Evaluation of Increasing Camera Baseline on Depth Perception in Surgical Robotics

Avinash, Apeksha; Abdelaal, Alaa Eldin; Salcudean, Septimiu E.

doi:10.1109/icra40945.2020.9197235

Cited by 6 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The PSMNet model used herein was finetuned with endoscopic data from the SCARED dataset specifically because the majority of the existing datasets for training CNN models are developed for non-surgical domains imaged with widebaseline stereo rigs. In autonomous driving, for example, typical baseline to scene depth ratios are 0.6-1.0, whereas in robotic surgery this value is closer to 0.1 [17][18][19]. Interestingly, SCARED finetuning was initially observed to have minimal effect on reconstruction accuracy which warrants further investigation.…”

Section: Resultsmentioning

confidence: 97%

Evaluating a PSMNet-based pipeline for intraoperative stereo reconstruction with the da Vinci Xi

Kokko

Andersen

Halter

2023

Medical Imaging 2023: Image-Guided Procedures, Robotic Interventions, and Modeling

View full text Add to dashboard Cite

Stereo reconstruction is an important tool for generating 3D surface observations of deformable tissues that can be used to non-rigidly update intraoperative image guidance. As compared to traditional image processing-based stereo matching techniques, emerging machine learning approaches aim to deliver shorter processing times, more accurate surface reconstructions, and greater robustness to the suboptimal qualities of intraoperative tissue imaging (e.g., occlusion, reflection, and minimally textured surfaces). This work evaluates the popular PSMNet convolutional neural network as tool for generating disparity maps from the video feed of the da Vinci Xi Surgical System. Reconstruction accuracy and speed were assessed for a series of 44 stereoendoscopic frame pairs showing key structures in a silicone renal phantom. Surface representation accuracy was found to be on the order of 1mm for reconstructions of the kidney and inferior vena cava, and disparity maps were produced in under 2s when inference was performed on a standard modern GPU. These preliminary results suggest that PSMNet and similar trained models may be useful tools for integrating intraoperative stereo reconstruction into advanced navigation platforms and warrant further development of the overall data pipeline and testing with biological tissues in representative surgical conditions.

show abstract

Section: Resultsmentioning

confidence: 97%