Search for: All records

A new framework for advanced machine learning-based analysis of hyperspectral datasets HSKL was built using the well-known package scikit-learn. In this paper, we describe HSKL’s structure and basic usage. We also showcase the diversity of models supported by the package by applying 17 classification algorithms and measure their baseline performance in segmenting objects with highly similar spectral properties. 

Multi- and hyperspectral imaging modalities encompass a growing number of spectral techniques that find many applications in geospatial, biomedical and machine vision fields. The rapidly increasing number of applications requires a convenient easy-to-navigate software that can be used by new and experienced users to analyze data, develop, apply, and deploy novel algorithms. Herein, we present our platform, IDCube that performs essential operations in hyperspectral data analysis to realize the full potential of spectral imaging. The strength of the software lies in its interactive features that enable the users to optimize parameters and obtain visual input for the user. The entire software can be operated without any prior programming skills allowing interactive sessions of raw and processed data. IDCube Lite, a free version of the software described in the paper, has many benefits compared to existing packages and offers structural flexibility to discover new hidden features. 

Abstract Shortwave infrared radiation (SWIR) is the portion of the electromagnetic spectrum from approximately 900 nm to 2500 nm. Recent advances in imaging systems have expanded the application of SWIR emitters from traditional fields in materials science to biomedical imaging, and the new detectors in SWIR opened an opportunity of deep tissue imaging. Achieving deep photon penetration while maintaining high resolution is one of the main objectives and challenges in bioimaging used for the investigation of diverse processes in living organisms. The application of SWIR emitters in biological settings is, however, hampered by low quantum efficiency. So far, photoluminescent properties in the SWIR region have not been improved by extending concepts that have been developed for the visible (400–650 nm) and near-infrared (NIR, 700–900 nm) wavelengths, which indicates that the governing behavior is fundamentally different in the SWIR. The focus of this minireview is to examine the mechanisms behind the low efficiency of SWIR emitters as well as to highlight the progress in their design for biological applications. Several common mechanisms will be considered in this review: (a) the effect of the energy gap between the excited and ground state on the quantum efficiency, (b) the coupling of the excited electronic states in SWIR emitters to vibrational states in the surrounding matrix, and (c) the role of environment in quenching the excited states. General strategies to improve the quantum yields for a diverse type of SWIR emitters will be also presented. 

Short‐wave infrared hyperspectral imaging is applied to diagnose and monitor a case of allergic contact dermatitis (ACD) due to poison ivy exposure in one subject. This approach directly demonstrates increased tissue fluid content in ACD lesional skin with a spectral signature that matches the spectral signature of intradermally injected normal saline. The best contrast between the affected and unaffected skin is achieved through a selection of specific wavelengths at 1070, 1340 and 1605 nm and combining them in a pseudo‐red‐green‐blue color space. An image derived from these wavelengths normalized to unaffected skin defines a “tissue fluid index” that may aid in the quantitative diagnosis and monitoring of ACD. Further clinical testing of this promising approach towards disease detection and monitoring with tissue fluid content quantification is warranted.