Dataset Information

A Perspective on Plant Phenomics: Coupling Deep Learning and Near-Infrared Spectroscopy.

ABSTRACT: The trait-based approach in plant ecology aims at understanding and classifying the diversity of ecological strategies by comparing plant morphology and physiology across organisms. The major drawback of the approach is that the time and financial cost of measuring the traits on many individuals and environments can be prohibitive. We show that combining near-infrared spectroscopy (NIRS) with deep learning resolves this limitation by quickly, non-destructively, and accurately measuring a suite of traits, including plant morphology, chemistry, and metabolism. Such an approach also allows to position plants within the well-known CSR triangle that depicts the diversity of plant ecological strategies. The processing of NIRS through deep learning identifies the effect of growth conditions on trait values, an issue that plagues traditional statistical approaches. Together, the coupling of NIRS and deep learning is a promising high-throughput approach to capture a range of ecological information on plant diversity and functioning and can accelerate the creation of extensive trait databases.

SUBMITTER: Vasseur F

PROVIDER: S-EPMC9163986 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Perspective on Plant Phenomics: Coupling Deep Learning and Near-Infrared Spectroscopy.

Vasseur François F Cornet Denis D Beurier Grégory G Messier Julie J Rouan Lauriane L Bresson Justine J Ecarnot Martin M Stahl Mark M Heumos Simon S Gérard Marianne M Reijnen Hans H Tillard Pascal P Lacombe Benoît B Emanuel Amélie A Floret Justine J Estarague Aurélien A Przybylska Stefania S Sartori Kevin K Gillespie Lauren M LM Baron Etienne E Kazakou Elena E Vile Denis D Violle Cyrille C

Frontiers in plant science 20220520

The trait-based approach in plant ecology aims at understanding and classifying the diversity of ecological strategies by comparing plant morphology and physiology across organisms. The major drawback of the approach is that the time and financial cost of measuring the traits on many individuals and environments can be prohibitive. We show that combining near-infrared spectroscopy (NIRS) with deep learning resolves this limitation by quickly, non-destructively, and accurately measuring a suite o ...[more]

PMID: 35668791

Similar Datasets

Project description:BackgroundNear-infrared spectroscopy (NIRS) has the potential to be a useful tool for assessing key entomological parameters of malaria-transmitting mosquitoes, including age, infectious status and species identity. However, before NIRS can be reliably used in the field at scale, methods for killing mosquitoes and conserving samples prior to NIRS scanning need to be further optimized. Historically, mosquitoes used in studies have been killed with chloroform, although this approach is not without health hazards and should not be used in human dwellings. For the application of NIRS scanning it is also unclear which mosquito preservation method to use. The aim of the study reported here was to investigate the use of pyrethrum spray, a commercially available insecticide spray in Burkina Faso, for killing mosquitoes METHODS: Laboratory-reared Anopheles gambiae and Anopheles coluzzii were killed using either a pyrethrum insecticide spray routinely used in studies involving indoor mosquito collections (Kaltox Paalga®; Saphyto, Bobo-Dioulasso, Burkina Faso) or chloroform ("gold standard"). Preservative methods were also investigated to determine their impact on NIRS accuracy in predicting the species of laboratory-reared Anopheles and wild-caught mosquito species. After analysis of fresh samples, mosquitoes were stored in 80% ethanol or in silica gel for 2 weeks and re-analyzed by NIRS. In addition, experimentally infected An. coluzzii and wild-caught An. gambiae sensu lato (s.l.) were scanned as fresh samples to determine whether they contained sporozoites, then stored in the preservatives mentioned above for 2 weeks before being re-analyzed.ResultsThe difference in the accuracy of NIRS to differentiate between laboratory-reared An. gambiae mosquitoes and An. coluzzii mosquitoes killed with either insecticide (90%) or chloroform (92%) was not substantial. NIRS had an accuracy of 90% in determining mosquito species for mosquitoes killed with chloroform and preserved in ethanol or silica gel. The accuracy was the same when the pyrethrum spray was used to kill mosquitoes followed by preservation in silica gel, but was lower when ethanol was used as a preservative (80%). Regarding infection status, NIRS was able to differentiate between infected and uninfected mosquitoes, with a slightly lower accuracy for both laboratory and wild-caught mosquitoes preserved in silica gel or ethanol.ConclusionsThe results show that NIRS can be used to classify An. gambiae s.l. species killed by pyrethrum spray with no loss of accuracy. This insecticide may have practical advantages over chloroform for the killing of mosquitoes in NIRS analysis.

Project description:AimsCoronary computed tomography angiography (CCTA) is inferior to intravascular imaging in detecting plaque morphology and quantifying plaque burden. We aim to, for the first time, train a deep-learning (DL) methodology for accurate plaque quantification and characterization in CCTA using near-infrared spectroscopy-intravascular ultrasound (NIRS-IVUS).Methods and resultsSeventy patients were prospectively recruited who underwent CCTA and NIRS-IVUS imaging. Corresponding cross sections were matched using an in-house developed software, and the estimations of NIRS-IVUS for the lumen, vessel wall borders, and plaque composition were used to train a convolutional neural network in 138 vessels. The performance was evaluated in 48 vessels and compared against the estimations of NIRS-IVUS and the conventional CCTA expert analysis. Sixty-four patients (186 vessels, 22 012 matched cross sections) were included. Deep-learning methodology provided estimations that were closer to NIRS-IVUS compared with the conventional approach for the total atheroma volume (ΔDL-NIRS-IVUS: -37.8 ± 89.0 vs. ΔConv-NIRS-IVUS: 243.3 ± 183.7 mm3, variance ratio: 4.262, P < 0.001) and percentage atheroma volume (-3.34 ± 5.77 vs. 17.20 ± 7.20%, variance ratio: 1.578, P < 0.001). The DL methodology detected lesions more accurately than the conventional approach (Area under the curve (AUC): 0.77 vs. 0.67, P < 0.001) and quantified minimum lumen area (ΔDL-NIRS-IVUS: -0.35 ± 1.81 vs. ΔConv-NIRS-IVUS: 1.37 ± 2.32 mm2, variance ratio: 1.634, P < 0.001), maximum plaque burden (4.33 ± 11.83% vs. 5.77 ± 16.58%, variance ratio: 2.071, P = 0.004), and calcific burden (-51.2 ± 115.1 vs. -54.3 ± 144.4, variance ratio: 2.308, P < 0.001) more accurately than conventional approach. The DL methodology was able to segment a vessel on CCTA in 0.3 s.ConclusionsThe DL methodology developed for CCTA analysis from co-registered NIRS-IVUS and CCTA data enables rapid and accurate assessment of lesion morphology and is superior to expert analysts (Clinicaltrials.gov: NCT03556644).

Dataset Information

A Perspective on Plant Phenomics: Coupling Deep Learning and Near-Infrared Spectroscopy.

Publications

A Perspective on Plant Phenomics: Coupling Deep Learning and Near-Infrared Spectroscopy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets