Tissue Germination Evaluation on Implants Based on Shearlet Transform and Color Coding

Зотин, А. Г.; Simonov, Konstantin; Капсаргин, Ф. П.; Cherepanova, Tatyana; Kruglyakov, Alexey

doi:10.1007/978-3-030-33795-7_9

Cited by 10 publications

(1 citation statement)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When using variations of Retinex the output image was formed by applying the BCET algorithm to the response, stretching the range taking into account the standard deviation and linear stretching with a multiplier. The formation of the color representation is based on the use of the Shearlet transform and color coding of objects of interest (Zotin et al, 2020).…”

Section: Description Of the Processing Methodsmentioning

confidence: 99%

Intraoperative Visualization of Anatomical Structures in Massive Bleeding Using Infrared Images

Medievsky

Зотин

Simonov

et al. 2023

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. One of the most dangerous complications during brain surgery is bleeding. Hemostasis can be difficult due to the lack of visibility caused by blood filling the surgical wound. To restore the visibility of the surgical area it is proposed to use NIR-camera data and Shearlet transform with color-coding algorithms. At the same time it is also assumed to conduct brightness characteristics enhancement of images (frames) and segmentation of biological tissues of interest. NIR beams are able to penetrate deeper into tissues than visible light and NIR is also absorbed to a greater extent by hemoglobin than by surrounding tissues. The blood has a significantly higher absorption coefficient of NIR rays in the range from 800 nm to 1050 nm in comparison with the absorption coefficient of the same spectrum by the tissues involved during the operation. Due to this effect there is the potential to detect structures of interest despite bleeding in the wound cavity. During experimental study it was found that it becomes possible to visualize all tissues that are at a depth of up to 3 mm. Use of BCET algorithm with the mask for processing made it possible to improve the image contrast from 34.20% to 198.73% depending on the depth of biological structures. In case of model images processing the best average accuracy of determining ROI contours taking into account depth was 0.961 ± 0.021 according Dice similarity coefficient.

show abstract

Section: Description Of the Processing Methodsmentioning

confidence: 99%