Abstract:, "Gray-level co-occurrence matrix analysis of several cell types in mouse brain using resolution-enhanced photothermal microscopy," J. Biomed. Opt. 22(3), 036011 (2017), doi: 10.1117/1.JBO.22.3.036011. Abstract. Qualifications of intracellular structure were performed for the first time using the gray-level co-occurrence matrix (GLCM) method for images of cells obtained by resolution-enhanced photothermal imaging. The GLCM method has been used to extract five parameters of texture features for five different … Show more
“…Second-order statistics study the texture through the spatial relationship between pairs of pixels [ 25 , 39 , 40 ]. To obtain these values, the spatial co-occurrence between pixel pairs is gathered through the gray-level co-occurrence matrix (GLCM) [ 41 ]. From the GLCM, up to fourteen parameters can be calculated to measure texture [ 25 , 40 ].…”
Section: Methodsmentioning
confidence: 99%
“…However, only seven provide essential information [ 39 ]. Hence, the used second-order statistics were: entropy, contrast, homogeneity, dissimilarity, angular second moment (ASM), energy, and correlation [ 25 , 41 ].…”
Endometriosis is a gynecological pathology that affects between 6 and 15% of women of childbearing age. One of the manifestations is intestinal deep infiltrating endometriosis. This condition may force patients to resort to surgical treatment, often ending in resection. The level of blood perfusion at the anastomosis is crucial for its outcome, for this reason, indocyanine green (ICG), a fluorochrome that green stains the structures where it is present, is injected during surgery. This study proposes a novel method based on deep learning algorithms for quantifying the level of blood perfusion in anastomosis. Firstly, with a deep learning algorithm based on the U-Net, models capable of automatically segmenting the intestine from the surgical videos were generated. Secondly, blood perfusion level, from the already segmented video frames, was quantified. The frames were characterized using textures, precisely nine first- and second-order statistics, and then two experiments were carried out. In the first experiment, the differences in the perfusion between the two-anastomosis parts were determined, and in the second, it was verified that the ICG variation could be captured through the textures. The best model when segmenting has an accuracy of 0.92 and a dice coefficient of 0.96. It is concluded that segmentation of the bowel using the U-Net was successful, and the textures are appropriate descriptors for characterization of the blood perfusion in the images where ICG is present. This might help to predict whether postoperative complications will occur during surgery, enabling clinicians to act on this information.
“…Second-order statistics study the texture through the spatial relationship between pairs of pixels [ 25 , 39 , 40 ]. To obtain these values, the spatial co-occurrence between pixel pairs is gathered through the gray-level co-occurrence matrix (GLCM) [ 41 ]. From the GLCM, up to fourteen parameters can be calculated to measure texture [ 25 , 40 ].…”
Section: Methodsmentioning
confidence: 99%
“…However, only seven provide essential information [ 39 ]. Hence, the used second-order statistics were: entropy, contrast, homogeneity, dissimilarity, angular second moment (ASM), energy, and correlation [ 25 , 41 ].…”
Endometriosis is a gynecological pathology that affects between 6 and 15% of women of childbearing age. One of the manifestations is intestinal deep infiltrating endometriosis. This condition may force patients to resort to surgical treatment, often ending in resection. The level of blood perfusion at the anastomosis is crucial for its outcome, for this reason, indocyanine green (ICG), a fluorochrome that green stains the structures where it is present, is injected during surgery. This study proposes a novel method based on deep learning algorithms for quantifying the level of blood perfusion in anastomosis. Firstly, with a deep learning algorithm based on the U-Net, models capable of automatically segmenting the intestine from the surgical videos were generated. Secondly, blood perfusion level, from the already segmented video frames, was quantified. The frames were characterized using textures, precisely nine first- and second-order statistics, and then two experiments were carried out. In the first experiment, the differences in the perfusion between the two-anastomosis parts were determined, and in the second, it was verified that the ICG variation could be captured through the textures. The best model when segmenting has an accuracy of 0.92 and a dice coefficient of 0.96. It is concluded that segmentation of the bowel using the U-Net was successful, and the textures are appropriate descriptors for characterization of the blood perfusion in the images where ICG is present. This might help to predict whether postoperative complications will occur during surgery, enabling clinicians to act on this information.
“…Each block, across all images, was analysed for texture by using a modi ed method of extracting Haralick features from the Gray Level Co-Occurrence Matrix (GLCM) [19]. LCM based texture measures provide information related to the local spatial relationships of gray levels in an image and have previously been successfully applied in a number of medical imaging modalities [19][20][21][22][23]. One of the challenges in the standard application of the GLCM is the dependence on rotation and spatial offset, which is pertinent to this study.…”
Infantile fibrosarcoma is a rare childhood tumour that originates in the fibrous connective tissue of the long bones for which there is an urgent need to identify novel therapeutic targets. This study aims to clarify the role of the extracellular matrix component Hyaluronan in the invasion of child fibroblasts and Infantile fibrosarcoma into the surrounding environment. Using nanoscale super-resolution STED microscopy followed by computational image analysis, we observed, for the first time, that metastasising child fibroblasts showed increased nanoscale clustering of Hyaluronan at the cell periphery, as compared to control cells. Hyaluronan was not observed within focal adhesions. Bioinformatic analyses further revealed that the increased nanoscale Hyaluronan clustering was accompanied by increased gene expression of Hyaluronan synthase 2, reduced expression of Hyaluronidase 2 and CD44, and no change of Hyaluronan synthase 1 and Hyaluronidases 1, 3, 4, 5. We further observed that the expression of the Hyaluronan synthase 1, 2 and 3, and the Hyaluronidase 3 and 5 genes was linked to reduced life expectancy of fibrosarcoma patients. The invasive front of infantile fibrosarcoma tumours further showed increased levels of Hyaluronan, as compared to the tumour centre. Taken together, our findings are consistent with the possibility that while Hyaluronan 2 increases the levels, the Hyaluronidases 3 and 5 reduce the weight of Hyaluronan, resulting in the nanoscale clustering of Hyaluronan at the leading edge of cells, cell invasion and the spread of Infantile fibrosarcoma.
“…Gray level co-occurrence matrix [23] is a statistical method for extracting texture features from digital images through calculating the spatial relationship of each image pixel. The implemented method is based on the joint conditional probability density among image grayscale levels, whose function is:…”
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.