Dataset Information

A dataset of necrotized cassava root cross-section images.

ABSTRACT: Cassava brown streak disease is a major disease affecting cassava. Along with foliar chlorosis and stem lesions, a very common symptom of cassava brown streak disease is the development of a dry, brown corky rot within the starch bearing tuberous roots, also known as necrosis. This paper presents a dataset of curated image data of necrosis bearing roots across different cassava varieties. The dataset contains images of cassava root cross-sections based on trial harvests from Uganda and Tanzania. The images were taken using a smartphone camera. The resulting dataset consists of 10,052 images making this the largest publicly available dataset for crop root necrosis. The data is comprehensive and contains different variations of necrosis expression including root cross-section types, number of necrosis lesions, presentation of the necrosis lesions. The dataset is important and can be used to train machine learning models which quantify the percentage of cassava root damage caused by necrosis.

SUBMITTER: Nakatumba-Nabende J

PROVIDER: S-EPMC7452662 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A dataset of necrotized cassava root cross-section images.

Nakatumba-Nabende Joyce J Akera Benjamin B Tusubira Jeremy Francis JF Nsumba Solomon S Mwebaze Ernest E

Data in brief 20200812

Cassava brown streak disease is a major disease affecting cassava. Along with foliar chlorosis and stem lesions, a very common symptom of cassava brown streak disease is the development of a dry, brown corky rot within the starch bearing tuberous roots, also known as necrosis. This paper presents a dataset of curated image data of necrosis bearing roots across different cassava varieties. The dataset contains images of cassava root cross-sections based on trial harvests from Uganda and Tanzania. ...[more]

PMID: 32904393

Similar Datasets

Project description:Cassava roots are complex structures comprising several distinct types of root. The number and size of the storage roots are two potential phenotypic traits reflecting crop yield and quality. Counting and measuring the size of cassava storage roots are usually done manually, or semi-automatically by first segmenting cassava root images. However, occlusion of both storage and fibrous roots makes the process both time-consuming and error-prone. While Convolutional Neural Nets have shown performance above the state-of-the-art in many image processing and analysis tasks, there are currently a limited number of Convolutional Neural Net-based methods for counting plant features. This is due to the limited availability of data, annotated by expert plant biologists, which represents all possible measurement outcomes. Existing works in this area either learn a direct image-to-count regressor model by regressing to a count value, or perform a count after segmenting the image. We, however, address the problem using a direct image-to-count prediction model. This is made possible by generating synthetic images, using a conditional Generative Adversarial Network (GAN), to provide training data for missing classes. We automatically form cassava storage root masks for any missing classes using existing ground-truth masks, and input them as a condition to our GAN model to generate synthetic root images. We combine the resulting synthetic images with real images to learn a direct image-to-count prediction model capable of counting the number of storage roots in real cassava images taken from a low cost aeroponic growth system. These models are used to develop a system that counts cassava storage roots in real images. Our system first predicts age group ('young' and 'old' roots; pertinent to our image capture regime) in a given image, and then, based on this prediction, selects an appropriate model to predict the number of storage roots. We achieve 91% accuracy on predicting ages of storage roots, and 86% and 71% overall percentage agreement on counting 'old' and 'young' storage roots respectively. Thus we are able to demonstrate that synthetically generated cassava root images can be used to supplement missing root classes, turning the counting problem into a direct image-to-count prediction task.

Project description:Root hydraulic properties play a central role in the global water cycle, in agricultural systems productivity, and in ecosystem survival as they impact the canopy water supply. However, the existing experimental methods to quantify root hydraulic conductivities, such as the root pressure probing, are particularly challenging, and their applicability to thin roots and small root segments is limited. Therefore, there is a gap in methods enabling easy estimations of root hydraulic conductivities in diverse root types. Here, we present a new pipeline to quickly estimate root hydraulic conductivities across different root types, at high resolution along root axes. Shortly, free-hand root cross-sections were used to extract a selected number of key anatomical traits. We used these traits to parametrize the Generator of Root Anatomy in R (GRANAR) model to simulate root anatomical networks. Finally, we used these generated anatomical networks within the Model of Explicit Cross-section Hydraulic Anatomy (MECHA) to compute an estimation of the root axial and radial hydraulic conductivities (k x and k r , respectively). Using this combination of anatomical data and computational models, we were able to create a root hydraulic conductivity atlas at the root system level, for 14-day-old pot-grown Zea mays (maize) plants of the var. B73. The altas highlights the significant functional variations along and between different root types. For instance, predicted variations of radial conductivity along the root axis were strongly dependent on the maturation stage of hydrophobic barriers. The same was also true for the maturation rates of the metaxylem vessels. Differences in anatomical traits along and across root types generated substantial variations in radial and axial conductivities estimated with our novel approach. Our methodological pipeline combines anatomical data and computational models to turn root cross-section images into a detailed hydraulic atlas. It is an inexpensive, fast, and easily applicable investigation tool for root hydraulics that complements existing complex experimental methods. It opens the way to high-throughput studies on the functional importance of root types in plant hydraulics, especially if combined with novel phenotyping techniques such as laser ablation tomography.

Dataset Information

A dataset of necrotized cassava root cross-section images.

Publications

A dataset of necrotized cassava root cross-section images.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets