Quantifying physiological trait variation with automated hyperspectral imaging in rice
Ontology highlight
ABSTRACT:
SUBMITTER: Ting T
PROVIDER: S-EPMC10548215 | biostudies-literature | 2023 Jan
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:ObjectivesEarly melanoma detection decreases morbidity and mortality. Early detection classically involves dermoscopy to identify suspicious lesions for which biopsy is indicated. Biopsy and histological examination then diagnose benign nevi, atypical nevi, or cancerous growths. With current methods, a considerable number of unnecessary biopsies are performed as only 11% of all biopsied, suspicious lesions are actually melanomas. Thus, there is a need for more advanced noninvasive diagnostics to guide the decision of whether or not to biopsy. Artificial intelligence can generate screening algorithms that transform a set of imaging biomarkers into a risk score that can be used to classify a lesion as a melanoma or a nevus by comparing the score to a classification threshold. Melanoma imaging biomarkers have been shown to be spectrally dependent in Red, Green, Blue (RGB) color channels, and hyperspectral imaging may further enhance diagnostic power. The purpose of this study was to use the same melanoma imaging biomarkers previously described, but over a wider range of wavelengths to determine if, in combination with machine learning algorithms, this could result in enhanced melanoma detection.MethodsWe used the melanoma advanced imaging dermatoscope (mAID) to image pigmented lesions assessed by dermatologists as requiring a biopsy. The mAID is a 21-wavelength imaging device in the 350-950 nm range. We then generated imaging biomarkers from these hyperspectral dermoscopy images, and, with the help of artificial intelligence algorithms, generated a melanoma Q-score for each lesion (0 = nevus, 1 = melanoma). The Q-score was then compared to the histopathologic diagnosis.ResultsThe overall sensitivity and specificity of hyperspectral dermoscopy in detecting melanoma when evaluated in a set of lesions selected by dermatologists as requiring biopsy was 100% and 36%, respectively.ConclusionWith widespread application, and if validated in larger clinical trials, this non-invasive methodology could decrease unnecessary biopsies and potentially increase life-saving early detection events. Lasers Surg. Med. 51:214-222, 2019. © 2019 The Authors. Lasers in Surgery and Medicine Published by Wiley Periodicals, Inc.
| S-EPMC6519386 | biostudies-literature
Project description:Cell communication is primarily regulated by secreted proteins, whose inhomogeneous secretion often indicates physiological disorder. Parallel monitoring of innate protein-secretion kinetics from individual cells is thus crucial to unravel systemic malfunctions. Here, we report a label-free, high-throughput method for parallel, in vitro, and real-time analysis of specific single-cell signaling using hyperspectral photonic crystal resonant technology. Heterogeneity in physiological thrombopoietin expression from individual HepG2 liver cells in response to platelet desialylation was quantified demonstrating how mapping real-time protein secretion can provide a simple, yet powerful approach for studying complex physiological systems regulating protein production at single-cell resolution.
| S-EPMC6310807 | biostudies-literature
Project description: Not available
| S-BSST32 | biostudies-other
Project description:Hyperspectral Imaging (HSI) is a relatively new medical imaging modality that exploits an area of diagnostic potential formerly untouched. Although exploratory translational and clinical studies exist, no surgical HSI datasets are openly accessible to the general scientific community. To address this bottleneck, this publication releases HeiPorSPECTRAL ( https://www.heiporspectral.org ; https://doi.org/10.5281/zenodo.7737674 ), the first annotated high-quality standardized surgical HSI dataset. It comprises 5,758 spectral images acquired with the TIVITA® Tissue and annotated with 20 physiological porcine organs from 8 pigs per organ distributed over a total number of 11 pigs. Each HSI image features a resolution of 480 × 640 pixels acquired over the 500-1000 nm wavelength range. The acquisition protocol has been designed such that the variability of organ spectra as a function of several parameters including the camera angle and the individual can be assessed. A comprehensive technical validation confirmed both the quality of the raw data and the annotations. We envision potential reuse within this dataset, but also its reuse as baseline data for future research questions outside this dataset. Measurement(s) Spectral Reflectance Technology Type(s) Hyperspectral Imaging Sample Characteristic - Organism Sus scrofa.
