See the published version of this preprint at Plant Methods.
This is a preprint, a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
A new preprint design is coming!
We have improved readability, clarity, accessibility, and opportunities for engagement.
Methodology
Hiranya Samanga Jayakody
University of New South Wales
Corresponding Author
ORCiD: https://orcid.org/0000-0003-0766-2085
License:
This work is licensed under a CC BY 4.0 License. Read Full License
Background: Stomata analysis using microscope imagery provides important insight into plant physiology, health and the surrounding environmental conditions. Plant scientists are now able to conduct automated high-throughput analysis of stomata in microscope data, however, existing detection methods are sensitive to the appearance of stomata in the training images, thereby limiting general applicability. In addition, existing methods only generate bounding-boxes around detected stomata, which require users to implement additional image processing steps to study stomata morphology. In this paper, we develop a fully automated, robust stomata detection algorithm which can also identify individual stomata boundaries regardless of the plant species, sample collection method, imaging technique and magnification level.
Results: The proposed solution consists of three stages. First, the input image is pre-processed to remove any colour space biases occurring from different sample collection and imaging techniques. Then, a Mask R-CNN is applied to estimate individual stomata boundaries. The feature pyramid network embedded in the Mask R-CNN is utilised to identify stomata at different scales. Finally, a statistical filter is implemented at the Mask R-CNN output to reduce the number of false positive generated by the network. The algorithm was tested using 16 datasets from 12 sources, containing over 60,000 stomata. For the first time in this domain, the proposed solution was tested against 7 microscope datasets never seen by the algorithm to show the generalisability of the solution. Results indicated that the proposed approach can detect stomata with a precision, recall, and F-score of 95.10\%, 83.34\%, and 88.61\%, respectively. A separate test conducted by comparing estimated stomata boundary values with manually measured data showed that the proposed method has an IoU score of 0.70; a 7\% improvement over the bounding-box approach.
Conclusions: The proposed method shows robust performance across multiple microscope image datasets of different quality and scale. This generalised stomata detection algorithm allows plant scientists to conduct stomata analysis whilst eliminating the need to re-label and re-train for each new dataset. The open-source code shared with this project can be directly deployed in Google Colab or any other Tensorflow environment.
Keywords
automatic stomata detection, microscope imagery, Mask R-CNN, instance segmentation, high-throughput analysis, machine learning
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Loading...
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Published
View the published article at Plant Methods.
Version 3
Posted 29 Dec, 2020
No community comments so far
Review #2 received
Received 25 Feb, 2021
Editorial decision: Accept
On 25 Feb, 2021
Review #1 received
Received 02 Jan, 2021
Reviewer #2 agreed
On 27 Dec, 2020
Reviewer #1 agreed
On 14 Dec, 2020
Reviewers invited
Invitations sent on 10 Dec, 2020
Editor assigned
On 09 Dec, 2020
Submission checks complete
On 09 Dec, 2020
Editor invited
On 09 Dec, 2020
No comments provided
Review #2 received
Received 27 Nov, 2020
Editorial decision: Minor revision
On 27 Nov, 2020
Reviewer #2 agreed
On 23 Nov, 2020
Review #1 received
Received 14 Nov, 2020
Reviewers invited
Invitations sent on 01 Nov, 2020
Reviewer #1 agreed
On 01 Nov, 2020
Editor assigned
On 05 Oct, 2020
Submission checks complete
On 04 Oct, 2020
Editor invited
On 04 Oct, 2020
No comments provided
Editorial decision: Minor revision
On 25 Sep, 2020
Review #3 received
Received 24 Sep, 2020
Reviewer #3 agreed
On 02 Sep, 2020
Review #1 received
Received 28 Jul, 2020
Review #2 received
Received 28 Jul, 2020
Reviewer #2 agreed
On 07 Jul, 2020
Reviewers invited
Invitations sent on 02 Jul, 2020
Reviewer #1 agreed
On 02 Jul, 2020
Editor assigned
On 11 Jun, 2020
Editor invited
On 10 Jun, 2020
Submission checks complete
On 03 Jun, 2020
First submitted
On 02 Jun, 2020
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
Learn more about our company.
