RootPainter: deep learning segmentation of biological images with corrective annotation. Issue 2 (10th August 2022)

• Record Type: Journal Article
• Authors: Smith, Abraham George; Han, Eusun; Petersen, Jens; Olsen, Niels Alvin Faircloth; Giese, Christian; Athmann, Miriam; Dresbøll, Dorte Bodin; Thorup‐Kristensen, Kristian
• Is Part Of: New phytologist. Volume 236:Issue 2(2022)
• Page Start: 774
• Page End: 791
• Publication Date: 2022-08-10
• Subjects: biopore -- deep learning -- GUI -- interactive machine learning -- phenotyping -- rhizotron -- root nodule -- segmentation; Botany -- Periodicals; 580
• DOI: 10.1111/nph.18387
• Languages: English
• ISSNs: 0028-646X

Abstract

Summary: Convolutional neural networks (CNNs) are a powerful tool for plant image analysis, but challenges remain in making them more accessible to researchers without a machine‐learning background. We present Root Painter, an open‐source graphical user interface based software tool for the rapid training of deep neural networks for use in biological image analysis. We evaluate Root Painter by training models for root length extraction from chicory ( Cichorium intybus L.) roots in soil, biopore counting, and root nodule counting. We also compare dense annotations with corrective ones that are added during the training process based on the weaknesses of the current model. Five out of six times the models trained using Root Painter with corrective annotations created within 2 h produced measurements strongly correlating with manual measurements. Model accuracy had a significant correlation with annotation duration, indicating further improvements could be obtained with extended annotation. Our results show that a deep‐learning model can be trained to a high accuracy for the three respective datasets of varying target objects, background, and image quality with < 2 h of annotation time. They indicate that, when using Root Painter, for many datasets it is possible to annotate, train, and complete data processing within 1 d.