Search Results (122)

Background: Current histopathology- and molecular-based gold standards for diagnosing adult diffuse gliomas (ADGs) have inherent limitations in reproducibility and interobserver concordance, while being time-intensive and resource-demanding. Although hyperspectral imaging (HSI)-based computer-aided pathology shows potential for automated diagnosis, it often yields suboptimal accuracy due to the lack of complementary spatial and structural tumor information. This study introduces a multimodal fusion framework integrating HSI with routinely acquired preoperative magnetic resonance imaging (MRI) to enable automated, high-precision ADG diagnosis. Methods: We developed the Hyperspectral Attention Fusion Network (HAFNet), incorporating residual learning and channel attention to jointly capture HSI patterns and MRI-derived radiomic features. The dataset comprised 1931 HSI cubes (400–1000 nm, 300 spectral bands) from histopathological patches of six major World Health Organization (WHO)-defined glioma subtypes in 30 patients, together with their routinely acquired preoperative MRI sequences. Informative wavelengths were selected using mutual information. Radiomic features were extracted with the PyRadiomics package. Model performance was assessed via stratified 5-fold cross-validation, with accuracy and area under the curve (AUC) as primary endpoints. Results: The multimodal HAFNet achieved a macro-averaged AUC of 0.9886 and a classification accuracy of 98.66%, markedly outperforming the HSI-only baseline (AUC 0.9267, accuracy 87.25%; p < 0.001), highlighting the complementary value of MRI-derived radiomic features in enhancing discrimination beyond spectral information. Conclusions: Integrating HSI biochemical and microstructural insights with MRI radiomics of morphology and context, HAFNet provides a robust, reproducible, and efficient framework for accurately predicting 2021 WHO types and grades of ADGs, demonstrating the significant added value of multimodal integration for precise glioma diagnosis. Full article

Hyperspectral imaging (HSI) is a swiftly developing intraoperative and diagnostic technique in several clinical specialties. By monitoring oxygenation and biochemical markers, it helps with tissue viability, burn depth measurement, wound healing, and tumor detection. HSI facilitates real-time, harmless diagnosis throughout surgeries or outpatient settings, and allows for the detection of tumor boundaries with over 90% accuracy, according to clinical studies. Originally developed for remote sensing and aerospace applications, HSI has rapidly evolved and found increasing relevance across diverse sectors, including agriculture, environmental monitoring, food safety, pharmaceuticals, defense, and especially medical diagnostics. This review explores the origins, development, and expanding applications of HSI, with a particular emphasis on its role in healthcare. It discusses the operational principles and unique features of hyperspectral systems, such as their ability to produce spectral data cubes, perform non-destructive analysis, and integrate with emerging technologies like artificial intelligence and drone-based platforms. By comparing hyperspectral imaging to traditional and multispectral techniques, the review highlights its superior spectral resolution and versatility. Key challenges, including data volume, sensor calibration, and real-time processing, are also addressed. Finally, emerging trends such as miniaturization, integration with the Internet of Things, and sustainable system designs are examined, offering insights into the future directions and interdisciplinary potentials of HSI in both scientific research and practical applications. Full article

The advent of hyperspectral remote sensing represented a breakthrough in the accurate, fast, and non-invasive estimation of important soil fertility parameters. The present study utilizes non-imaging hyperspectral data in the spectral range of 350–2500 nm for estimating soil organic carbon (SOC) content. When partial least squares (PLS) scores were taken as independent variables, support vector machine (SVM) outperformed artificial neural network (ANN) and partial least squares regression (PLSR), achieving an R² value of 0.83. After pre-processing, the proximal spectral values were spatially interpolated to construct a synthetic hyperspectral image of the experimental fields. By applying the regression model to this synthetic hyperspectral imagery, a high-resolution SOC map showing the variability of organic carbon content in the soil was generated. Full article

