A New Method for Counting Reproductive Structures in Digitized Herbarium Specimens Using Mask R-CNN

Davis, Charles C.; Champ, Julien; Park, Daniel; Breckheimer, Ian; Lyra, Goia de Mattos; Xie, Junxi; Joly, Alexis; Tarapore, Dharmesh; Ellison, Aaron M.; Bonnet, Pierre

doi:10.3389/fpls.2020.01129

Cited by 34 publications

(45 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…is was similar to the results of Davis et al [17], indicating that CUS analysis of COPD could greatly improve the diagnosis accuracy of the disease and improve the efficiency of diagnosis and treatment.…”

Section: Discussionsupporting

confidence: 90%

Deep Learning-Based Analysis of the Effect of Cardiac Color Ultrasound on Chronic Obstructive Pulmonary Disease under Mask Region

Chen²,

Chen

2021

Scientific Programming

View full text Add to dashboard Cite

This study was developed to analyze the application effect of cardiac ultrasound (CUS) in chronic obstructive pulmonary disease (COPD) patients. A mask region-based convolutional neural network (Mask R-CNN) algorithm was constructed for lung disease detection based on deep learning algorithms, and it was compared with the RetinaNet algorithm for lung disease detection. The results showed that the sensitivity, specificity, accuracy, and running time of the Mask R-CNN algorithm were statistically greater than those of the RetinaNet algorithm ( P < 0.05 ). A total of 92 cases confirmed with lung diseases by pathology were set as experimental group, including 23 cases of COPD classification for level I, II, III, and IV. In addition, 20 cases of healthy adults were selected as control group. The experimental group was compared with the control group, as the lung function decreased, the right atrium diameter (RAD), right ventricle diameter (RVD), and the right ventricular anterior wall thickness (RVAW) increased, the right ventricular ejection fraction (RVEF) gradually decreased, and the AWT-RV, the interventricular septal thickness (IVST), and right ventricular end-diastole volume (RVEDV) changed greatly in the lung function classification ( P < 0.01 ). It was concluded that the CUS based on the Mask R-CNN algorithm could show the changes in bronchial lumen volume at all levels and could detect and evaluate the lung function diseases.

show abstract

Section: Discussionsupporting

confidence: 90%

Deep Learning-Based Analysis of the Effect of Cardiac Color Ultrasound on Chronic Obstructive Pulmonary Disease under Mask Region

Chen²,

Chen

2021

Scientific Programming

View full text Add to dashboard Cite

show abstract

“…Use of machine learning in phenological scoring of herbarium specimens has recently advanced from lower-order scoring (e.g., presence/absence of reproductive structures; ref. [17]) to higher-order scoring, specifically the detection and counting of individual reproductive structures including buds, flowers, and fruits [18,19]. In contrast to first-order scoring, counting individual reproductive structures provides data that are more valuable for ecological research [20,21].…”

Section: Mask R-cnn Model Underestimates Organ Counts But Results In High Concordance Between Manual-vs Machine-learning-derived Phenologmentioning

confidence: 99%

“…This underestimation was more evident for counts of buds and flowers than for immature and mature fruits (Table 1). Davis et al [18] used a similar machine-learning approach to detect and count reproductive structures on over 3000 herbarium specimens representing six common wildflower species native to the eastern United States. In contrast to the current study, their models produced more accurate counts of flowers and fruits than of buds.…”

Section: Mask R-cnn Model Underestimates Organ Counts But Results In High Concordance Between Manual-vs Machine-learning-derived Phenologmentioning

confidence: 99%

“…Recently, machine learning techniques-specifically, convolutional neural networks (CNN)-have been used to harvest accurate phenological data from imaged herbarium specimens [17][18][19], and represents a promising approach for large-scale and automated phenological data extraction [20]. For example, Lorieul et al [17] used CNN to distinguish fertile from non-fertile specimens (i.e., coarse-scale or first-order scoring; [21]) of thousands of species with an accuracy of 96.3% (percent of specimens correctly classified as fertile or non-fertile).…”

