Deep learning and citizen science enable automated plant trait predictions from photographs.
Ontology highlight
ABSTRACT:
SUBMITTER: Schiller C
PROVIDER: S-EPMC8361087 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Citizen science programs using organism photographs have become popular, but there are two problems related to photographs. One problem is the low quality of photographs. It is laborious to identify species in photographs taken outdoors because they are out of focus, partially invisible, or under different lighting conditions. The other is difficulty for non-experts to identify species. Organisms usually have interspecific similarity and intraspecific variation, which hinder species identification by non-experts. Deep learning solves these problems and increases the availability of organism photographs. We trained a deep convolutional neural network, Xception, to identify bee species using various quality of bee photographs that were taken by citizens. These bees belonged to two honey bee species and 10 bumble bee species with interspecific similarity and intraspecific variation. We investigated the accuracy of species identification by biologists and deep learning. The accuracy of species identification by Xception (83.4%) was much higher than that of biologists (53.7%). When we grouped bee photographs by different colors resulting from intraspecific variation in addition to species, the accuracy of species identification by Xception increased to 84.7%. The collaboration with deep learning and experts will increase the reliability of species identification and their use for scientific researches.
| S-EPMC8786926 | biostudies-literature
Project description:Abstract Premise Petal color is an ecologically important trait, and uncovering color variation over a geographic range, particularly in species with large distributions and/or short bloom times, requires extensive fieldwork. We have developed an alternative method that segments images from citizen science repositories using Python and k‐means clustering in the hue‐saturation‐value (HSV) color space. Methods Our method uses k‐means clustering to aggregate like‐color pixels in sample images to generate the HSV color space encapsulating the color range of petals. Using the HSV values, our method isolates photographs containing clusters in that range and bins them into a classification scheme based on user‐defined categories. Results We demonstrate the application of this method using two species: one with a continuous range of variation of pink‐purple petals in Geranium maculatum, and one with a binary classification of white versus blue in Linanthus parryae. We demonstrate results that are repeatable and accurate. Discussion This method provides a flexible, robust, and easily adjustable approach for the classification of color images from citizen science repositories. By using color to classify images, this pipeline sidesteps many of the issues encountered using more traditional computer vision applications. This approach provides a tool for making use of large citizen scientist data sets.
| S-EPMC9934523 | biostudies-literature
Project description:Deep learning may transform health care, but model development has largely been dependent on availability of advanced technical expertise. Herein we present the development of a deep learning model by clinicians without coding, which predicts reported sex from retinal fundus photographs. A model was trained on 84,743 retinal fundus photos from the UK Biobank dataset. External validation was performed on 252 fundus photos from a tertiary ophthalmic referral center. For internal validation, the area under the receiver operating characteristic curve (AUROC) of the code free deep learning (CFDL) model was 0.93. Sensitivity, specificity, positive predictive value (PPV) and accuracy (ACC) were 88.8%, 83.6%, 87.3% and 86.5%, and for external validation were 83.9%, 72.2%, 78.2% and 78.6% respectively. Clinicians are currently unaware of distinct retinal feature variations between males and females, highlighting the importance of model explainability for this task. The model performed significantly worse when foveal pathology was present in the external validation dataset, ACC: 69.4%, compared to 85.4% in healthy eyes, suggesting the fovea is a salient region for model performance OR (95% CI): 0.36 (0.19, 0.70) p = 0.0022. Automated machine learning (AutoML) may enable clinician-driven automated discovery of novel insights and disease biomarkers.
| S-EPMC8119673 | biostudies-literature
Project description:Global monitoring of disease vectors is undoubtedly becoming an urgent need as the human population rises and becomes increasingly mobile, international commercial exchanges increase, and climate change expands the habitats of many vector species. Traditional surveillance of mosquitoes, vectors of many diseases, relies on catches, which requires regular manual inspection and reporting, and dedicated personnel, making large-scale monitoring difficult and expensive. New approaches are solving the problem of scalability by relying on smartphones and the Internet to enable novel community-based and digital observatories, where people can upload pictures of mosquitoes whenever they encounter them. An example is the Mosquito Alert citizen science system, which includes a dedicated mobile phone app through which geotagged images are collected. This system provides a viable option for monitoring the spread of various mosquito species across the globe, although it is partly limited by the quality of the citizen scientists' photos. To make the system useful for public health agencies, and to give feedback to the volunteering citizens, the submitted images are inspected and labeled by entomology experts. Although citizen-based data collection can greatly broaden disease-vector monitoring scales, manual inspection of each image is not an easily scalable option in the long run, and the system could be improved through automation. Based on Mosquito Alert's curated database of expert-validated mosquito photos, we trained a deep learning model to find tiger mosquitoes (Aedes albopictus), a species that is responsible for spreading chikungunya, dengue, and Zika among other diseases. The highly accurate 0.96 area under the receiver operating characteristic curve score promises not only a helpful pre-selector for the expert validation process but also an automated classifier giving quick feedback to the app participants, which may help to keep them motivated. In the paper, we also explored the possibilities of using the model to improve future data collection quality as a feedback loop.
