Applications of hyperspectral imaging in plant phenotyping

Our ability to interrogate and manipulate the genome far exceeds our capacity to measure the effects of genetic changes on plant traits. Much effort has been made recently by the plant science research community to address this imbalance. The responses of plants to environmental conditions can now be defined using a variety of imaging approaches. Hyperspectral imaging (HSI) has emerged as a promising approach to measure traits using a wide range of wavebands simultaneously in 3D to capture information in lab, glasshouse, or field settings. HSI has been applied to define abiotic, biotic, and quality traits for optimisation of crop management.

Hyperspectral imaging in wound care: A systematic review

Multispectral and hyperspectral imaging (HSI) are emerging imaging techniques with the potential to transform the way patients with wounds are cared for, but it is not clear whether current systems are capable of delivering real-time tissue characterisation and treatment guidance. We conducted a systematic review of HSI systems that have been assessed in patients, published over the past 32 years. We analysed 140 studies, including 10 different HSI systems. Current in vivo HSI systems generate a tissue oxygenation map. Tissue oxygenation measurements may help to predict those patients at risk of wound formation or delayed healing. No safety concerns were reported in any studies. A small number of studies have demonstrated the capabilities of in vivo label-free HSI, but further work is needed to fully integrate it into the current clinical workflow for different wound aetiologies. As an emerging imaging modality for medical applications, HSI offers great potential for non-invasive disease diagnosis and guidance when treating patients with both acute and chronic wounds.

Plot-level rapid screening for photosynthetic parameters using proximal hyperspectral imaging

Photosynthesis is currently measured using time-laborious and/or destructive methods which slows research and breeding efforts to identify crop germplasm with higher photosynthetic capacities. We present a plot-level screening tool for quantification of photosynthetic parameters and pigment contents that utilizes hyperspectral reflectance from sunlit leaf pixels collected from a plot (~2 m×2 m) in <1 min. Using field-grown Nicotiana tabacum with genetically altered photosynthetic pathways over two growing seasons (2017 and 2018), we built predictive models for eight photosynthetic parameters and pigment traits. Using partial least squares regression (PLSR) analysis of plot-level sunlit vegetative reflectance pixels from a single visible near infra-red (VNIR) (400-900 nm) hyperspectral camera, we predict maximum carboxylation rate of Rubisco (Vc,max, R2=0.79) maximum electron transport rate in given conditions (J1800, R2=0.59), maximal light-saturated photosynthesis (Pmax, R2=0.54), chlorophyll content (R2=0.87), the Chl a/b ratio (R2=0.63), carbon content (R2=0.47), and nitrogen content (R2=0.49). Model predictions did not improve when using two cameras spanning 400-1800 nm, suggesting a robust, widely applicable and more 'cost-effective' pipeline requiring only a single VNIR camera. The analysis pipeline and methods can be used in any cropping system with modified species-specific PLSR analysis to offer a high-throughput field phenotyping screening for germplasm with improved photosynthetic performance in field trials.

Callicó G, Fei B. Hyperspectral Imaging for the Detection of Glioblastoma Tumor Cells in H&E Slides Using Convolutional Neural Networks

Hyperspectral imaging (HSI) technology has demonstrated potential to provide useful information about the chemical composition of tissue and its morphological features in a single image modality. Deep learning (DL) techniques have demonstrated the ability of automatic feature extraction from data for a successful classification. In this study, we exploit HSI and DL for the automatic differentiation of glioblastoma (GB) and non-tumor tissue on hematoxylin and eosin (H&E) stained histological slides of human brain tissue. GB detection is a challenging application, showing high heterogeneity in the cellular morphology across different patients. We employed an HSI microscope, with a spectral range from 400 to 1000 nm, to collect 517 HS cubes from 13 GB patients using 20× magnification. Using a convolutional neural network (CNN), we were able to automatically detect GB within the pathological slides, achieving average sensitivity and specificity values of 88% and 77%, respectively, representing an improvement of 7% and 8% respectively, as compared to the results obtained using RGB (red, green, and blue) images. This study demonstrates that the combination of hyperspectral microscopic imaging and deep learning is a promising tool for future computational pathologies.

