Kidney edge detection in laparoscopic image data for computer-assisted surgery

Hattab, Georges; Arnold, Marvin; Strenger, Leon; Allan, Max; Arsentjeva, Darja; Gold, Oliver; Simpfendörfer, Tobias; Maier-Hein, Lena; Speidel, Stefanie

doi:10.1007/s11548-019-02102-0

Cited by 22 publications

(23 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yet kidneys are involved in up to 20% of severe abdominal trauma cases and up to 14% of chronic kidney disease 6 – 8 . This motivates ways to acquire accurate data pertaining to its mechanical properties to help identify mechanisms of injury and/or validate computer vision based systems 9 for assisted or guided surgery.…”

Section: Introductionmentioning

confidence: 99%

Uniaxial compression testing and Cauchy stress modeling to design anatomical silicone replicas

Hattab

Ahlfeld²,

Klimová

et al. 2020

Sci Rep

Self Cite

View full text Add to dashboard Cite

Anatomically realistic organ replicas or phantoms allow for accurate studies and reproducible research. To recreate a human kidney, mimicry of the elastic properties of the human kidney is crucial. However, none of the related work addressed the design and development of a kidney phantom using only silicone as material. In contrast to paraffin and hydrogel, silicone is an ideal variant for its extended shelf life, soft-tissue-like feeling, and viscoelastic modularity. To this end, we conducted Uniaxial Compression testing and Cauchy stress modeling. Results indicate that none of the available manufacturer silicone brands are suitable for the task of creating a realistic kidney phantom. Indeed, the tested silicone mixtures in low and high strain fall outside the required approximate target compressive moduli of 20 kPa and 500 kPa, respectively. This work provides a frame of reference for future work by avoiding the pitfalls of the selected ready-made silicones and reusing the reported theoretical and experimental setup to design a realistic replica of the kidney organ.

show abstract

Section: Introductionmentioning

confidence: 99%

Uniaxial compression testing and Cauchy stress modeling to design anatomical silicone replicas

Hattab

Ahlfeld²,

Klimová

et al. 2020

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…• Kidney boundaries: We use this data set as is [12]. It consists of 2,250 images captured during porcine partial nephrectomies and for the task of kidney edge detection.…”

Section: Data Setsmentioning

confidence: 99%

“…However, these works provide all edges of an image and the task of filtering out non-relevant edge remains. The extraction of task-relevant edges, called semantic edges, is an active research topic across many research fields [10,11,12]. A graph-based solution was introduced by stitching together appropriate edge fragments to produce a closed or linked object boundary [13].…”

Section: Introductionmentioning

confidence: 99%

“…For minimally invasive surgery, and specifically laparoscopic image data, the task of semantic segmentation has proven challenging due to different limiting factors (e.g., the occlusion by fatty tissue or surgical instruments, or the homogeneity of the texture of the target organ) [16]. In our proposed deep learning based edge detector [12], the neural net predicts kidney boundaries that are then post-processed into 1 pixel wide edges. In this work, the specific edge location is determined by a confidence value, that is represented by the pixel intensity within the predicted boundary.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Towards Improving Edge Quality using Combinatorial Optimization and a Novel Skeletonize Algorithm

Arnold

Hattab

Speidel

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Background: Object detection and image segmentation of regions of interest provide the foundation for numerous pipelines across disciplines. Robust and accurate computer vision methods are needed to properly solve image-based tasks. Multiple algorithms have been developed to solely detect edges in images. Constrained to the problem of creating a thin, one-pixel wide, edge from a predicted object boundary, we require an algorithm that removes pixels while preserving the topology. Thanks to skeletonize algorithms, an object boundary is transformed into an edge; contrasting uncertainty with exact positions.Methods: To extract edges from boundaries generated from different algorithms, we present a computational pipeline that relies on: a novel skeletonize algorithm, a non-exhaustive discrete parameter search to find the optimal parameter combination of a specific post-processing pipeline, and an extensive evaluation using three data sets from the medical and natural image domains (kidney boundaries, NYU-Depth V2, BSDS 500). While the skeletonize algorithm was compared to classical topological skeletons, the validity of our post-processing algorithm was evaluated by integrating the original post-processing methods from six different works.Results: Using the state of the art metrics, precision and recall based Signed Distance Error (SDE) and the Intersection over Union bounding box (IOU-box), our results indicate that the SDE metric for these edges is improved up to 2.3 times.Conclusions: Our work provides guidance for parameter tuning and algorithm selection in the post-processing of predicted object boundaries.

show abstract

“…Moreover, recent studies indicate that optical imaging is also improved through deep learning algorithms [22][23][24][25][26]. This article proposes a proof-of-concept simulation model to enhance imaging through scattering media using multiple vortex beams and convoluted neural networks.…”

Section: Introductionmentioning

confidence: 99%

Detecting objects behind scattering media using vortex beams and deep learning

Balasubramaniam

Biton

Arnon

2021

Preprint

View full text Add to dashboard Cite

Reconstructing objects behind scattering media is a challenging issue with applications in biomedical imaging, non-distractive testing, computer-assisted surgery, and autonomous vehicular systems. Such systems’ main challenge is the multiple scattering of the photons in the angular and spatial domain, which results in a blurred image. Previous works try to improve the reconstructing ability using deep learning algorithms, with some success. We enhance these methods by illuminating the set-up using several modes of vortex beams obtaining a series of time-gated images corresponding to each mode. The images are accurately reconstructed using a deep learning algorithm by analyzing the pattern captured in the camera. This study shows that using vortex beams instead of Gaussian beams enhances the deep learning algorithm’s image reconstruction ability in terms of the peak signal-to-noise ratio (PSNR) by ~ 2.5 dB and ~1 dB when low and high scattering scatterers are used respectively.

show abstract

Kidney edge detection in laparoscopic image data for computer-assisted surgery

Cited by 22 publications

References 19 publications

Uniaxial compression testing and Cauchy stress modeling to design anatomical silicone replicas

Uniaxial compression testing and Cauchy stress modeling to design anatomical silicone replicas

Towards Improving Edge Quality using Combinatorial Optimization and a Novel Skeletonize Algorithm

Detecting objects behind scattering media using vortex beams and deep learning

Contact Info

Product

Resources

About