Dataset Information

LeafMachine: Using machine learning to automate leaf trait extraction from digitized herbarium specimens.

ABSTRACT:

Premise

Obtaining phenotypic data from herbarium specimens can provide important insights into plant evolution and ecology but requires significant manual effort and time. Here, we present LeafMachine, an application designed to autonomously measure leaves from digitized herbarium specimens or leaf images using an ensemble of machine learning algorithms.

Methods and results

We trained LeafMachine on 2685 randomly sampled specimens from 138 herbaria and evaluated its performance on specimens spanning 20 diverse families and varying widely in resolution, quality, and layout. LeafMachine successfully extracted at least one leaf measurement from 82.0% and 60.8% of high- and low-resolution images, respectively. Of the unmeasured specimens, only 0.9% and 2.1% of high- and low-resolution images, respectively, were visually judged to have measurable leaves.

Conclusions

This flexible autonomous tool has the potential to vastly increase available trait information from herbarium specimens, and inform a multitude of evolutionary and ecological studies.

SUBMITTER: Weaver WN

PROVIDER: S-EPMC7328653 | biostudies-literature | 2020 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

LeafMachine: Using machine learning to automate leaf trait extraction from digitized herbarium specimens.

Weaver William N WN Ng Julienne J Laport Robert G RG

Applications in plant sciences 20200601 6

<h4>Premise</h4>Obtaining phenotypic data from herbarium specimens can provide important insights into plant evolution and ecology but requires significant manual effort and time. Here, we present LeafMachine, an application designed to autonomously measure leaves from digitized herbarium specimens or leaf images using an ensemble of machine learning algorithms.<h4>Methods and results</h4>We trained LeafMachine on 2685 randomly sampled specimens from 138 herbaria and evaluated its performance on ...[more]

PMID: 32626609

Similar Datasets

Project description:Phenology-the timing of life-history events-is a key trait for understanding responses of organisms to climate. The digitization and online mobilization of herbarium specimens is rapidly advancing our understanding of plant phenological response to climate and climatic change. The current practice of manually harvesting data from individual specimens, however, greatly restricts our ability to scale-up data collection. Recent investigations have demonstrated that machine-learning approaches can facilitate this effort. However, present attempts have focused largely on simplistic binary coding of reproductive phenology (e.g., presence/absence of flowers). Here, we use crowd-sourced phenological data of buds, flowers, and fruits from >3,000 specimens of six common wildflower species of the eastern United States (Anemone canadensis L., A. hepatica L., A. quinquefolia L., Trillium erectum L., T. grandiflorum (Michx.) Salisb., and T. undulatum Wild.) to train models using Mask R-CNN to segment and count phenological features. A single global model was able to automate the binary coding of each of the three reproductive stages with >87% accuracy. We also successfully estimated the relative abundance of each reproductive structure on a specimen with ≥90% accuracy. Precise counting of features was also successful, but accuracy varied with phenological stage and taxon. Specifically, counting flowers was significantly less accurate than buds or fruits likely due to their morphological variability on pressed specimens. Moreover, our Mask R-CNN model provided more reliable data than non-expert crowd-sourcers but not botanical experts, highlighting the importance of high-quality human training data. Finally, we also demonstrated the transferability of our model to automated phenophase detection and counting of the three Trillium species, which have large and conspicuously-shaped reproductive organs. These results highlight the promise of our two-phase crowd-sourcing and machine-learning pipeline to segment and count reproductive features of herbarium specimens, thus providing high-quality data with which to investigate plant responses to ongoing climatic change.

Project description:BackgroundEvidence-based medicine requires synthesis of research through rigorous and time-intensive systematic literature reviews (SLRs), with significant resource expenditure for data extraction from scientific publications. Machine learning may enable the timely completion of SLRs and reduce errors by automating data identification and extraction.MethodsWe evaluated the use of machine learning to extract data from publications related to SLRs in oncology (SLR 1) and Fabry disease (SLR 2). SLR 1 predominantly contained interventional studies and SLR 2 observational studies. Predefined key terms and data were manually annotated to train and test bidirectional encoder representations from transformers (BERT) and bidirectional long-short-term memory machine learning models. Using human annotation as a reference, we assessed the ability of the models to identify biomedical terms of interest (entities) and their relations. We also pretrained BERT on a corpus of 100,000 open access clinical publications and/or enhanced context-dependent entity classification with a conditional random field (CRF) model. Performance was measured using the F1 score, a metric that combines precision and recall. We defined successful matches as partial overlap of entities of the same type.ResultsFor entity recognition, the pretrained BERT+CRF model had the best performance, with an F1 score of 73% in SLR 1 and 70% in SLR 2. Entity types identified with the highest accuracy were metrics for progression-free survival (SLR 1, F1 score 88%) or for patient age (SLR 2, F1 score 82%). Treatment arm dosage was identified less successfully (F1 scores 60% [SLR 1] and 49% [SLR 2]). The best-performing model for relation extraction, pretrained BERT relation classification, exhibited F1 scores higher than 90% in cases with at least 80 relation examples for a pair of related entity types.ConclusionsThe performance of BERT is enhanced by pretraining with biomedical literature and by combining with a CRF model. With refinement, machine learning may assist with manual data extraction for SLRs.

Dataset Information

LeafMachine: Using machine learning to automate leaf trait extraction from digitized herbarium specimens.

Premise

Methods and results

Conclusions

Publications

LeafMachine: Using machine learning to automate leaf trait extraction from digitized herbarium specimens.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets