A particle filter approach to dynamic kidney pose estimation in robotic surgical exposure

Kokko, Michael A.; Citters, Douglas W. Van; Seigne, John D.; Halter, Ryan J.

doi:10.1007/s11548-022-02638-8

Cited by 5 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, some open-source frameworks have been proposed to facilitate the implementation and application of medical image segmentation methods for researchers and clinicians who lack experience in this field. For example, NiftyNet [ 66 ] is a TensorFlow-based framework that can perform segmentation on CT images; MIScnn [ 67 ] is a Python--based framework that supports state-of-the-art deep learning models for medical image segmentation; and 3DSlicer [ 34 , 35 , 68 ] is a software platform that can deal with 3D data or render 2D data into 3D.…”

Section: Resultsmentioning

confidence: 99%

“…Tracking Registration [22] Yes No ICP [23] 3D Slicer OTS Surface-matching [24] Learning-based No ICP [25] No Learning-based Learning-based [26] Learning-based No No [27,28] Yes OTS Fiducial markers [29] Threshold/Region growing OTS ICP [30] Region growing Visual-inertial stereo slam ICP [31] Threshold Learning-based Super4PCS [32] [33] Yes OTS ICP [34] 3D Slicer EMT Fiducial markers [35] Mimics 6 OTS Anatomical landmark [36] Manual No ICP [37] No Depth estimation Learning-based [38] [39] EndoSize 6 No Rigid intensity-based [40] Yes EMT ICP [41] Threshold OTS ICP [42] 3D Slicer/Learning-based No ICP and CPD 5 [43] Yes Visual SLAM Visual SLAM 1 EMT: electromagnetic tracker. 2 PDM: Philips Disease Management.…”

Section: Paper Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Modern Image-Guided Surgery: A Narrative Review of Medical Image Processing and Visualization

Lin,

Lei,

Yang

2023

Sensors

View full text Add to dashboard Cite

Medical image analysis forms the basis of image-guided surgery (IGS) and many of its fundamental tasks. Driven by the growing number of medical imaging modalities, the research community of medical imaging has developed methods and achieved functionality breakthroughs. However, with the overwhelming pool of information in the literature, it has become increasingly challenging for researchers to extract context-relevant information for specific applications, especially when many widely used methods exist in a variety of versions optimized for their respective application domains. By being further equipped with sophisticated three-dimensional (3D) medical image visualization and digital reality technology, medical experts could enhance their performance capabilities in IGS by multiple folds. The goal of this narrative review is to organize the key components of IGS in the aspects of medical image processing and visualization with a new perspective and insights. The literature search was conducted using mainstream academic search engines with a combination of keywords relevant to the field up until mid-2022. This survey systemically summarizes the basic, mainstream, and state-of-the-art medical image processing methods as well as how visualization technology like augmented/mixed/virtual reality (AR/MR/VR) are enhancing performance in IGS. Further, we hope that this survey will shed some light on the future of IGS in the face of challenges and opportunities for the research directions of medical image processing and visualization.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Paper Segmentationmentioning

confidence: 99%

Modern Image-Guided Surgery: A Narrative Review of Medical Image Processing and Visualization

Lin,

Lei,

Yang

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…There has also been a report of extracting feature points from the surgical field, capturing them as a 3D point cloud through Structure from Motion (SfM), and tracking them, but no mention was made of registration with the 3D kidney model [52] . Zhang et al used Semi-Global Block Matching (SGBM) to extract 3D point clouds from stereo image disparity [53] . They also used a deep learning method, Mask Region-based CNN (Mask R-CNN), for kidney segmentation to assist with 3D point cloud extraction.…”

Section: Other Registration Innovationsmentioning

confidence: 99%

Current status and challenges of 3D navigation in partial nephrectomy

Magaribuchi,

Masui,

Goto

et al. 2024

Mini-invasive Surg

View full text Add to dashboard Cite

Partial nephrectomy, a standard treatment for small renal cancers, has evolved through minimally invasive procedures such as laparoscopic and robot-assisted partial nephrectomy. The use of three-dimensional (3D) kidney models derived from preoperative computed tomography (CT) images has been investigated to improve surgical outcomes. This review explores various navigation techniques, such as 3D printing, virtual reality (VR), and augmented reality (AR), to address organ movement and deformation challenges during surgery. Despite the promising positive impact of these methods, as revealed by a systematic review in 2022, achieving the desired navigation accuracy remains elusive. The use of Virtual Reality and Augmented Reality, capable of overlaying the 3D model onto the surgical image in real-time, has shown potential. Still, we need advanced techniques, for instance, non-rigid 3D models employing nonlinear parametric deformation, to adapt to organ deformation. Additionally, the application of deep learning from artificial intelligence for high accuracy 3D navigation is an emerging area of interest. Although considerable progress has been achieved, a comprehensive, widely adoptable solution has yet to be discovered. The paper underscores the necessity for ongoing research and development in 3D navigation methods, anticipating their substantial contribution to future surgical procedures.

show abstract

“…Image guidance for laparoscopic procedures performed in the presence of significant tissue deformation and displacement remains an active research topic both in the clinical and technical literature [1][2][3][4]. In less dynamic environments, preoperative imaging can be rigidly registered to the surgical field via externally-visible landmarks or discrete fiducials relative to which the internal anatomy of interest can be assumed stationary.…”

Section: Introductionmentioning

confidence: 99%

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

Self Cite

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

A particle filter approach to dynamic kidney pose estimation in robotic surgical exposure

Cited by 5 publications

References 34 publications

Modern Image-Guided Surgery: A Narrative Review of Medical Image Processing and Visualization

Modern Image-Guided Surgery: A Narrative Review of Medical Image Processing and Visualization

Current status and challenges of 3D navigation in partial nephrectomy

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

Contact Info

Product

Resources

About