Evaluation of Interactive Virtual Reality as a Preoperative Aid in Localizing Renal Tumors

Patient-specific simulations and navigation systems for partial nephrectomy

Partial nephrectomy (PN) is the standard treatment for T1 renal cell carcinoma. PN is affected more by surgical variations and requires greater surgical experience than radical nephrectomy. Patient-specific simulations and navigation systems may help to reduce the surgical experience required for PN. Recent advances in three-dimensional (3D) virtual reality (VR) imaging and 3D printing technology have allowed accurate patient-specific simulations and navigation systems. We reviewed previous studies about patient-specific simulations and navigation systems for PN. Recently, image reconstruction technology has developed, and commercial software that converts two-dimensional images into 3D images has become available. Many urologists are now able to view 3DVR images when preparing for PN. Surgical simulations based on 3DVR images can change surgical plans and improve surgical outcomes, and are useful during patient consultations. Patient-specific simulators that are capable of simulating surgical procedures, the gold-standard form of patient-specific simulations, have also been reported. Besides VR, 3D printing is also useful for understanding patient-specific information. Some studies have reported simulation and navigation systems for PN based on solid 3D models. Patient-specific simulations are a form of preoperative preparation, whereas patient-specific navigation is used intraoperatively. Navigation-assisted PN procedures using 3DVR images have become increasingly common, especially in robotic surgery. Some studies found that these systems produced improvements in surgical outcomes. Once its accuracy has been confirmed, it is hoped that this technology will spread further and become more generalized.

Virtual reality and surgical oncology

More than 80% of people diagnosed with cancer will require surgery. However, less than 5% have access to safe, affordable and timely surgery in low- and middle-income countries (LMICs) settings mostly due to the lack of trained workforce. Since its creation, virtual reality (VR) has been heralded as a viable adjunct to surgical training, but its adoption in surgical oncology to date is poorly understood. We undertook a systematic review to determine the application of VR across different surgical specialties, modalities and cancer pathway globally between January 2011 and 2021. We reviewed their characteristics and respective methods of validation of 24 articles. The results revealed gaps in application and accessibility of VR with a proclivity for high-income countries and high-risk, complex oncological surgeries. There is a lack of standardisation of clinical evaluation of VR, both in terms of clinical trials and implementation science. While all VR illustrated face and content validity, only around two-third exhibited construct validity and predictive validity was lacking overall. In conclusion, the asynchrony between VR development and actual global cancer surgery demand means the technology is not effectively, efficiently and equitably utilised to realise its surgical capacity-building potential. Future research should prioritise cost-effective VR technologies with predictive validity for high demand, open cancer surgeries required in LMICs.

Outcomes of Artificial Intelligence Volumetric Assessment of Kidneys and Renal Tumors for Preoperative Assessment of Nephron Sparing Interventions

Background Renal cell carcinoma is the most common kidney cancer and the 13th most common cause of cancer death worldwide. Partial nephrectomy and percutaneous ablation, increasingly utilized to treat small renal masses and preserve renal parenchyma, require precise preoperative imaging interpretation. We sought to develop and evaluate a convolutional neural network (CNN), a type of deep learning artificial intelligence, to act as a surgical planning aid by determining renal tumor and kidney volumes via segmentation on single-phase computed tomography (CT). Materials and Methods After institutional review board approval, the CT images of 319 patients were retrospectively analyzed. Two distinct CNNs were developed for (1) bounding cube localization of the right and left hemi-abdomen and (2) segmentation of the renal parenchyma and tumor within each bounding cube. Training was performed on a randomly selected cohort of 269 patients. CNN performance was evaluated on a separate cohort of 50 patients using Sorensen-Dice coefficients (which measures the spatial overlap between the manually segmented and neural network derived segmentations) and Pearson correlation coefficients. Experiments were run on a GPU-optimized workstation with a single NVIDIA GeForce GTX Titan X (12GB, Maxwell architecture). Results Median Dice coefficients for kidney and tumor segmentation were 0.970 and 0.816, respectively; Pearson correlation coefficients between CNN-generated and human-annotated estimates for kidney and tumor volume were 0.998 and 0.993 (p < 0.001), respectively. End-to-end trained CNNs were able to perform renal parenchyma and tumor segmentation on a new test case in an average of 5.6 seconds. Conclusions Initial experience with automated deep learning artificial intelligence demonstrates that it is capable of rapidly and accurately segmenting kidneys and renal tumors on single-phase contrast-enhanced CT scans and calculating tumor and renal volumes.