A new preprint design is coming!
We have improved readability, clarity, accessibility, and opportunities for engagement.
See the published version of this preprint at Plant Methods.
This is a preprint, a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
Methodology
Hiranya Samanga Jayakody
University of New South Wales
Corresponding Author
ORCiD: https://orcid.org/0000-0003-0766-2085
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Published
View the published article at Plant Methods.
Version 3
Posted 29 Dec, 2020
No community comments so far
Review #2 received
Received 25 Feb, 2021
Editorial decision: Accept
On 25 Feb, 2021
Review #1 received
Received 02 Jan, 2021
Reviewer #2 agreed
On 27 Dec, 2020
Reviewer #1 agreed
On 14 Dec, 2020
Reviewers invited
Invitations sent on 10 Dec, 2020
Editor assigned
On 09 Dec, 2020
Submission checks complete
On 09 Dec, 2020
Editor invited
On 09 Dec, 2020
No comments provided
Review #2 received
Received 27 Nov, 2020
Editorial decision: Minor revision
On 27 Nov, 2020
Reviewer #2 agreed
On 23 Nov, 2020
Review #1 received
Received 14 Nov, 2020
Reviewers invited
Invitations sent on 01 Nov, 2020
Reviewer #1 agreed
On 01 Nov, 2020
Editor assigned
On 05 Oct, 2020
Submission checks complete
On 04 Oct, 2020
Editor invited
On 04 Oct, 2020
No comments provided
Editorial decision: Minor revision
On 25 Sep, 2020
Review #3 received
Received 24 Sep, 2020
Reviewer #3 agreed
On 02 Sep, 2020
Review #1 received
Received 28 Jul, 2020
Review #2 received
Received 28 Jul, 2020
Reviewer #2 agreed
On 07 Jul, 2020
Reviewers invited
Invitations sent on 02 Jul, 2020
Reviewer #1 agreed
On 02 Jul, 2020
Editor assigned
On 11 Jun, 2020
Editor invited
On 10 Jun, 2020
Submission checks complete
On 03 Jun, 2020
First submitted
On 02 Jun, 2020
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
License:
This work is licensed under a CC BY 4.0 License. Read Full License
View the published article at Plant Methods.
Background: Stomata analysis using microscope imagery provides important insight into plant physiology, health and the surrounding environmental conditions. Plant scientists are now able to conduct automated high-throughput analysis of stomata in microscope data, however, existing detection methods are sensitive to the appearance of stomata in the training images, thereby limiting general applicability. In addition, existing methods only generate bounding-boxes around detected stomata, which require users to implement additional image processing steps to study stomata morphology. In this paper, we develop a fully automated, robust stomata detection algorithm which can also identify individual stomata boundaries regardless of the plant species, sample collection method, imaging technique and magnification level.
Results: The proposed solution consists of three stages. First, the input image is pre-processed to remove any colour space biases occurring from different sample collection and imaging techniques. Then, a Mask R-CNN is applied to estimate individual stomata boundaries. The feature pyramid network embedded in the Mask R-CNN is utilised to identify stomata at different scales. Finally, a statistical filter is implemented at the Mask R-CNN output to reduce the number of false positive generated by the network. The algorithm was tested using 16 datasets from 12 sources, containing over 60,000 stomata. For the first time in this domain, the proposed solution was tested against 7 microscope datasets never seen by the algorithm to show the generalisability of the solution. Results indicated that the proposed approach can detect stomata with a precision, recall, and F-score of 95.10\%, 83.34\%, and 88.61\%, respectively. A separate test conducted by comparing estimated stomata boundary values with manually measured data showed that the proposed method has an IoU score of 0.70; a 7\% improvement over the bounding-box approach.
Conclusions: The proposed method shows robust performance across multiple microscope image datasets of different quality and scale. This generalised stomata detection algorithm allows plant scientists to conduct stomata analysis whilst eliminating the need to re-label and re-train for each new dataset. The open-source code shared with this project can be directly deployed in Google Colab or any other Tensorflow environment.
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Loading...