Weeding in melon and watermelon fields requires selective and pinpoint operation because the crop plants are sensitive to herbicides and tend to grow on the ground in all directions. Hyperspectral images have high spectral and spatial resolution, enabling an object’s classification according to its spectral properties. Spectral band selection is a common practice with hyperspectral images, as it reduces the number of bands in use with only a minor effect on the results. This study’s innovative contribution is the development and validation of a practical methodology to simplify complex hyperspectral data for real-world robotic weed management. This includes the introduction of the ‘normalized crop sample index’ (NCSI) to guide band selection and the use of machine learning methods, which revealed a set of four spectral bands—480 nm, 550 nm, 686 nm and 750 nm—that hold sufficient discriminating information between weeds and watermelon crop. This minimal set of bands enables the simulation and future development of a low-cost, high-speed multispectral camera system. An XGBoost model showed the lowest misclassification error level of 2–14%. The selected spectral bands were used to extract single-band images from the hyperspectral cube. In these images, vegetation pixels were separated using a normalized difference vegetation index filter, and each pixel was classified into a crop or weed class. The classified pixels were grouped into segmented objects, and weeding points were selected, suitable for robotic pinpoint operation. Full article

In recent years, hybrid models that integrate Convolutional Neural Networks (CNNs) with Vision Transformers (ViTs) have achieved significant improvements in hyperspectral image classification (HSIC). Nevertheless, their complex architectures often lead to computational redundancy and inefficient feature fusion, particularly struggling to balance global modeling and local detail extraction in high-dimensional spectral data. To solve these issues, this paper proposes a Spectral-Cube Gated Harmony Network (SCGHN) that achieves efficient spectral–spatial joint feature modeling through a dynamic gating mechanism and hierarchical feature decoupling strategy. There are three primary innovative contributions of this paper as follows: Firstly, we design a Spectral Cooperative Parallel Convolution (SCPC) module that combines dynamic gating in the spectral dimension and spatial deformable convolution. This module adopts a dual-path parallel architecture that adaptively enhances key bands and captures local textures, thereby significantly improving feature discriminability at mixed ground object boundaries. Secondly, we propose a Dual-Gated Fusion (DGF) module that achieves cross-scale contextual complementarity through group convolution and lightweight attention, thereby enhancing hierarchical semantic representations with significantly lower computational complexity. Finally, by means of the coordinated design of 3D convolution and lightweight classification decision blocks, we construct an end-to-end lightweight framework that effectively alleviates the structural redundancy issues of traditional hybrid models. Extensive experiments on three standard hyperspectral datasets reveal that our SCGHN requires fewer parameters and exhibits lower computational complexity as compared with some existing HSIC methods. Full article

Bacterial leaf streak (BLS), caused by Xanthomonas translucens pv. undulosa, has become an intermittent yet economically significant disease of wheat in the Upper Midwest during the last decade. Because chemical and cultural controls remain ineffective, breeders rely on developing resistant varieties, yet visual ratings in inoculated nurseries are labor-intensive, subjective, and time-consuming. To accelerate this process, we combined unmanned-aerial-vehicle hyperspectral imaging (UAV-HSI) with a carefully tuned chemometric workflow that delivers rapid, objective estimates of disease severity. Principal component analysis cleanly separated BLS, leaf rust, and Fusarium head blight, with the first component explaining 97.76% of the spectral variance, demonstrating in-field pathogen discrimination. Pre-processing of the hyperspectral cubes, followed by robust Partial Least Squares (RPLS) regression, improved model reliability by managing outliers and heteroscedastic noise. Four variable-selection strategies—Variable Importance in Projection (VIP), Interval PLS (iPLS), Recursive Weighted PLS (rPLS), and Genetic Algorithm (GA)—were evaluated; rPLS provided the best balance between parsimony and accuracy, trimming the predictor set from 244 to 29 bands. Informative wavelengths clustered in the near-infrared and red-edge regions, which are linked to chlorophyll loss and canopy water stress. The best model, RPLS with optimal preprocessing and variable selection based on the rPLS method, showed high predictive accuracy, achieving a cross-validated R² of 0.823 and cross-validated RMSE of 7.452, demonstrating its effectiveness for detecting and quantifying BLS. We also explored the spectral overlap with Sentinel-2 bands, showing how UAV-derived maps can nest within satellite mosaics to link plot-level scouting to landscape-scale surveillance. Together, these results lay a practical foundation for breeders to speed the selection of resistant lines and for agronomists to monitor BLS dynamics across multiple spatial scales. Full article

