{"title":"一种用户友好的机器学习管道用于矩阵透镜体叶片自动分割。","authors":"Michelle Lynn Yung, Kamila Murawska-Wlodarczyk, Alicja Babst-Kostecka, Raina Margaret Maier, Nirav Merchant, Aikseng Ooi","doi":"10.1177/11779322251344033","DOIUrl":null,"url":null,"abstract":"<p><p>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 <i>Atriplex lentiformis</i>. 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.</p>","PeriodicalId":9065,"journal":{"name":"Bioinformatics and Biology Insights","volume":"19 ","pages":"11779322251344033"},"PeriodicalIF":2.4000,"publicationDate":"2025-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12149614/pdf/","citationCount":"0","resultStr":"{\"title\":\"A User-Friendly Machine Learning Pipeline for Automated Leaf Segmentation in <i>Atriplex lentiformis</i>.\",\"authors\":\"Michelle Lynn Yung, Kamila Murawska-Wlodarczyk, Alicja Babst-Kostecka, Raina Margaret Maier, Nirav Merchant, Aikseng Ooi\",\"doi\":\"10.1177/11779322251344033\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>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 <i>Atriplex lentiformis</i>. 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.</p>\",\"PeriodicalId\":9065,\"journal\":{\"name\":\"Bioinformatics and Biology Insights\",\"volume\":\"19 \",\"pages\":\"11779322251344033\"},\"PeriodicalIF\":2.4000,\"publicationDate\":\"2025-06-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12149614/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Bioinformatics and Biology Insights\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1177/11779322251344033\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/1/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q3\",\"JCRName\":\"BIOCHEMICAL RESEARCH METHODS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Bioinformatics and Biology Insights","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1177/11779322251344033","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q3","JCRName":"BIOCHEMICAL RESEARCH METHODS","Score":null,"Total":0}
A User-Friendly Machine Learning Pipeline for Automated Leaf Segmentation in Atriplex lentiformis.
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.
期刊介绍:
Bioinformatics and Biology Insights is an open access, peer-reviewed journal that considers articles on bioinformatics methods and their applications which must pertain to biological insights. All papers should be easily amenable to biologists and as such help bridge the gap between theories and applications.