| S-EPMC10290660 | biostudies-literature
Project description:Hyperspectral cameras onboard unmanned aerial vehicles (UAVs) have recently emerged for monitoring crop traits at the sub-field scale. Different physical, statistical, and hybrid methods for crop trait retrieval have been developed. However, spectra collected from UAVs can be confounded by various issues, including illumination variation throughout the crop growing season, the effect of which on the retrieval performance is not well understood at present. In this study, four retrieval methods are compared, in terms of retrieving the leaf area index (LAI), fractional vegetation cover (fCover), and canopy chlorophyll content (CCC) of potato plants over an agricultural field for six dates during the growing season. We analyzed: (1) The standard look-up table method (LUTstd), (2) an improved (regularized) LUT method that involves variable correlation (LUTreg), (3) hybrid methods, and (4) random forest regression without (RF) and with (RFexp) the exposure time as an additional explanatory variable. The Soil-Leaf-Canopy (SLC) model was used in association with the LUT-based inversion and hybrid methods, while the statistical modelling methods (RF and RFexp) relied entirely on in situ data. The results revealed that RFexp was the best-performing method, yielding the highest accuracies, in terms of the normalized root mean square error (NRMSE), for LAI (5.36%), fCover (5.87%), and CCC (15.01%). RFexp was able to reduce the effects of illumination variability and cloud shadows. LUTreg outperformed the other two retrieval methods (hybrid methods and LUTstd), with an NRMSE of 9.18% for LAI, 10.46% for fCover, and 12.16% for CCC. Conversely, LUTreg led to lower accuracies than those derived from RF for LAI (5.51%) and for fCover (6.23%), but not for CCC (16.21%). Therefore, the machine learning approaches-in particular, RF-appear to be the most promising retrieval methods for application to UAV-based hyperspectral data.
| S-EPMC7613394 | biostudies-literature
Project description:Various rice diseases threaten the growth of rice. It is of great importance to achieve the rapid and accurate detection of rice diseases for precise disease prevention and control. Hyperspectral imaging (HSI) was performed to detect rice leaf diseases in four different varieties of rice. Considering that it costs much time and energy to develop a classifier for each variety of rice, deep transfer learning was firstly introduced to rice disease detection across different rice varieties. Three deep transfer learning methods were adapted for 12 transfer tasks, namely, fine-tuning, deep CORrelation ALignment (CORAL), and deep domain confusion (DDC). A self-designed convolutional neural network (CNN) was set as the basic network of the deep transfer learning methods. Fine-tuning achieved the best transferable performance with an accuracy of over 88% for the test set of the target domain in the majority of transfer tasks. Deep CORAL obtained an accuracy of over 80% in four of all the transfer tasks, which was superior to that of DDC. A multi-task transfer strategy has been explored with good results, indicating the potential of both pair-wise, and multi-task transfers. A saliency map was used for the visualization of the key wavelength range captured by CNN with and without transfer learning. The results indicated that the wavelength range with and without transfer learning was overlapped to some extent. Overall, the results suggested that deep transfer learning methods could perform rice disease detection across different rice varieties. Hyperspectral imaging, in combination with the deep transfer learning method, is a promising possibility for the efficient and cost-saving field detection of rice diseases among different rice varieties.
| S-EPMC8511421 | biostudies-literature
Project description:With progress of genetic sequencing technology, plant genomics has experienced rapid development and subsequently triggered the progress of plant phenomics. In this study, a high-throughput hyperspectral imaging system (HHIS) was developed to obtain 1,540 hyperspectral indices at whole-plant level during tillering, heading, and ripening stages. These indices were used to quantify traditional agronomic traits and to explore genetic variation. We performed genome-wide association study (GWAS) of these indices and traditional agronomic traits in a global rice collection of 529 accessions. With the genome-level suggestive P-value threshold, 989 loci were identified. Of the 1,540 indices, we detected 502 significant indices (designated as hyper-traits) that exhibited phenotypic and genetic relationship with traditional agronomic traits and had high heritability. Many hyper-trait-associated loci could not be detected using traditional agronomic traits. For example, we identified a candidate gene controlling chlorophyll content (Chl). This gene, which was not identified based on Chl, was significantly associated with a chlorophyll-related hyper-trait in GWAS and was demonstrated to control Chl. Moreover, our study demonstrates that red edge (680-760?nm) is vital for rice research for phenotypic and genetic insights. Thus, combination of HHIS and GWAS provides a novel platform for dissection of complex traits and for crop breeding.