A comprehensive and fast microplastics identification based on near-infrared hyperspectral imaging (HSI-NIR) and chemometrics

Microplastic pollution is a global concern theme, and there is still the need for less laborious and faster analytical methods aiming at microplastics detection. This article describes a high throughput screening method based on near-infrared hyperspectral imaging (HSI-NIR) to identify microplastics in beach sand automatically with minimum sample preparation. The method operates directly in the entire sample or on its retained fraction (150 μm-5 mm) after sieving. Small colorless microplastics (<600 μm) that would probably be imperceptible as a microplastic by visual inspection, or missed during manual pick up, can be easily detected. No spectroscopic subsampling was performed due to the high-speed analysis of line-scan instrumentation, allowing multiple microplastics to be assessed simultaneously (video available). This characteristic is an advantage over conventional infrared (IR) spectrometers. A 75 cm² scan area was probed in less than 1 min at a pixel size of 156 × 156 μm. An in-house comprehensive spectral dataset, including weathered microplastics, was used to build multivariate supervised soft independent modelling of class analogy (SIMCA) classification models. The chemometric models were validated for hundreds of microplastics (primary and secondary) collected in the environment. The effect of particle size, color and weathering are discussed. Models' sensitivity and specificity for polyethylene (PE), polypropylene (PP), polyamide-6 (PA), polyethylene terephthalate (PET) and polystyrene (PS) were over 99% at the defined statistical threshold. The method was applied to a sand sample, identifying 803 particles without prior visual sorting, showing automatic identification was robust and reliable even for weathered microplastics analyzed together with other matrix constituents. The HSI-NIR-SIMCA described is also applicable for microplastics extracted from other matrices after sample preparation. The HSI-NIR principals were compared to other common techniques used to microplastic chemical characterization. The results show the potential to use HSI-NIR combined with classification models as a comprehensive microplastic-type characterization screening.

Hyperspectral analysis for perioperative perfusion monitoring-a clinical feasibility study on free and pedicled flaps

OBJECTIVES

In reconstructive surgery, flap monitoring is crucial for early identification of perfusion problems. Using hyperspectral imaging (HSI), this clinical study aimed to develop a non-invasive, objective approach for perfusion monitoring of free and pedicled flaps.

MATERIAL AND METHODS

HSI of 22 free (FF) and 8 pedicled flaps (PF) in 30 patients was recorded over time. Parameters assessed were tissue oxygenation/superficial perfusion (0-1 mm) (StO2 (0-100%)), near-infrared perfusion/deep perfusion (0-4 mm) (NIR (0-100)), distribution of haemoglobin (THI (0-100)), and water (TWI (0-100)). Measurements up to 72 h were correlated to clinical assessment.

RESULTS

Directly after flap inset, mean StO2 was significantly higher in FF (70.3 ± 13.6%) compared with PF 56.2 ± 14.2% (p = 0.05), whereas NIR, THI, and TWI were similar (NIR_p = 0.82, THI_p = 0.97, TWI_p = 0.27). After 24 h, StO2, NIR, THI, and TWI did not differ between FF and PF. After 48 h, StO2, NIR, and TWI did not differ between FF and PF whereas THI was significantly increased in FF compared with PF(p = 0.001). In three FF, perfusion decreased clinically and in HSI, 36(1), 40(2), 5(3), and 61(3) h after flap inset which was followed by prompt intervention.

CONCLUSIONS

StO2 < 40%, NIR < 25/100, and THI < 40/100 indicated arterial occlusion, whereas venous problems revealed an increase of THI. In comparison with FF, perfusion parameters of PF were decreased after flap transfer but remained similar to FF later on.

CLINICAL RELEVANCE

HSI provides objective and non-invasive perfusion monitoring after flap transplantation in accordance to the clinical situation. With HSI, signs of deterioration can be detected hours before clinical diagnosis.

Near-infrared hyperspectral imaging for detection and visualization of offal adulteration in ground pork