| S-EPMC7907246 | biostudies-literature
Project description:Trait-based ecology is greatly informed by large datasets for the analyses of inter- and intraspecific trait variation (ITV) in plants. This is especially true in trait-based agricultural research where crop ITV is high, yet crop trait data remains limited. Based on farmer-led collections, we developed and evaluated the first citizen science plant trait initiative. Here we generated a dataset of eight leaf traits for a commercially important crop species (Daucus carota), sampled from two distinct regions in Canada, which is 25-fold larger than datasets available in existing trait databases. Citizen-collected trait data supported analyses addressing theoretical and applied questions related to (i) intraspecific trait dimensionality, (ii) the extent and drivers of ITV, and (iii) the sampling intensity needed to derive accurate trait values. Citizen science is a viable means to enhance functional trait data coverage across terrestrial ecosystems, and in doing so, can directly support theoretical and applied trait-based analyses of plants.
| S-EPMC6823441 | biostudies-literature
Project description:A model’s ability to express its own predictive uncertainty is an essential attribute for maintaining clinical user confidence as computational biomarkers are deployed into real-world medical settings. In the domain of cancer digital histopathology, we describe a clinically-oriented approach to uncertainty quantification for whole-slide images, estimating uncertainty using dropout and calculating thresholds on training data to establish cutoffs for low- and high-confidence predictions. We train models to identify lung adenocarcinoma vs. squamous cell carcinoma and show that high-confidence predictions outperform predictions without uncertainty, in both cross-validation and testing on two large external datasets spanning multiple institutions. Our testing strategy closely approximates real-world application, with predictions generated on unsupervised, unannotated slides using predetermined thresholds. Furthermore, we show that uncertainty thresholding remains reliable in the setting of domain shift, with accurate high-confidence predictions of adenocarcinoma vs. squamous cell carcinoma for out-of-distribution, non-lung cancer cohorts. Safe clinical deployment of deep learning models for digital pathology requires reliable estimates of predictive uncertainty. Here the authors describe an algorithm for quantifying whole-slide image uncertainty, demonstrating their approach with models trained to distinguish lung cancer subtypes.
| S-EPMC9630455 | biostudies-literature
Project description:PURPOSE:To assess the utility of deep learning in the detection of geographic atrophy (GA) from color fundus photographs and to explore potential utility in detecting central GA (CGA). DESIGN:A deep learning model was developed to detect the presence of GA in color fundus photographs, and 2 additional models were developed to detect CGA in different scenarios. PARTICIPANTS:A total of 59?812 color fundus photographs from longitudinal follow-up of 4582 participants in the Age-Related Eye Disease Study (AREDS) dataset. Gold standard labels were from human expert reading center graders using a standardized protocol. METHODS:A deep learning model was trained to use color fundus photographs to predict GA presence from a population of eyes with no AMD to advanced AMD. A second model was trained to predict CGA presence from the same population. A third model was trained to predict CGA presence from the subset of eyes with GA. For training and testing, 5-fold cross-validation was used. For comparison with human clinician performance, model performance was compared with that of 88 retinal specialists. MAIN OUTCOME MEASURES:Area under the curve (AUC), accuracy, sensitivity, specificity, and precision. RESULTS:The deep learning models (GA detection, CGA detection from all eyes, and centrality detection from GA eyes) had AUCs of 0.933-0.976, 0.939-0.976, and 0.827-0.888, respectively. The GA detection model had accuracy, sensitivity, specificity, and precision of 0.965 (95% confidence interval [CI], 0.959-0.971), 0.692 (0.560-0.825), 0.978 (0.970-0.985), and 0.584 (0.491-0.676), respectively, compared with 0.975 (0.971-0.980), 0.588 (0.468-0.707), 0.982 (0.978-0.985), and 0.368 (0.230-0.505) for the retinal specialists. The CGA detection model had values of 0.966 (0.957-0.975), 0.763 (0.641-0.885), 0.971 (0.960-0.982), and 0.394 (0.341-0.448). The centrality detection model had values of 0.762 (0.725-0.799), 0.782 (0.618-0.945), 0.729 (0.543-0.916), and 0.799 (0.710-0.888). CONCLUSIONS:A deep learning model demonstrated high accuracy for the automated detection of GA. The AUC was noninferior to that of human retinal specialists. Deep learning approaches may also be applied to the identification of CGA. The code and pretrained models are publicly available at https://github.com/ncbi-nlp/DeepSeeNet.
