A User-Friendly Machine Learning Pipeline for Automated Leaf Segmentation in
Automated leaf segmentation pipelines must balance accuracy, scalability, and usability to be readily adopted in plant research. We present an end-to-end deep learning pipeline designed for practical use in plant phenotyping, which we developed and evaluated during a real-world plant growth experime...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2025-06-01
|
| Series: | Bioinformatics and Biology Insights |
| Online Access: | https://doi.org/10.1177/11779322251344033 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850159833606520832 |
|---|---|
| author | Michelle Lynn Yung Kamila Murawska-Wlodarczyk Alicja Babst-Kostecka Raina Margaret Maier Nirav Merchant Aikseng Ooi |
| author_facet | Michelle Lynn Yung Kamila Murawska-Wlodarczyk Alicja Babst-Kostecka Raina Margaret Maier Nirav Merchant Aikseng Ooi |
| author_sort | Michelle Lynn Yung |
| collection | DOAJ |
| description | Automated leaf segmentation pipelines must balance accuracy, scalability, and usability to be readily adopted in plant research. We present an end-to-end deep learning pipeline designed for practical use in plant phenotyping, which we developed and evaluated during a real-world plant growth experiment using Atriplex lentiformis . The pipeline integrates a fine-tuned Mask Region-based Convolutional Neural Network (Mask R-CNN) segmentation model trained on 176 plant images and achieves high performance despite the small training data set (Dice coefficient = 0.781). We quantitatively compare the fine-tuned Mask R-CNN model to Meta AI’s Segment Anything Model (SAM) and evaluate natural language prompts using Grounded SAM and the Leaf-Only SAM post-processing pipeline for refining segmentation outputs. Our findings highlight that transfer learning on a specialized data set can still outperform a large foundation model in domain-specific tasks. In addition, we integrate QR codes for automated sample identification and benchmark multiple QR code decoding libraries, evaluating their robustness under real-world imaging conditions like distortion and lighting variation. To ensure accessibility, we deploy the pipeline as a user-friendly Streamlit web application, allowing researchers to analyze images without deep learning expertise. By focusing on practical deployment in addition to model performance, this study provides an open-source, scalable framework for plant science applications and addresses real-world challenges in automation and usability by the end-researcher. |
| format | Article |
| id | doaj-art-c28d13c7da074296a264da7289dab4eb |
| institution | OA Journals |
| issn | 1177-9322 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Bioinformatics and Biology Insights |
| spelling | doaj-art-c28d13c7da074296a264da7289dab4eb2025-08-20T02:23:23ZengSAGE PublishingBioinformatics and Biology Insights1177-93222025-06-011910.1177/11779322251344033A User-Friendly Machine Learning Pipeline for Automated Leaf Segmentation in Michelle Lynn Yung0Kamila Murawska-Wlodarczyk1Alicja Babst-Kostecka2Raina Margaret Maier3Nirav Merchant4Aikseng Ooi5Data Science Institute, The University of Arizona, Tucson, AZ, USADepartment of Environmental Science, College of Agriculture, Life & Environmental Sciences, The University of Arizona, Tucson, AZ, USADepartment of Environmental Science, College of Agriculture, Life & Environmental Sciences, The University of Arizona, Tucson, AZ, USADepartment of Environmental Science, College of Agriculture, Life & Environmental Sciences, The University of Arizona, Tucson, AZ, USAData Science Institute, The University of Arizona, Tucson, AZ, USADepartment of Pharmacology and Toxicology, R Ken Coit College of Pharmacy, The University of Arizona, Tucson, AZ, USAAutomated leaf segmentation pipelines must balance accuracy, scalability, and usability to be readily adopted in plant research. We present an end-to-end deep learning pipeline designed for practical use in plant phenotyping, which we developed and evaluated during a real-world plant growth experiment using Atriplex lentiformis . The pipeline integrates a fine-tuned Mask Region-based Convolutional Neural Network (Mask R-CNN) segmentation model trained on 176 plant images and achieves high performance despite the small training data set (Dice coefficient = 0.781). We quantitatively compare the fine-tuned Mask R-CNN model to Meta AI’s Segment Anything Model (SAM) and evaluate natural language prompts using Grounded SAM and the Leaf-Only SAM post-processing pipeline for refining segmentation outputs. Our findings highlight that transfer learning on a specialized data set can still outperform a large foundation model in domain-specific tasks. In addition, we integrate QR codes for automated sample identification and benchmark multiple QR code decoding libraries, evaluating their robustness under real-world imaging conditions like distortion and lighting variation. To ensure accessibility, we deploy the pipeline as a user-friendly Streamlit web application, allowing researchers to analyze images without deep learning expertise. By focusing on practical deployment in addition to model performance, this study provides an open-source, scalable framework for plant science applications and addresses real-world challenges in automation and usability by the end-researcher.https://doi.org/10.1177/11779322251344033 |
| spellingShingle | Michelle Lynn Yung Kamila Murawska-Wlodarczyk Alicja Babst-Kostecka Raina Margaret Maier Nirav Merchant Aikseng Ooi A User-Friendly Machine Learning Pipeline for Automated Leaf Segmentation in Bioinformatics and Biology Insights |
| title | A User-Friendly Machine Learning Pipeline for Automated Leaf Segmentation in |
| title_full | A User-Friendly Machine Learning Pipeline for Automated Leaf Segmentation in |
| title_fullStr | A User-Friendly Machine Learning Pipeline for Automated Leaf Segmentation in |
| title_full_unstemmed | A User-Friendly Machine Learning Pipeline for Automated Leaf Segmentation in |
| title_short | A User-Friendly Machine Learning Pipeline for Automated Leaf Segmentation in |
| title_sort | user friendly machine learning pipeline for automated leaf segmentation in |
| url | https://doi.org/10.1177/11779322251344033 |
| work_keys_str_mv | AT michellelynnyung auserfriendlymachinelearningpipelineforautomatedleafsegmentationin AT kamilamurawskawlodarczyk auserfriendlymachinelearningpipelineforautomatedleafsegmentationin AT alicjababstkostecka auserfriendlymachinelearningpipelineforautomatedleafsegmentationin AT rainamargaretmaier auserfriendlymachinelearningpipelineforautomatedleafsegmentationin AT niravmerchant auserfriendlymachinelearningpipelineforautomatedleafsegmentationin AT aiksengooi auserfriendlymachinelearningpipelineforautomatedleafsegmentationin AT michellelynnyung userfriendlymachinelearningpipelineforautomatedleafsegmentationin AT kamilamurawskawlodarczyk userfriendlymachinelearningpipelineforautomatedleafsegmentationin AT alicjababstkostecka userfriendlymachinelearningpipelineforautomatedleafsegmentationin AT rainamargaretmaier userfriendlymachinelearningpipelineforautomatedleafsegmentationin AT niravmerchant userfriendlymachinelearningpipelineforautomatedleafsegmentationin AT aiksengooi userfriendlymachinelearningpipelineforautomatedleafsegmentationin |