Identifying the role of vision transformer for skin cancer-A scoping review.

Introduction: Detecting and accurately diagnosing early melanocytic lesions is challenging due to extensive intra- and inter-observer variabilities. Dermoscopy images are widely used to identify and study skin cancer, but the blurred boundaries between lesions and besieging tissues can lead to incorrect identification. Artificial Intelligence (AI) models, including vision transformers, have been proposed as a solution, but variations in symptoms and underlying effects hinder their performance. Objective: This scoping review synthesizes and analyzes the literature that uses vision transformers for skin lesion detection. Methods: The review follows the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Revise) guidelines. The review searched online repositories such as IEEE Xplore, Scopus, Google Scholar, and PubMed to retrieve relevant articles. After screening and pre-processing, 28 studies that fulfilled the inclusion criteria were included. Results and discussions: The review found that the use of vision transformers for skin cancer detection has rapidly increased from 2020 to 2022 and has shown outstanding performance for skin cancer detection using dermoscopy images. Along with highlighting intrinsic visual ambiguities, irregular skin lesion shapes, and many other unwanted challenges, the review also discusses the key problems that obfuscate the trustworthiness of vision transformers in skin cancer diagnosis. This review provides new insights for practitioners and researchers to understand the current state of knowledge in this specialized research domain and outlines the best segmentation techniques to identify accurate lesion boundaries and perform melanoma diagnosis. These findings will ultimately assist practitioners and researchers in making more authentic decisions promptly.

Low-volume PEEK gas cell for BTEX detection using portable deep-UV absorption spectrophotometry.

Monitoring of indoor air quality by detecting individual airborne pollutant is essential for maintaining a healthy indoor environment. UV absorption spectrophotometry coupled with gas chromatography offers a reliable, self-referenced and non-destructive technique for the identification and detection of gas molecules. This paper presents a deep-UV absorption spectrophotometer coupled with a micro gas-chromatography (µGC) for the detection of benzene, toluene, ethylbenzene and xylenes (BTEX). The spectrophotometer was developed using a low-volume gas cell made of PolyEther Ether Ketone (PEEK) polymer tube, connected with a portable deep-UV LED and photomultiplier tube. The performance of the detection unit was evaluated with different concentrations of toluene (5-100 ppm) in nitrogen and a sensitivity of 107.1 µAU/ppm with a limit of detection of 1.41 ppm was obtained. The detector was incorporated into a micro gas-chromatography setup and high quality chromatograms, having all the peaks separated with good repeatability were obtained for BTEX molecules. The deep-UV absorption spectrophotometer has low-volume, low-cost, and ease of development and integration. While demonstrated for BTEX in a nitrogen carrier gas, the spectrometer has the potential to be applied to chromatographic analysis of different analytes in gas or liquid media.

Gas Detection Using Portable Deep-UV Absorption Spectrophotometry: A Review.

Several gas molecules of environmental and domestic significance exhibit a strong deep-UV absorption. Therefore, a sensitive and a selective gas detector based on this unique molecular property (i.e., absorption at a specific wavelength) can be developed using deep-UV absorption spectrophotometry. UV absorption spectrometry provides a highly sensitive, reliable, self-referenced, and selective approach for gas sensing. This review article addresses the recent progress in the application of deep-UV absorption for gas sensing owing to its inherent features and tremendous potentials. Applications, advancements, and challenges related to UV emission sources, gas cells, and UV photodetectors are assessed and compared. We present the relevant theoretical aspects and challenges associated with the development of portable sensitive spectrophotometer. Finally, the applications of UV absorption spectrometry for ozone, NO2, SO2, and aromatic organic compounds during the last decades are discussed and compared. A portable UV absorption spectrophotometer can be developed by using LEDs, hollow core waveguides (HCW), and UV photodetectors (i.e., photodiodes). LED provides a portable UV emission source with low power input, low-intensity drifts, low cost, and ease of alignment. It is a quasi-chromatic UV source and covers the absorption band of molecules without optical filters for absorbance measurement of a target analyte. HCWs can be applied as a miniature gas cell for guiding UV radiation for measurement of low gas concentrations. Photodiodes, on the other hand, offer a portable UV photodetector with excellent spectral selectivity with visible rejection, minimal dark current, linearity, and resistance against UV-aging.

Development of a Toluene Detector Based on Deep UV Absorption Spectrophotometry Using Glass and Aluminum Capillary Tube Gas Cells with a LED Source.

A simple deep-ultraviolet (UV) absorption spectrophotometer based on ultraviolet light-emitting diode (UV LED) was developed for the detection of air-borne toluene with a good sensitivity. A fiber-coupled deep UV-LED was employed as a light source, and a spectrometer was used as a detector with a gas cell in between. 3D printed opto-fluidics connectors were designed to integrate the gas flow with UV light. Two types of hollow core waveguides (HCW) were tested as gas cells: a glass capillary tube with aluminum-coated inner walls and an aluminum capillary tube. The setup was tested for different toluene concentrations (10⁻100 ppm), and a linear relationship was observed with sensitivities of 0.20 mA·U/ppm and 0.32 mA·U/ppm for the glass and aluminum HCWs, respectively. The corresponding limits of detection were found to be 8.1 ppm and 12.4 ppm, respectively.

Design, synthesis, and biological evaluation of a novel class of fluorescein-based N-glycosylamines.

A series of fluorescein-based N-glycosylamines was synthesized from the corresponding fluorescein amine and a partially protected d-glucose. The physiochemical investigation of these compounds by spectral and morphological studies reveals their gelation potential. The exclusive localization of fluorescence in the cytoplasm through cell imaging studies reveals the anti-cancer potentials of N-glycosylamines.