Section: Introductionmentioning

confidence: 99%

“…Machine learning has also been used successfully to detect and count individual reproductive structures on herbarium sheets (i.e., third-order scoring) using instance segmentation (mask R-CNN or regional CNN; [18,19]). Goëau et al [19] trained a model using only 21 manually-scored herbarium sheets bearing a total of 279 buds, 349 open flowers, 196 developing ovaries, and 212 full-sized fruits that resulted in accurate estimates of the number of reproductive structures present on a given herbarium sheet (77.9% accuracy); however, the level of accuracy depended on the type of structure being detected (i.e., flowers vs. fruits).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning Undercounts Reproductive Organs on Herbarium Specimens but Accurately Derives Their Quantitative Phenological Status: A Case Study of Streptanthus tortuosus

Love

Bonnet

Goëau

et al. 2021

Plants

Self Cite

View full text Add to dashboard Cite

Machine learning (ML) can accelerate the extraction of phenological data from herbarium specimens; however, no studies have assessed whether ML-derived phenological data can be used reliably to evaluate ecological patterns. In this study, 709 herbarium specimens representing a widespread annual herb, Streptanthus tortuosus, were scored both manually by human observers and by a mask R-CNN object detection model to (1) evaluate the concordance between ML and manually-derived phenological data and (2) determine whether ML-derived data can be used to reliably assess phenological patterns. The ML model generally underestimated the number of reproductive structures present on each specimen; however, when these counts were used to provide a quantitative estimate of the phenological stage of plants on a given sheet (i.e., the phenological index or PI), the ML and manually-derived PI’s were highly concordant. Moreover, herbarium specimen age had no effect on the estimated PI of a given sheet. Finally, including ML-derived PIs as predictor variables in phenological models produced estimates of the phenological sensitivity of this species to climate, temporal shifts in flowering time, and the rate of phenological progression that are indistinguishable from those produced by models based on data provided by human observers. This study demonstrates that phenological data extracted using machine learning can be used reliably to estimate the phenological stage of herbarium specimens and to detect phenological patterns.

show abstract

From leaves to labels: Building modular machine learning networks for rapid herbarium specimen analysis with LeafMachine2

Weaver,

Smith

2023

Appl Plant Sci

View full text Add to dashboard Cite

PremiseQuantitative plant traits play a crucial role in biological research. However, traditional methods for measuring plant morphology are time consuming and have limited scalability. We present LeafMachine2, a suite of modular machine learning and computer vision tools that can automatically extract a base set of leaf traits from digital plant data sets.MethodsLeafMachine2 was trained on 494,766 manually prepared annotations from 5648 herbarium images obtained from 288 institutions and representing 2663 species; it employs a set of plant component detection and segmentation algorithms to isolate individual leaves, petioles, fruits, flowers, wood samples, buds, and roots. Our landmarking network automatically identifies and measures nine pseudo‐landmarks that occur on most broadleaf taxa. Text labels and barcodes are automatically identified by an archival component detector and are prepared for optical character recognition methods or natural language processing algorithms.ResultsLeafMachine2 can extract trait data from at least 245 angiosperm families and calculate pixel‐to‐metric conversion factors for 26 commonly used ruler types.DiscussionLeafMachine2 is a highly efficient tool for generating large quantities of plant trait data, even from occluded or overlapping leaves, field images, and non‐archival data sets. Our project, along with similar initiatives, has made significant progress in removing the bottleneck in plant trait data acquisition from herbarium specimens and shifted the focus toward the crucial task of data revision and quality control.

show abstract

A New Method for Counting Reproductive Structures in Digitized Herbarium Specimens Using Mask R-CNN

Abstract: reproductive features of herbarium specimens, thus providing high-quality data with which to investigate plant responses to ongoing climatic change.

Cited by 34 publications

References 35 publications

Deep Learning-Based Analysis of the Effect of Cardiac Color Ultrasound on Chronic Obstructive Pulmonary Disease under Mask Region

Deep Learning-Based Analysis of the Effect of Cardiac Color Ultrasound on Chronic Obstructive Pulmonary Disease under Mask Region

Machine Learning Undercounts Reproductive Organs on Herbarium Specimens but Accurately Derives Their Quantitative Phenological Status: A Case Study of Streptanthus tortuosus

From leaves to labels: Building modular machine learning networks for rapid herbarium specimen analysis with LeafMachine2

Contact Info

Product

Resources

About