Hyperspectral imaging (HSI) technique was investigated to explore a feasible protocol for detecting the potential offal (lung) adulteration in ground pork. Tested samples (176 adulterated and 2 controls) were first prepared with adulterant of ground lung in range of 0%-100% (w/w) at 10% intervals. After hyperspectral images were acquired and calibrated in reflectance mode (400-1000 nm), full spectra were extracted from identified regions of interests (ROIs) and then transformed into absorbance and Kubelka-Munck spectral units, respectively. Partial least squares regression (PLSR) models based on full spectra showed that raw reflectance spectra with no preprocessings performed best with coefficient of determination (R_p²) of 0.98, root mean square error (RMSEP) of 4.25%, and ratio performance deviation (RPD) of 7.53 in prediction set. To reduce the high dimensionality of spectra, data was further explored using principal component loadings, two-dimensional correlation spectroscopy (2D-COS), and regression coefficients (RC), respectively. The optimal performance of established simplified PLSR model were acquired using eleven featured wavelengths selected by PC loadings with R_p² of 0.98, RMSEP of 4.47% and RPD of 7.16. Finally, the limit of detection (LOD) was calculated to be a satisfactory 7.58%, and readily discernible visualization procedure using preferred simplified PLSR model yielded satisfactory spatial distribution of adulteration situation. Control samples with known distribution were also visualized to successfully prove the validity. Consequently, this research offers an alternative assay for visually and rapidly detecting offal of lung adulteration in ground pork.

Skin Complications of Diabetes Mellitus Revealed by Polarized Hyperspectral Imaging and Machine Learning

Aging and diabetes lead to protein glycation and cause dysfunction of collagen-containing tissues. The accompanying structural and functional changes of collagen significantly contribute to the development of various pathological malformations affecting the skin, blood vessels, and nerves, causing a number of complications, increasing disability risks and threat to life. In fact, no methods of non-invasive assessment of glycation and associated metabolic processes in biotissues or prediction of possible skin complications, e.g., ulcers, currently exist for endocrinologists and clinical diagnosis. In this publication, utilizing emerging photonics-based technology, innovative solutions in machine learning, and definitive physiological characteristics, we introduce a diagnostic approach capable of evaluating the skin complications of diabetes mellitus at the very earlier stage. The results of the feasibility studies, as well as the actual tests on patients with diabetes and healthy volunteers, clearly show the ability of the approach to differentiate diabetic and control groups. Furthermore, the developed in-house polarization-based hyperspectral imaging technique accomplished with the implementation of the artificial neural network provides new horizons in the study and diagnosis of age-related diseases.

Supervised Machine Learning Methods and Hyperspectral Imaging Techniques Jointly Applied for Brain Cancer Classification

Hyperspectral imaging techniques (HSI) do not require contact with patients and are non-ionizing as well as non-invasive. As a consequence, they have been extensively applied in the medical field. HSI is being combined with machine learning (ML) processes to obtain models to assist in diagnosis. In particular, the combination of these techniques has proven to be a reliable aid in the differentiation of healthy and tumor tissue during brain tumor surgery. ML algorithms such as support vector machine (SVM), random forest (RF) and convolutional neural networks (CNN) are used to make predictions and provide in-vivo visualizations that may assist neurosurgeons in being more precise, hence reducing damages to healthy tissue. In this work, thirteen in-vivo hyperspectral images from twelve different patients with high-grade gliomas (grade III and IV) have been selected to train SVM, RF and CNN classifiers. Five different classes have been defined during the experiments: healthy tissue, tumor, venous blood vessel, arterial blood vessel and dura mater. Overall accuracy (OACC) results vary from 60% to 95% depending on the training conditions. Finally, as far as the contribution of each band to the OACC is concerned, the results obtained in this work are 3.81 times greater than those reported in the literature.

Air Pollution Detection Using a Novel Snap-Shot Hyperspectral Imaging Technique

Air pollution has emerged as a global problem in recent years. Particularly, particulate matter (PM2.5) with a diameter of less than 2.5 μm can move through the air and transfer dangerous compounds to the lungs through human breathing, thereby creating major health issues. This research proposes a large-scale, low-cost solution for detecting air pollution by combining hyperspectral imaging (HSI) technology and deep learning techniques. By modeling the visible-light HSI technology of the aerial camera, the image acquired by the drone camera is endowed with hyperspectral information. Two methods are used for the classification of the images. That is, 3D Convolutional Neural Network Auto Encoder and principal components analysis (PCA) are paired with VGG-16 (Visual Geometry Group) to find the optical properties of air pollution. The images are classified into good, moderate, and severe based on the concentration of PM2.5 particles in the images. The results suggest that the PCA + VGG-16 has the highest average classification accuracy of 85.93%.

