A workflow for segmenting soil and plant X-ray CT images with deep\n learning in Googles Colaboratory Article Swipe

MAKE IMPACT

Devin A. Rippner , P. M. Siva Raja , J. Mason Earles , Alexander C. Buchko , Mina Momayyezi , Fiona Duong , Dilworth Y. Parkinson , Elizabeth J. Forrestel , Ken Shackel , Jeffrey Neyhart , Andrew J. McElrone · YOU? · · 2022 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2203.09674

X-ray micro-computed tomography (X-ray microCT) has enabled the\ncharacterization of the properties and processes that take place in plants and\nsoils at the micron scale. Despite the widespread use of this advanced\ntechnique, major limitations in both hardware and software limit the speed and\naccuracy of image processing and data analysis. Recent advances in machine\nlearning, specifically the application of convolutional neural networks to\nimage analysis, have enabled rapid and accurate segmentation of image data.\nYet, challenges remain in applying convolutional neural networks to the\nanalysis of environmentally and agriculturally relevant images. Specifically,\nthere is a disconnect between the computer scientists and engineers, who build\nthese AI/ML tools, and the potential end users in agricultural research, who\nmay be unsure of how to apply these tools in their work. Additionally, the\ncomputing resources required for training and applying deep learning models are\nunique, more common to computer gaming systems or graphics design work, than to\ntraditional computational systems. To navigate these challenges, we developed a\nmodular workflow for applying convolutional neural networks to X-ray microCT\nimages, using low-cost resources in Googles Colaboratory web application. Here\nwe present the results of the workflow, illustrating how parameters can be\noptimized to achieve best results using example scans from walnut leaves,\nalmond flower buds, and a soil aggregate. We expect that this framework will\naccelerate the adoption and use of emerging deep learning techniques within the\nplant and soil sciences.\n

Type

preprint

Landing Page

http://arxiv.org/abs/2203.09674

PDF

https://arxiv.org/pdf/2203.09674

OA Status

green

Cited By

1

Related Works

10

OpenAlex ID

https://openalex.org/W4288012749

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4288012749

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2203.09674

Digital Object Identifier

Title

A workflow for segmenting soil and plant X-ray CT images with deep\n learning in Googles Colaboratory

Work title

Type

preprint

OpenAlex work type

Publication year

2022

Year of publication

Publication date

2022-03-17

Full publication date if available

Authors

Devin A. Rippner, P. M. Siva Raja, J. Mason Earles, Alexander C. Buchko, Mina Momayyezi, Fiona Duong, Dilworth Y. Parkinson, Elizabeth J. Forrestel, Ken Shackel, Jeffrey Neyhart, Andrew J. McElrone

List of authors in order

Landing page

https://arxiv.org/abs/2203.09674

Publisher landing page

PDF URL

https://arxiv.org/pdf/2203.09674

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2203.09674

Direct OA link when available

Concepts

Workflow, Convolutional neural network, Computer science, Deep learning, Artificial intelligence, Modular design, Machine learning, Segmentation, Software, Artificial neural network, Image processing, Data science, Image (mathematics), Database, Operating system, Programming language

Top concepts (fields/topics) attached by OpenAlex

Cited by

1

Total citation count in OpenAlex

Citations by year (recent)

2024: 1

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload