Advanced searches left 3/3

Skin Cancer - Astrophysics Data System

Summarized by Plex Scholar
Last Updated: 27 April 2022

* If you want to update the article please login/register

From the Cover: Control of skin cancer by the circadian rhythm

Skin cancer is the most common form of cancer in the United States. Mice exposed to UV radiation at 4:00 p. m. increased latency and about a fivefold increased multiplicity of skin cancer than mice exposed to UV radiation at 4:00 p. m. , in parallel with the regularity of repair rates.

Source link: https://ui.adsabs.harvard.edu/abs/2011PNAS..10818790G/abstract


Optimization of measurement mode and sample processing for FTIR microspectroscopy in skin cancer research

Because of its ability to collect spatially resolved data at the molecular level, the use of Fourier Transform Infrared microspectroscopy to study cancerous cells and tissues has gained traction. The tissue samples tested in these modes are often paraffinized or deparaffinized, and transmission and transflection are the most commonly used measurement techniques for FTIR microspectroscopy. This research compares the spectra of primary and metastatic melanoma cell lines obtained in both transmission and transflection modes, with paraffinized and deparaffinized samples to determine the correct mixture for accurate classification. Both modes and sample processing options are useful for distinguishing cultured cell samples using supervised multivariate analysis, as shown by the PLS-DA model built for the classification of two cell lines in each case. Regardless of mode or sample type used, the biochemical data in the cells capable of distinguishing two melanoma cell lines is present.

Source link: https://ui.adsabs.harvard.edu/abs/2022Ana...147..851S/abstract


Detection of skin cancer image based on convolutional neural network model and website application

Convolutional neural networks are mainly used for image processing, classification, and segmentation, as well as finding skin cancer. However, some current CNN models used to assess skin cancer in a variety of ways other than images of skin lesions. The paper suggested a new but simple CNN model to tackle this problem. Using image classification, it can be used to find and distinguish benign and malignant skin cancer at the patients' end. We present a single CNN model that was trained end-to-end from real skin lesion images directly in this paper. We used Claudio Fancon's malignant vs. benign skin cancer dataset. The public ISIC 2018 Skin Lesion Dataset has a gallery. We start with a multiple-layer CNN model and track it on all the data. Wen, we develop a multi-layer CNN model and train it on all the data. This could help to minimize human mistakes in the skin cancer diagnosis process.

Source link: https://ui.adsabs.harvard.edu/abs/2022SPIE12168E..0TD/abstract


Hydrogels as promising therapeutic strategy for the treatment of skin cancer

Skin cancer, such as melanoma and non-melanoma, is the most common disease in white populations. Hydrogels can be used as reusable platforms, and local therapy plans can play a vital role in skin cancer treatment, and hydrogels can be used as reusable platforms. The biggest issue with common melanoma chemotherapy is the strong side effects, because neoplastic factors do not recognize cancer cells from healthy cells. The discovery of novel therapies for cancer cells is fueled by the side effects of standard drugs. Hydrogel has been used for tissue engineering scaffolds, wound dressings, and drug delivery systems in recent years. These percutaneous drug delivery systems are a promising alternative to intra-neoplastic agents' delivery systems in order to avoid side effects. The aim of this article is to highlight some of the latest advancements in the use of hydrogels for the treatment of skin cancer.

Source link: https://ui.adsabs.harvard.edu/abs/2022JMoSt126233014M/abstract


Detection of face skin cancer using deep convoluted neural network

With increasing global warming, the incidence of cancers, particularly skin cancer, is on the rise. Skin cancer is often confused with moles and other skin tags, and therefore is detected at a very early stage later on. Image processing has gained traction over the past few years, and Image processing has employed advanced techniques that shrink an image to its minute constituents. Fuzzy C means classification is used for segmentation because it has higher accuracy than K means and can segment each pixel with high accuracy, which can be used for segmentation. The image's lesion in the picture is cancerous or not, according to a non-knowledge based classification system, it would be used to determine whether the lesion is cancerous or not. As the activation function is enabled, BPN's model with a radial basis function is introduced. An image set with 3000 photos will be used to prepare the model with additional 2000 images for testing.