Investigating potato late blight physiological differences across potato cultivars with spectroscopy and machine learning

Understanding plant disease resistance is important in the integrated management of Phytophthora infestans, causal agent of potato late blight. Advanced field-based methods of disease detection that can identify infection before the onset of visual symptoms would improve management by greatly reducing disease potential and spread as well as improve both the financial and environmental sustainability of potato farms. In-vivo foliar spectroscopy offers the capacity to rapidly and non-destructively characterize plant physiological status, which can be used to detect the effects of necrotizing pathogens on plant condition prior to the appearance of visual symptoms. Here, we tested differences in spectral response of four potato cultivars, including two cultivars with a shared genotypic background except for a single copy of a resistance gene, to inoculation with Phytophthora infestans clonal lineage US-23 using three statistical approaches: random forest discrimination (RF), partial least squares discrimination analysis (PLS-DA), and normalized difference spectral index (NDSI). We find that cultivar, or plant genotype, has a significant impact on spectral reflectance of plants undergoing P. infestans infection. The spectral response of four potato cultivars to infection by Phytophthora infestans clonal lineage US-23 was highly variable, yet with important shared characteristics that facilitated discrimination. Early disease physiology was found to be variable across cultivars as well using non-destructively derived PLS-regression trait models. This work lays the foundation to better understand host-pathogen interactions across a variety of genotypic backgrounds, and establishes that host genotype has a significant impact on spectral reflectance, and hence on biochemical and physiological traits, of plants undergoing pathogen infection.

Investigation of human pancreatic cancer tissues by Fourier Transform Infrared Hyperspectral Imaging

Fourier-transform infrared hyperspectral imaging (FTIR-HSI) provides hyperspectral images containing both morphological and chemical information. It is widely applied in the biomedical field to detect tumor lesions, even at the early stage, by identifying specific spectral biomarkers. Pancreatic neoplasms present different prognoses and are not always easily classified by conventional analyses. In this study, tissue samples with diagnosis of pancreatic ductal adenocarcinoma and pancreatic neuroendocrine tumor were analyzed by FTIR-HSI and the spectral data compared with those from healthy and dysplastic samples. Multivariate/univariate approaches were complemented to hyperspectral images, and definite spectral markers of the different lesions identified. The malignant lesions were recognizable both from healthy/dysplastic pancreatic tissues (high values of phospholipids and triglycerides with shorter, more branched and less unsaturated alkyl chains) and between each other (different amounts of total lipids, phosphates and carbohydrates). These findings highlight different metabolic pathways characterizing the different samples, well detectable by FTIR-HSI.

Hyperspectral Imaging for Glioblastoma Surgery: Improving Tumor Identification Using a Deep Spectral-Spatial Approach

The primary treatment for malignant brain tumors is surgical resection. While gross total resection improves the prognosis, a supratotal resection may result in neurological deficits. On the other hand, accurate intraoperative identification of the tumor boundaries may be very difficult, resulting in subtotal resections. Histological examination of biopsies can be used repeatedly to help achieve gross total resection but this is not practically feasible due to the turn-around time of the tissue analysis. Therefore, intraoperative techniques to recognize tissue types are investigated to expedite the clinical workflow for tumor resection and improve outcome by aiding in the identification and removal of the malignant lesion. Hyperspectral imaging (HSI) is an optical imaging technique with the power of extracting additional information from the imaged tissue. Because HSI images cannot be visually assessed by human observers, we instead exploit artificial intelligence techniques and leverage a Convolutional Neural Network (CNN) to investigate the potential of HSI in twelve in vivo specimens. The proposed framework consists of a 3D-2D hybrid CNN-based approach to create a joint extraction of spectral and spatial information from hyperspectral images. A comparison study was conducted exploiting a 2D CNN, a 1D DNN and two conventional classification methods (SVM, and the SVM classifier combined with the 3D-2D hybrid CNN) to validate the proposed network. An overall accuracy of 80% was found when tumor, healthy tissue and blood vessels were classified, clearly outperforming the state-of-the-art approaches. These results can serve as a basis for brain tumor classification using HSI, and may open future avenues for image-guided neurosurgical applications.

Laparoscopic system for simultaneous high-resolution video and rapid hyperspectral imaging in the visible and near-infrared spectral range

SIGNIFICANCE

Hyperspectral imaging (HSI) can support intraoperative perfusion assessment, the identification of tissue structures, and the detection of cancerous lesions. The practical use of HSI for minimal-invasive surgery is currently limited, for example, due to long acquisition times, missing video, or large set-ups.

AIM

An HSI laparoscope is described and evaluated to address the requirements for clinical use and high-resolution spectral imaging.