Salmonella serovar identification typically requires multiple enrichment steps using selective media, consuming considerable time and resources. This study presents a rapid, culture-independent method leveraging artificial intelligence (AI) to classify Salmonella serovars from rich hyperspectral microscopy data. Five serovars (Enteritidis, Infantis, Kentucky, Johannesburg, 4,[5],12:i:-) were analyzed from samples prepared using only sterilized de-ionized water. Hyperspectral data cubes were collected to generate single-cell spectra and RGB composite images representing the full microscopy field. Data analysis involved two parallel branches followed by multimodal fusion. The spectral branch compared manual feature selection with data-driven feature extraction via principal component analysis (PCA), followed by classification using conventional machine learning models (i.e., k-nearest neighbors, support vector machine, random forest, and multilayer perceptron). The image branch employed a convolutional neural network (CNN) to extract spatial features directly from images without predefined morphological descriptors. Using PCA-derived spectral features, the highest performing machine learning model achieved 81.1% accuracy, outperforming manual feature selection. CNN-based classification using image features alone yielded lower accuracy (57.3%) in this serovar-level discrimination. In contrast, a multimodal fusion model combining spectral and image features improved accuracy to 82.4% on the unseen test set while reducing overfitting on the train set. This study demonstrates that AI-enabled hyperspectral microscopy with multimodal fusion can streamline Salmonella serovar identification workflows. Full article

Accurate and early detection of plant diseases is essential for effective management and the advancement of sustainable smart agriculture. However, building large annotated datasets for disease classification is often costly and time-consuming, requiring expert input. To address this challenge, this study explores the integration of few-shot learning with hyperspectral imaging to detect four major fungal diseases in tomato plants: Alternaria alternata, Alternaria solani, Botrytis cinerea, and Fusarium oxysporum. Following inoculation, hyperspectral images were captured every other day from Day 1 to Day 7 post inoculation. The proposed hybrid method includes three main steps: (1) preprocessing of hyperspectral image cubes, (2) deep feature extraction using the EfficientNet model, and (3) classification using Manhattan distance within a few-shot learning framework. This combination leverages the strengths of both spectral imaging and deep learning for robust detection with minimal data. The few-shot learning approach achieved high detection accuracies of 85.73%, 80.05%, 90.33%, and 82.09% for A. alternata, A. solani, B. cinerea, and F. oxysporum, respectively, based on data collected on Day 7 post inoculation using only three training images per class. Accuracy improved over time, reflecting the progressive nature of symptom development and the model’s adaptability with limited data. Notably, A. alternata and B. cinerea were reliably detected by Day 3, while A. solani and F. oxysporum reached dependable detection levels by Day 5. Routine visual assessments showed that A. alternata and B. cinerea developed visible symptoms by Day 5, whereas A. solani and F. oxysporum remained asymptomatic until Day 7. The model’s ability to detect infections up to two days before visual symptoms emerged highlights its value for pre-symptomatic diagnosis. These findings support the use of few-shot learning and hyperspectral imaging for early, accurate disease detection, offering a practical solution for precision agriculture and timely intervention. Full article

To effectively utilize the rich spectral information of hyperspectral remote sensing images (HRSIs), the fractional Fourier transform (FRFT) feature of HRSIs is proposed to reflect the time-domain and frequency-domain characteristics of a spectral pixel simultaneously, and an FRFT order selection criterion is also proposed based on maximizing separability. Firstly, FRFT is applied to the spectral pixels, and the amplitude spectrum is taken as the FRFT feature of HRSIs. The FRFT feature is mixed with the pixel spectral to form the presented spectral and fractional Fourier transform mixed feature (SF²MF), which contains time–frequency mixing information and spectral information of pixels. K-nearest neighbor, logistic regression, and random forest classifiers are used to verify the superiority of the proposed feature. A 1-dimensional convolutional neural network (1D-CNN) and a two-branch CNN network (Two-CNN_SF²MF-Spa) are designed to extract the depth SF²MF feature and the SF²MF-spatial joint feature, respectively. Moreover, to compensate for the defect that CNN cannot effectively capture the long-range features of spectral pixels, a long short-term memory (LSTM) network is introduced to be combined with CNN to form a two-branch network C-CLSTM_SF²MF for extracting deeper and more efficient fusion features. A 3D-CNN_SF²MF model is designed, which firstly performs the principal component analysis on the spa-SF²MF cube containing spatial information and then feeds it into the 3-dimensional convolutional neural network 3D-CNN_SF²MF to extract the SF²MF-spatial joint feature effectively. The experimental results of three real HRSIs show that the presented mixed feature SF²MF can effectively improve classification accuracy. Full article

A miniaturized hyperspectral camera, developed by integrating a linear variable band-pass filter (LVBPF) with an image sensor, was installed on the TIRSAT 3U CubeSat, launched on 17 February 2024 by Japan’s H3 launch vehicle. The satellite and its onboard hyperspectral camera conducted on-orbit experiments and successfully acquired hyperspectral data from multiple locations. The required attitude control for the hyperspectral mission was also achieved. CubeSat-based hyperspectral missions often face challenges in image alignment due to factors such as parallax, distortion, and limited attitude stability. This study presents solutions to these issues, supported by actual observational hyperspectral data. To verify the consistency of the hyperspectral data acquired by TIRSAT and processed using the proposed method, a validation analysis was conducted. Full article

This study examines the mineral composition of volcanic samples similar to lunar materials, focusing on olivine and pyroxene. Using hyperspectral imaging (HSI) from 400 to 1000 nm, we created data cubes to analyze the reflectance characteristics of samples from Vulcano, a volcanically active island in the Aeolian archipelago, north of Sicily, Italy, categorizing them into nine regions of interest (ROIs) and analyzing spectral data for each. We applied various unsupervised clustering algorithms, including K-Means, hierarchical clustering, Gaussian mixture models (GMMs), and spectral clustering, to classify the spectral profiles. Principal component analysis (PCA) revealed distinct spectral signatures associated with specific minerals, facilitating precise identification. The clustering performance varied by region, with K-Means achieving the highest silhouette score of 0.47, whereas GMMs performed poorly with a score of only 0.25. Non-negative matrix factorization (NMF) aided in identifying similarities among clusters across different methods and reference spectra for olivine and pyroxene. Hierarchical clustering emerged as the most reliable technique, achieving a 94% similarity with the olivine spectrum in one sample, whereas GMMs exhibited notable variability. Overall, the analysis indicated that both the hierarchical and K-Means methods yielded lower errors in total measurements, with K-Means demonstrating superior performance in estimated dispersion and clustering. Additionally, GMMs showed a higher root mean square error (RMSE) compared to the other models. The RMSE analysis confirmed K-Means as the most consistent algorithm across all samples, suggesting a predominance of olivine in the Vulcano region relative to pyroxene. This predominance is likely linked to historical formation conditions similar to volcanic processes on the Moon, where olivine-rich compositions are common in ancient lava flows and impact-melt rocks. These findings provide a deeper context for mineral distribution and formation processes in volcanic landscapes. Full article