| S-EPMC5493659 | biostudies-literature
Project description:Microscopy and omics are complementary approaches to probe the molecular state of cells in health and disease, combining granularity with scalability. While important advances have been achieved over the last decade in each area, integrating both imaging- and sequencing-based assays on the same cell has proven challenging. In this study, a new approach called HyperSeq that combines hyperspectral autofluorescence imaging with transcriptomics on the same cell is demonstrated. HyperSeq was applied to Michigan Cancer Foundation 7 (MCF-7) breast cancer cells and identified a subpopulation of cells exhibiting bright autofluorescence rings at the plasma membrane in optical channel 13 (ex = 431 nm, em = 594 nm). Correlating the presence of a ring with the gene expression in the same cell indicated that ringed cells are more likely to express hallmark genes of apoptosis and gene silencing and less likely to express genes associated with ATP production. Further, correlation of cell morphology with gene expression suggested that multiple members of the spliceosome were upregulated in larger cells. A number of genes, albeit evenly expressed across cell sizes, exhibited higher usage of specific exons in larger or smaller cells. Finally, correlation between gene expression and fluorescence within the spectral range of Nicotinamide adenine dinucleotide hydrogen (NADH) provided preliminary insight into the metabolic states of cells. These observations provided a link between the cell’s optical spectrum and its internal molecular state, demonstrating the utility of HyperSeq to study cell biology at single cell resolution by integrating spectral, morphological and transcriptomic analyses into a single, streamlined workflow.
2024-02-05 | GSE254034 | GEO
Project description:Hyperspectral imaging (HSI) can measure both spatial (morphological) and spectral (biochemical) information from biological tissues. While HSI appears promising for biomedical applications, interpretation of hyperspectral images can be challenging when data is acquired in complex biological environments. Variations in surface topology or optical power distribution at the sample, encountered for example during endoscopy, can lead to errors in post-processing of the HSI data, compromising disease diagnostic capabilities. Here, we propose a background correction method to compensate for such variations, which estimates the optical properties of illumination at the target based on the normalised spectral profile of the light source and the measured HSI intensity values at a fixed wavelength where the absorption characteristics of the sample are relatively low (in this case, 800 nm). We demonstrate the feasibility of the proposed method by imaging blood samples, tissue-mimicking phantoms, and ex vivo chicken tissue. Moreover, using synthetic HSI data composed from experimentally measured spectra, we show the proposed method would improve statistical analysis of HSI data. The proposed method could help the implementation of HSI techniques in practical clinical applications, where controlling the illumination pattern and power is difficult.
| S-EPMC7069652 | biostudies-literature
Project description:PremisePhysiological processes may vary within leaf laminae; however, the accompanying heterogeneity in leaf venation is rarely investigated because its quantification can be time consuming. Here we introduce accelerated protocols using existing software to increase sample throughput and ask whether laminae venation varies among three crop types and four subspecies of Brassica rapa.MethodsFAA (formaldehyde, glacial acetic acid, and ethanol)-fixed samples were stored in ethanol. Without performing any additional clearing or staining, we tested two methods of image acquisition at three locations along the proximal-distal axis of the laminae and estimated the patterns of venation using the program phenoVein. We developed and made available an R script to handle the phenoVein output and then analyzed our data using linear mixed-effects models.ResultsBeyond fixation and storage, staining and clearing are not necessary to estimate leaf venation using phenoVein if the images are acquired using a stereomicroscope. All estimates of venation required some manual adjustment. We found a significant effect of location within the laminae for all aspects of venation.DiscussionBy removing the clearing and staining steps and utilizing the semi-automated program phenoVein, we quickly and cheaply acquired leaf venation data. Venation may be an important target for crop breeding efforts, particularly if intralaminar variation correlates with variation in physiological processes, which remains an open question.
| S-EPMC7249269 | biostudies-literature