APPROACH

Reflectance measurements with reference objects and resected human tissue from 500 to 1000 nm are performed to show the consistency with an approved medical HSI device for open surgery. Varying object distances are investigated, and the signal-to-noise ratio (SNR) is determined for different light sources.

RESULTS

The handheld design enables real-time processing and visualization of HSI data during acquisition within 4.6 s. A color video is provided simultaneously and can be augmented with spectral information from push-broom imaging. The reflectance data from the HSI system for open surgery at 50 cm and the HSI laparoscope are consistent for object distances up to 10 cm. A standard rigid laparoscope in combination with a customized LED light source resulted in a mean SNR of 30 to 43 dB (500 to 950 nm).

CONCLUSIONS

Compact and rapid HSI with a high spatial- and spectral-resolution is feasible in clinical practice. Our work may support future studies on minimally invasive HSI to reduce intra- and postoperative complications.

Near-infrared hyperspectral imaging technology combined with deep convolutional generative adversarial network to predict oil content of single maize kernel

Rapidly and non-destructively predicting the oil content of single maize kernel is crucial for food industry. However, obtaining a large number of oil content reference values of maize kernels is time-consuming and expensive, and the limited data set also leads to low generalization ability of the model. Here, hyperspectral imaging technology and deep convolutional generative adversarial network (DCGAN) were combined to predict the oil content of single maize kernel. DCGAN was used to simultaneously expand their spectral data and oil content data. After many iterations, fake data that was very similar to the experimental data was generated. Partial least squares regression (PLSR) and support vector regression (SVR) models were established respectively, and their performance was compared before and after data augmentation. The results showed that this method not only improved the performance of two regression models, but also solved the problem of requiring a large amount of training data.

Application of hyperspectral imaging technology in the rapid identification of microplastics in farmland soil

Microplastics (MPs) are emerging environmental pollutants and their accumulation in the soil can adversely affect the soil biota. This study aims to employ hyperspectral imaging technology for the rapid screening and classification of MPs in farmland soil. In this study, a total of 600 hyperspectral data are collected from 180 sets of farmland soil samples with a hyperspectral imager in the wavelength range of 369- 988 nm. To begin, the hyperspectral data are preprocessed by the Savitzky-Golay (S-G) smoothing filter and mean normalization. Second, principal component analysis (PCA) is used to minimize the dimensions of the hyperspectral data and hence the amount of data, making the subsequent model easier to construct. The cumulative contribution rate of the first three principal components is reached 98.37%, including the main information of the original spectral data. Finally, three models including decision tree (DT), support vector machine (SVM), and convolutional neural network (CNN) are established, all of which can achieve well classification effects on three MP polymers including polyethylene (PE), polypropylene (PP), and polyvinyl chloride (PVC) in farmland soil. By comparing the recognition accuracy of the three models, the classification accuracy of DT and SVM is 87.9% and 85.6%, respectively. The CNN model based on the S-G smoothing filter obtains the best prediction effect, the classification accuracy reaches 92.6%, exhibiting obvious advantages in classification effect. Altogether, these results show that the proposed hyperspectral imaging technique identifies the soil MPs rapidly and nondestructively, and provides an effective automated method for the detection of polymers, requiring only rapid and simple sample preparation.

Classification, identification, and growth stage estimation of microalgae based on transmission hyperspectral microscopic imaging and machine learning

A transmission hyperspectral microscopic imager (THMI) that utilizes machine learning algorithms for hyperspectral detection of microalgae is presented. The THMI system has excellent performance with spatial and spectral resolutions of 4 µm and 3 nm, respectively. We performed hyperspectral imaging (HSI) of three species of microalgae to verify their absorption characteristics. Transmission spectra were analyzed using principal component analysis (PCA) and peak ratio algorithms for dimensionality reduction and feature extraction, and a support vector machine (SVM) model was used for classification. The average accuracy, sensitivity and specificity to distinguish one species from the other two species were found to be 94.4%, 94.4% and 97.2%, respectively. A species identification experiment for a group of mixed microalgae in solution demonstrates the usability of the classification method. Using a random forest (RF) model, the growth stage in a phaeocystis growth cycle cultivated under laboratory conditions was predicted with an accuracy of 98.1%, indicating the feasibility to evaluate the growth state of microalgae through their transmission spectra. Experimental results show that the THMI system has the capability for classification, identification and growth stage estimation of microalgae, with strong potential for in-situ marine environmental monitoring and early warning detection applications.