| S-EPMC6810830 | biostudies-literature
Project description:Premise:Citizen science platforms for sharing photographed digital vouchers, such as iNaturalist, are a promising source of phenology data, but methods and best practices for use have not been developed. Here we introduce methods using Yucca flowering phenology as a case study, because drivers of Yucca phenology are not well understood despite the need to synchronize flowering with obligate pollinators. There is also evidence of recent anomalous winter flowering events, but with unknown spatiotemporal extents. Methods:We collaboratively developed a rigorous, consensus-based approach for annotating and sharing whole plant and flower presence data from iNaturalist and applied it to Yucca records. We compared spatiotemporal flowering coverage from our annotations with other broad-scale monitoring networks (e.g., the National Phenology Network) in order to determine the unique value of photograph-based citizen science resources. Results:Annotations from iNaturalist were uniquely able to delineate extents of unusual flowering events in Yucca. These events, which occurred in two different regions of the Desert Southwest, did not appear to disrupt the typical-period flowering. Discussion:Our work demonstrates that best practice approaches to scoring iNaturalist records provide fine-scale delimitation of phenological events. This approach can be applied to other plant groups to better understand how phenology responds to changing climate.
| S-EPMC6976896 | biostudies-literature
Project description:Computer vision models that can recognize plant diseases in the field would be valuable tools for disease management and resistance breeding. Generating enough data to train these models is difficult, however, since only trained experts can accurately identify symptoms. In this study, we describe and implement a two-step method for generating a large amount of high-quality training data with minimal expert input. First, experts located symptoms of northern leaf blight (NLB) in field images taken by unmanned aerial vehicles (UAVs), annotating them quickly at low resolution. Second, non-experts were asked to draw polygons around the identified diseased areas, producing high-resolution ground truths that were automatically screened based on agreement between multiple workers. We then used these crowdsourced data to train a convolutional neural network (CNN), feeding the output into a conditional random field (CRF) to segment images into lesion and non-lesion regions with accuracy of 0.9979 and F1 score of 0.7153. The CNN trained on crowdsourced data showed greatly improved spatial resolution compared to one trained on expert-generated data, despite using only one fifth as many expert annotations. The final model was able to accurately delineate lesions down to the millimeter level from UAV-collected images, the finest scale of aerial plant disease detection achieved to date. The two-step approach to generating training data is a promising method to streamline deep learning approaches for plant disease detection, and for complex plant phenotyping tasks in general.
| S-EPMC6927297 | biostudies-literature
Project description:ObjectivesTo present and validate a deep ensemble algorithm to detect diabetic retinopathy (DR) and diabetic macular oedema (DMO) using retinal fundus images.MethodsA total of 8739 retinal fundus images were collected from a retrospective cohort of 3285 patients. For detecting DR and DMO, a multiple improved Inception-v4 ensembling approach was developed. We measured the algorithm's performance and made a comparison with that of human experts on our primary dataset, while its generalization was assessed on the publicly available Messidor-2 dataset. Also, we investigated systematically the impact of the size and number of input images used in training on model's performance, respectively. Further, the time budget of training/inference versus model performance was analyzed.ResultsOn our primary test dataset, the model achieved an 0.992 (95% CI, 0.989-0.995) AUC corresponding to 0.925 (95% CI, 0.916-0.936) sensitivity and 0.961 (95% CI, 0.950-0.972) specificity for referable DR, while the sensitivity and specificity for ophthalmologists ranged from 0.845 to 0.936, and from 0.912 to 0.971, respectively. For referable DMO, our model generated an AUC of 0.994 (95% CI, 0.992-0.996) with a 0.930 (95% CI, 0.919-0.941) sensitivity and 0.971 (95% CI, 0.965-0.978) specificity, whereas ophthalmologists obtained sensitivities ranging between 0.852 and 0.946, and specificities ranging between 0.926 and 0.985.ConclusionThis study showed that the deep ensemble model exhibited excellent performance in detecting DR and DMO, and had good robustness and generalization, which could potentially help support and expand DR/DMO screening programs.
| S-EPMC9232645 | biostudies-literature