 preresectional iUS acquisitions with corresponding tumor segmentations. Evaluation was performed on 30 iUS acquisitions against segmentations validated by 2 neurosurgeons. Performance benchmarks were set at a minimum Dice Similarity Coefficient (DSC) of 0.85 and a maximum mean surface distance and 95th percentile Hausdorff distance of 5 mm. RESULTS: The trained algorithm predicted tumor segmentations for all acquisitions in the test set, which met the predefined benchmark values with a median DSC of 0.89 (IQR: 0.13), a median mean surface distance of 1.1 mm (IQR: 1.0 mm), and a median 95th percentile Hausdorff distance of 5.6 mm (IQR: 3.5 mm). The lowest quartile of DSC values consisted of 5 patients, including craniopharyngiomas (n = 3) and high-grade gliomas (n = 2). Oversegmentation of the lateral ventricle as tumor was observed in 2 patients. In 1 high-grade glioma case, edema was misclassified as tumor because of unclear tumor boundaries. CONCLUSION: This study demonstrates that automatic segmentation of pediatric brain tumors using navigated iUS is feasible and achieved high performance in most cases, with few outliers that showed moderate performance in tumor prediction. Future efforts will focus on real-time segmentation of residual tumor tissue during tumor resection. Ultimately, real-time visualization of automatically segmented tumors in 3 dimensions could improve intraoperative navigation and support neurosurgical decision making.