Improving On-Patient Medical Data Visualization in a Markerless Augmented Reality Environment by Volume Clipping

Macedo, Márcio C. F.; Apolinário, Antônio L.

doi:10.1109/sibgrapi.2014.33

Cited by 10 publications

(11 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In surface-based registration techniques [2][3][4][5][6], a tablet-PC is mounted with a range camera, RGB-D sensor or stereo-vision to continuously capture the depth and color information, from which the skin surface is automatically extracted. This surface is then registered with the P3DM acquired from CT images, typically ICP (iterative closest point) is used.…”

Section: On-patient Ar Visualizationmentioning

confidence: 99%

“…This surface is then registered with the P3DM acquired from CT images, typically ICP (iterative closest point) is used. This process is repeated for every frame at 5-10 Hz [4]. The major drawbacks of this type of techniques are the computation cost of depth image segmentation and ICP.…”

Section: On-patient Ar Visualizationmentioning

confidence: 99%

“…Third, this kind of methods are not robust to partial occlusions of the skin. To achieve real-time performance, either parallel processing [4] or client/server architecture [6] or both [2] are used: A powerful server PC is necessary to process data, and the tablet-PC is used as a display tool only.…”

Section: On-patient Ar Visualizationmentioning

confidence: 99%

“…Indeed, markers are likely to be occluded by surgeon hand or a surgical instruments. Moreover, current on-patient visualization techniques typically evaluate their accuracy by measuring the registration errors of skin fiducials [2,3,5,6], the discrepancy in pixels in the image [8,10] and/or the processing time [4]. To address these drawbacks, a VSLAM-based method for on-patient visualization is proposed.…”

Section: On-patient Ar Visualizationmentioning

confidence: 99%

See 3 more Smart Citations

On-patient see-through augmented reality based on visual SLAM

et al. 2016

View full text Add to dashboard Cite

show abstract

Section: On-patient Ar Visualizationmentioning

confidence: 99%

Section: On-patient Ar Visualizationmentioning

confidence: 99%

Section: On-patient Ar Visualizationmentioning

confidence: 99%

Section: On-patient Ar Visualizationmentioning

confidence: 99%

See 2 more Smart Citations

On-patient see-through augmented reality based on visual SLAM

et al. 2016

View full text Add to dashboard Cite

show abstract

“…Some of them do not run in real-time (more than 15 frames per second, FPS) [9,10] and others rely on specific prior knowledge about the ROI to be tracked (see [11][12][13] for the body and [14] for the face). To the best of our knowledge, there is only one exception which can be used for general-purpose markerless on-patient medical data visualization: the semiautomatic approach proposed in [15][16][17].…”

Section: Related Workmentioning

confidence: 99%

Focus plus context visualization based on volume clipping for markerless on-patient medical data visualization

Macedo

Apolinário

2015

Computers & Graphics

View full text Add to dashboard Cite

a b s t r a c tFocus plus context visualization can be used in augmented reality to improve the visual perception of the augmented scene. In the scope of in situ or on-patient medical data visualization, the focus plus context paradigm is used to improve depth perception for physicians showing the patient's anatomy as a focus region in the context of the patient's body. Volume clipping is one technique to realize focus plus context visualization. However, some of the existing methods for focus plus context visualization based on volume clipping do not run in full real time or are prone to artifacts. In this paper, we present an extension for two of these techniques to improve performance and image quality of the original approaches. We validate all the techniques in a markerless augmented reality environment. A 3D reference model is tracked by the application, and volumetric medical data are shown to the user at the position of the patient's anatomy. Our technique is able to handle multiple anatomic regions, although the main region of interest used in this paper is the face. Moreover, tracking accuracy is improved by the use of a hierarchical approach. From an evaluation of the proposed techniques, the results obtained highlight that all of them are free of artifacts, optimized for real-time performance, and improve the visual quality of the augmented scene.

show abstract