Comparison of different spectral cameras for image-guided organ transplantation

Mühle, Richard; Markgraf, Wenke; Hilsmann, Anna; Malberg, Hagen; Eisert, Peter; Wisotzky, Eric L.

doi:10.1117/1.jbo.26.7.076007

Cited by 11 publications

(19 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the statement, that ischemia has a relevant impact on graft injury, monitoring of oxygen supply might provide a potential marker for assessment and early identification of functional limitations, particularly in case of marginal organs [30]. Hence, HSI may contribute to ease the decision-making process whether an organ is suitable for transplantation or not, by providing additional valuable information on perfusion quality and graft viability [3,25,[33][34][35].…”

Section: Discussionmentioning

confidence: 99%

“…The digitization of pre-and intraoperatively imaging procedures offers the possibility of both the real-time analysis of acquired image data during the medical procedure and the visualization of the automatically extracted information for the surgeon [3]. In this way, space-and time-resolved imaging of clinical-relevant information, such as tissue type, or potential structures at risk are obtained during surgery.…”

Section: Spectral Cameras For Image-guided Organ Transplantationmentioning

confidence: 99%

“…The hyperspectral snapshot imager captures x, y, and lambda in the same sensor read out. The data cube is taken at once without any timely offset [3]. HSI has been evaluated as an additional technique in order to measure tissue physiology, morphology, and composition [17].…”

Section: Spectral Cameras For Image-guided Organ Transplantationmentioning

confidence: 99%

“…Due to its capacity to capture ultraviolet and infrared wavelength spectra and based on the absorption/reflectance of the analyzed tissue, HSI acquires two-dimensional spatial images, ultimately formed into a three-dimensional data set called the hypercube [18]. This technique can be used to monitor the physiologically relevant tissue parameters, operating among other spectral ranges in the region of the optical window where the most relevant absorbers are melanin, lipids, water, and hemoglobin [3,17]. Subsequent imaging procedures generate pictures of the chemical tissue composition indicating the oxygen saturation (StO 2 ), tissue perfusion (near-infrared perfusion index, NIR), tissue hemoglobin index (THI), and tissue water index (TWI) [19].…”

Section: Spectral Cameras For Image-guided Organ Transplantationmentioning

confidence: 99%

“…Due to the lack of an accurate predictive organ evaluation strategy, certain organs were rejected although they would still have been suitable for transplantation. The decision to accept or reject an organ for transplantation depends primarily on the expertise of the transplant team rather than on an objective measurement [3]. Therefore, optical evaluation tools to monitor organ quality before transplantation would be of great interest.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Hyperspectral Imaging and Machine Perfusion in Solid Organ Transplantation: Clinical Potentials of Combining Two Novel Technologies

Fodor

Hofmann

Lanser

et al. 2021

JCM

View full text Add to dashboard Cite

Organ transplantation survival rates have continued to improve over the last decades, mostly due to reduction of mortality early after transplantation. The advancement of the field is facilitating a liberalization of the access to organ transplantation with more patients with higher risk profile being added to the waiting list. At the same time, the persisting organ shortage fosters strategies to rescue organs of marginal donors. In this regard, hypothermic and normothermic machine perfusion are recognized as one of the most important developments in the modern era. Owing to these developments, novel non-invasive tools for the assessment of organ quality are on the horizon. Hyperspectral imaging represents a potentially suitable method capable of evaluating tissue morphology and organ perfusion prior to transplantation. Considering the changing environment, we here discuss the hypothetical combination of organ machine perfusion and hyperspectral imaging as a prospective feasibility concept in organ transplantation.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Spectral Cameras For Image-guided Organ Transplantationmentioning

confidence: 99%

Section: Spectral Cameras For Image-guided Organ Transplantationmentioning

confidence: 99%

Section: Spectral Cameras For Image-guided Organ Transplantationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Hyperspectral Imaging and Machine Perfusion in Solid Organ Transplantation: Clinical Potentials of Combining Two Novel Technologies

Fodor

Hofmann

Lanser

et al. 2021

JCM

View full text Add to dashboard Cite

show abstract

Hyperspectral Demosaicing of Snapshot Camera Images Using Deep Learning

Wisotzky

Daudkane

Hilsmann

et al. 2022

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Spectral imaging technologies have rapidly evolved during the past decades. The recent development of single-camera-one-shot techniques for hyperspectral imaging allows multiple spectral bands to be captured simultaneously (3 × 3, 4 × 4 or 5 × 5 mosaic), opening up a wide range of applications. Examples include intraoperative imaging, agricultural field inspection and food quality assessment. To capture images across a wide spectrum range, i.e. to achieve high spectral resolution, the sensor design sacrifices spatial resolution. With increasing mosaic size, this effect becomes increasingly detrimental. Furthermore, demosaicing is challenging. Without incorporating edge, shape, and object information during interpolation, chromatic artifacts are likely to appear in the obtained images. Recent approaches use neural networks for demosaicing, enabling direct information extraction from image data. However, obtaining training data for these approaches poses a challenge as well. This work proposes a parallel neural network based demosaicing procedure trained on a new ground truth dataset captured in a controlled environment by a hyperspectral snapshot camera with a 4 × 4 mosaic pattern. The dataset is a combination of real captured scenes with images from publicly available data adapted to the 4 × 4 mosaic pattern. To obtain real world ground-truth data, we performed multiple camera captures with 1-pixel shifts in order to compose the entire data cube. Experiments show that the proposed network outperforms state-of-art networks.

show abstract