HyperSCAN (Hyper Spectral Camera ANalyzer) is a hyperspectral imager which monitors the Earth’s environment and also an educational platform to integrate college students’ ideas and skills in optical design and data processing. The advantages of HyperSCAN are that it is designed for modular design, is compact and lightweight, and low-cost using commercial off-the-shelf (COTS) optical components. The modular design allows for flexible and rapid development, as well as validation within college lab environments. To optimize space utilization and reduce the optical path, HyperSCAN’s optical system incorporates a folding mirror, making it ideal for the constrained environment of a CubeSat. The use of COTS components significantly lowers pre-development costs and minimizes associated risks. The compact size and cost-effectiveness of CubeSats, combined with the advanced capabilities of hyperspectral imagers, make them a powerful tool for a broad range of applications, such as environmental monitoring of Earth, disaster management, mineral and resource exploration, atmospheric and climate studies, and coastal and marine research. We conducted a spatial-resolution-boost experiment using HyperSCAN data and various hyperspectral datasets including Urban, Pavia University, Pavia Centre, Botswana, and Indian Pines. After testing various data-fusion deep learning models, the best image quality of these methods is a two-branches convolutional neural network (TBCNN), where TBCNN retrieves spatial and spectral features in parallel and reconstructs the higher-spatial-resolution data. With the aid of higher-spatial-resolution multispectral data, we can boost the spatial resolution of HyperSCAN data. Full article

To achieve large-scale stitching of the hyperspectral remote sensing images obtained by unmanned aerial vehicles (UAVs) equipped with an acousto-optic tunable filter spectrometer, this study proposes a method based on a feature fusion strategy and a seam-finding strategy using hyperspectral image classification. In the feature extraction stage, SuperPoint deep features from images in different spectral segments of the data cube were extracted and fused. The feature depth matcher, LightGlue, was employed for feature matching. During the data cube fusion stage, unsupervised K-means spectral classification was performed separately on the two hyperspectral data cubes. Subsequently, grayscale transformations were applied to the classified images. A dynamic programming method, based on a grayscale loss function, was then used to identify seams in the transformed images. Finally, the identified splicing seam was applied across all bands to produce a unified hyperspectral data cube. The proposed method was applied to hyperspectral data cubes acquired at specific waypoints by UAVs using an acousto-optic tunable filter spectral imager. Experimental results demonstrated that the proposed method outperformed both single-spectral-segment feature extraction methods and stitching methods that rely on seam identification from a single spectral segment. The improvement was evident in both the spatial and spectral dimensions. Full article

Algorithms for detecting point targets in hyperspectral imaging commonly employ the spectral inverse covariance matrix to whiten inherent image noise. Since data cubes often lack stationarity, segmentation appears to be an attractive preprocessing operation. Surprisingly, the literature reports both successful and unsuccessful segmentation cases, with no clear explanations for these divergent outcomes. This paper elucidates the conditions under which segmentation might improve detector performance. Focusing on a representative algorithm and assuming a target additive model, the study examines all influential factors through theoretical analysis and extensive simulations. The findings offer fundamental insights and practical guidelines for characterizing segmented datasets, enabling a thorough evaluation of segmentation’s utility for detector performance. They outline the range of target scenarios and parameters where segmentation may prove beneficial and help assess the potential impact of proposed segmentation strategies on detection outcomes. Full article

CubeSats have emerged as a promising alternative to satellite missions for studying remote areas where satellite data are scarce and insufficient, such as coastal and marine environments. However, their standard size and weight limitations make integrating remote sensing optical instruments challenging. This work presents the development of Bentayga-I, a CubeSat designed to validate PANDORA, a self-made, lightweight, cost-effective multispectral camera with interchangeable spectral optical filters, in near-space conditions. Its four selected spectral bands are relevant for ocean studies. Alongside the camera, Bentayga-I integrates a power system for short-time operation capacity; a thermal subsystem to maintain battery function; environmental sensors to monitor the CubeSat’s internal and external conditions; and a communication subsystem to transmit acquired data to a ground station. The first helium balloon launch with B2Space proved that Bentayga-I electronics worked correctly in near-space environments. During this launch, the spectral capabilities of PANDORA alongside the spectrum were validated using a hyperspectral camera. Its scientific applicability was also tested by capturing images of coastal areas. A second launch is planned to further validate the multispectral camera in a real-world scenario. The integration of Bentayga-I and PANDORA presents promising results for future low-cost CubeSats missions. Full article