The basic principle of automated histopathologic image analysis is the use of a series of mathematical algorithms that process images, enabling the segmentation of picture elements into regions of interest based on their color, texture, and/or context.
Consists of a cloud based deep learning solution for image segmentation of light, electron and X-ray microscopy. CDeep3M serves for image segmentation tasks of large and complex 2D and 3D microscopy datasets by taking advantage of the underlying architecture of a deep learning convolutional neural network (CNN) called DeepEM3D. This software is also available on the Amazon Web Services (AWS) platform.
Recognizes cell in microscopic images. GemIdent supports standard RGB images, for image sets derived from the Bacus Laboratories Incorporated Slide Scanner and the CRI Nuance Multispectral Imager. It allows users to analyze multispectral images where the chromatic markers are separated a priori. This tool uses density estimation to compute scores in the unidimsensional space of the fluorescent layer intensity images.
Detects patch-based carcinoma in confocal laser endomicroscopy (CLE) images. This patch probability fusion method that can provide additional real-time information about the suspicious lesion, supportive to the clinical examination. The software can serve as an additional tool supporting the biopsy and the following histopathological examination. It was applied on CLE images of oral squamous cell carcinoma (OSCC).
Calculates the stained areas in a Masson Trichrome stained slide as well as the adipose tissue area. FibroQuant is a method for systematic high resolution digital quantification of different tissue types in the heart. This method of fibrosis quantification can be used for several applications like the determination of the fibrosis pattern in the heart could provide an important link for genotype-phenotype relationships in genetic cardiomyopathies.
Assists in cell nuclei counting and staining estimation of accurate immunohistochemical (IHC)‑stained tissue slices and tissue microarrays (TMAs). TMARKER is a toolkit suitable for cancer cell nucleus setection, segmentation, counting, and classification (malignant/benign and stained/unstained). The software uses a superpixel‑based approach for classification. One of its advantages is the reproducibility of competitive cell counts.
You can access more results by creating a free plan account or unlimited content via a premium account.