The AppNL-G-F mouse retina is a site for preclinical Alzheimer's disease diagnosis and research

In this study, we report the results of a comprehensive phenotyping of the retina of the AppNL-G-F mouse. We demonstrate that soluble Aβ accumulation is present in the retina of these mice early in life and progresses to Aβ plaque formation by midlife. This rising Aβ burden coincides with local microglia reactivity, astrogliosis, and abnormalities in retinal vein morphology. Electrophysiological recordings revealed signs of neuronal dysfunction yet no overt neurodegeneration was observed and visual performance outcomes were unaffected in the AppNL-G-F mouse. Furthermore, we show that hyperspectral imaging can be used to quantify retinal Aβ, underscoring its potential as a biomarker for AD diagnosis and monitoring. These findings suggest that the AppNL-G-F retina mimics the early, preclinical stages of AD, and, together with retinal imaging techniques, offers unique opportunities for drug discovery and fundamental research into preclinical AD.

Classification and distribution of freshwater microplastics along the Italian Po river by hyperspectral imaging

In this work, freshwater microplastic samples collected from four different stations along the Italian Po river were characterized in terms of abundance, distribution, category, morphological and morphometrical features, and polymer type. The correlation between microplastic category and polymer type was also evaluated. Polymer identification was carried out developing and implementing a new and effective hierarchical classification logic applied to hyperspectral images acquired in the short-wave infrared range (SWIR: 1000-2500 nm). Results showed that concentration of microplastics ranged from 1.89 to 8.22 particles/m3, the most abundant category was fragment, followed by foam, granule, pellet, and filament and the most diffused polymers were expanded polystyrene followed by polyethylene, polypropylene, polystyrene, polyamide, polyethylene terephthalate and polyvinyl chloride, with some differences in polymer distribution among stations. The application of hyperspectral imaging (HSI) as a rapid and non-destructive method to classify freshwater microplastics for environmental monitoring represents a completely innovative approach in this field.

High-throughput phenotyping using digital and hyperspectral imaging-derived biomarkers for genotypic nitrogen response

The development of crop varieties with higher nitrogen use efficiency is crucial for sustainable crop production. Combining high-throughput genotyping and phenotyping will expedite the discovery of novel alleles for breeding crop varieties with higher nitrogen use efficiency. Digital and hyperspectral imaging techniques can efficiently evaluate the growth, biophysical, and biochemical performance of plant populations by quantifying canopy reflectance response. Here, these techniques were used to derive automated phenotyping of indicator biomarkers, biomass and chlorophyll levels, corresponding to different nitrogen levels. A detailed description of digital and hyperspectral imaging and the associated challenges and required considerations are provided, with application to delineate the nitrogen response in wheat. Computational approaches for spectrum calibration and rectification, plant area detection, and derivation of vegetation index analysis are presented. We developed a novel vegetation index with higher precision to estimate chlorophyll levels, underpinned by an image-processing algorithm that effectively removed background spectra. Digital shoot biomass and growth parameters were derived, enabling the efficient phenotyping of wheat plants at the vegetative stage, obviating the need for phenotyping until maturity. Overall, our results suggest value in the integration of high-throughput digital and spectral phenomics for rapid screening of large wheat populations for nitrogen response.

Current State of Hyperspectral Remote Sensing for Early Plant Disease Detection: A Review

The development of hyperspectral remote sensing equipment, in recent years, has provided plant protection professionals with a new mechanism for assessing the phytosanitary state of crops. Semantically rich data coming from hyperspectral sensors are a prerequisite for the timely and rational implementation of plant protection measures. This review presents modern advances in early plant disease detection based on hyperspectral remote sensing. The review identifies current gaps in the methodologies of experiments. A further direction for experimental methodological development is indicated. A comparative study of the existing results is performed and a systematic table of different plants' disease detection by hyperspectral remote sensing is presented, including important wave bands and sensor model information.

Gastric cancer diagnosis using hyperspectral imaging with principal component analysis and spectral angle mapper

SIGNIFICANCE

Hyperspectral imaging (HSI) is an emerging optical technique that has a double function of spectroscopy and imaging.

AIM

Near-infrared hyperspectral imaging (NIR-HSI) (900 to 1700 nm) with the help of chemometrics was investigated for gastric cancer diagnosis.