Source link: https://ui.adsabs.harvard.edu/abs/2022AIPC.2405b0003N/abstract


Prospects for Terahertz Imaging the Human Skin Cancer with the Help of Gold-Nanoparticles-Based Terahertz-to-Infrared Converter

An instrument to detect a skin cancer tumor in the terahertz range is suggested, as well as potential operation parameters, for a skin cancer tumor in the terahertz range, transforming the photograph into the infrared and making it visible with the aid of a standard IR camera. It is likely that the biological tissue sample would be irradiated using an external THz source.

Source link: https://ui.adsabs.harvard.edu/abs/2019fane.book..151P/abstract


Synergistic effect of plasma-activated medium and novel indirubin derivatives on human skin cancer cells by activation of the AhR pathway

The use of cold atmospheric pressure plasma has become more important in recent years as anti-cancer therapy. Cell viability and cell adhesion were significantly reduced in cell viability and cell adhesion in combinatorial experiments using plasma-activated medium and KD87. Only in A431 cells had a pro-apoptotic effect, so we hypothesize a different mode of action of the indirubin derivatives in the two skin cancer cells, possibly due to a different expression of this receptor and subsequent gene expression activation.

Source link: https://ui.adsabs.harvard.edu/abs/2022NatSR..12.2528R/abstract


DUNEScan: a web server for uncertainty estimation in skin cancer detection with deep neural networks

The number of skin cancer detection applications has risen dramatically in recent years. While deep learning advancements in deep learning enabled classification accuracy to hit new heights, no publicly available skin cancer detection services provide confidence estimates for these predictions. We welcome DUNESCAN, a web server that provides an intuitive in-depth review of uncertainty in commonly used skin cancer classification schemes based on convolutional neural networks.

Source link: https://ui.adsabs.harvard.edu/abs/2022NatSR..12..179M/abstract


Real-time high-resolution millimeter-wave imaging for in-vivo skin cancer diagnosis

High-resolution millimeter-wave imaging, with its high discrimination contrast and deep penetration depth, can potentially provide affordable tissue diagnostic data noninvasively. In this research, we examine the use of a real-time HR-MMWI for in-vivo skin cancer diagnosis. 136 benign and malignant skin lesions from 71 patients, including melanoma, basal cell carcinoma, squamous cell carcinoma, actinic keratosis, melanoma, squamous cell carcinoma, squamous cell carcinoma, actinic keratosis, angiokeratoma, solar lentigo, seborrheic nevi, keratosis, chona Our findings show that real-time millimeter wave imaging can be used to distinguish malignant tissues from benign skin lesions with high diagnostic precision comparable to clinical examination and other methods.

Source link: https://ui.adsabs.harvard.edu/abs/2022NatSR..12.4971M/abstract


New pyramidal hybrid textural and deep features based automatic skin cancer classification model: Ensemble DarkNet and textural feature extractor

Background: Skin cancer is one of the most common cancers worldwide, and dermatology clinics can be aided by a clear diagnosis. Hence, a machine learning-based automatic skin cancer detection system must be introduced. Methods and Method: This research aims to solve the common skin cancer detection problem. The use of a colored skin cancer image database is used. Using discrete wavelet transform, local phase quantization, local binary pattern, pre-trained DarkNet19, and DarkNet53 are used to create features of the skin cancer images, top 1000 components are selected threshold value-based neighborhood component analysis. Conclusions: The findings and accuracies found have shown that this method could be used in dermatology and pathology clinics to reduce the skin cancer detection process and assist physicians, according to the authors.

Source link: https://ui.adsabs.harvard.edu/abs/2022arXiv220315090B/abstract

* Please keep in mind that all text is summarized by machine, we do not bear any responsibility, and you should always check original source before taking any actions

* Please keep in mind that all text is summarized by machine, we do not bear any responsibility, and you should always check original source before taking any actions