APPROACH

Mean spectra and standard deviation of normal and cancerous pixels were extracted. Principal component analysis (PCA) was used to compress the dimension of hypercube data and select the optimal wavelengths. Moreover, spectral angle mapper (SAM) was utilized as chemometrics to discriminate gastric cancer from normal.

RESULTS

Major spectral difference of cancerous and normal gastric tissue was observed around 975, 1215, and 1450 nm by comparison. A total of six wavelengths (i.e., 975, 1075, 1215, 1275, 1390, and 1450 nm) were then selected as optimal wavelengths by PCA. The accuracy using SAM is up to 90% according to hematoxylin-eosin results.

CONCLUSIONS

These results suggest that NIR-HSI has the potential as a cutting-edge optical diagnostic technique for gastric cancer diagnosis with suitable chemometrics.

Proximal Methods for Plant Stress Detection Using Optical Sensors and Machine Learning

Plant stresses have been monitored using the imaging or spectrometry of plant leaves in the visible (red-green-blue or RGB), near-infrared (NIR), infrared (IR), and ultraviolet (UV) wavebands, often augmented by fluorescence imaging or fluorescence spectrometry. Imaging at multiple specific wavelengths (multi-spectral imaging) or across a wide range of wavelengths (hyperspectral imaging) can provide exceptional information on plant stress and subsequent diseases. Digital cameras, thermal cameras, and optical filters have become available at a low cost in recent years, while hyperspectral cameras have become increasingly more compact and portable. Furthermore, smartphone cameras have dramatically improved in quality, making them a viable option for rapid, on-site stress detection. Due to these developments in imaging technology, plant stresses can be monitored more easily using handheld and field-deployable methods. Recent advances in machine learning algorithms have allowed for images and spectra to be analyzed and classified in a fully automated and reproducible manner, without the need for complicated image or spectrum analysis methods. This review will highlight recent advances in portable (including smartphone-based) detection methods for biotic and abiotic stresses, discuss data processing and machine learning techniques that can produce results for stress identification and classification, and suggest future directions towards the successful translation of these methods into practical use.

Determination of hardness for maize kernels based on hyperspectral imaging

In order to realize rapid and non-destructive detection of hardness for maize kernels, a method for quantitative hardness measurement was proposed based on hyperspectral imaging technology. Firstly, the regression model of hardness and moisture content was established. Then, based on reflectance hyperspectral imaging at wavelengths within 399.75-1005.80 nm, the prediction model of the moisture content was studied by the partial least squares regression (PLSR) based on the characteristic wavelengths, which was selected through successive projection algorithm (SPA). Finally, the hardness prediction model was validated by combing the prediction model of moisture content with the regression model of hardness. The coefficient of determination (R²), the root mean square error (RMSE) the ratio of performance-to-deviation (RPD) and the ratio of error range (RER) of hardness prediction were 0.912, 17.76 MPa, 3.41 and 14, respectively. Therefore, this study provided a method for rapid and non-destructive detection of hardness of maize kernels.

Hyperspectral imaging for accurate determination of rice variety using a deep learning network with multi-feature fusion

The phenomena of rice adulteration and shoddy rice arise continuously in high-quality rice and reduce the interests of producers, consumers and traders. Hyperspectral imaging (HSI) was conducted to determine rice variety using a deep learning network with multiple features, namely, spectroscopy, texture and morphology. HSI images of 10 representative high-quality rice varieties in China were measured. Spectroscopy and morphology were extracted from HSI images and binary images in region of interest, respectively. And texture was obtained from the monochromatic images of characteristic wavelengths which were highly correlated with rice varieties. A deep learning network, namely principal component analysis network (PCANet), was adopted with these features to develop classification models for determining rice variety, and machine learning methods as K-nearest neighbour and random forest were used to compare with PCANet. Meanwhile, multivariate scatter correction, standard normal variate, Savitzky-Golay smoothing and Savitzky-Golay's first-order were applied to eliminate spectral interference, and principal component analysis (PCA) was performed to obtain the main information of high-dimensional features. Multi-feature fusion improved recognition accuracy, and PCANet demonstrated considerable advantage in classification performance. The best result was achieved by PCANet with PCA-processed spectroscopic and texture features with correct classification rates of 98.66% and 98.57% for the training and prediction sets, respectively. In summary, the proposed method provides an accurate identification of rice variety and can be easily extended to the classification, attribution and grading of other agricultural products.