Evaluation of Effective Class-Balancing Techniques for CNN-Based Assessment of Aphanomyces Root Rot Resistance in Pea (Pisum sativum L.)

Abstract

Aphanomyces root rot (ARR) is a devastating disease that affects the production of pea. The plants are prone to infection at any growth stage, and there are no chemical or cultural controls. Thus, the development of resistant pea cultivars is important. Phenomics technologies to support the selection of resistant cultivars through phenotyping can be valuable. One such approach is to couple imaging technologies with deep learning algorithms that are considered efficient for the assessment of disease resistance across a large number of plant genotypes. In this study, the resistance to ARR was evaluated through a CNN-based assessment of pea root images. The proposed model, DeepARRNet, was designed to classify the pea root images into three classes based on ARR severity scores, namely, resistant, intermediate, and susceptible classes. The dataset consisted of 1581 pea root images with a skewed distribution. Hence, three effective data-balancing techniques were identified to solve the prevalent problem of unbalanced datasets. Random oversampling with image transformations, generative adversarial network (GAN)-based image synthesis, and loss function with class-weighted ratio were implemented during the training process. The result indicated that the classification F1-score was 0.92 ± 0.03 when GAN-synthesized images were added, 0.91 ± 0.04 for random resampling, and 0.88 ± 0.05 when class-weighted loss function was implemented, which was higher than when an unbalanced dataset without these techniques were used (0.83 ± 0.03). The systematic approaches evaluated in this study can be applied to other image-based phenotyping datasets, which can aid the development of deep-learning models with improved performance.

Pea Breeding for Resistance to Rhizospheric Pathogens

“…Nowadays, low-throughput screening is considered a bottleneck to phenotyping and often requires specialised breeders’ expertise, thus high-throughput techniques are beginning to replace visual screening [ 224 , 233 ]. High-throughput phenotyping gives the opportunity to overcome visual assessment bias and difficulty to access plant traits.…”

“…Genomic approaches using high-throughput genomic information in the areas of genome sequencing, data resequencing, genome-wide markers, genetic maps, QTLs, diagnostic markers, and omics strategies (transcriptomics, proteomics, metabolomics biomarkers), assist with and direct multiple breeding strategies [ 4 , 233 , 262 ]. The genetic revolution provided by the next-generation sequencing (NGS) platforms ensures the development of approaches, such as genotyping by sequence (GBS), diversity array technology sequencing (DArTseq), ribonucleic acid sequencing (RNA-Seq), whole-genome sequencing (WGS), among others, which have improved the quality of marker technologies [ 263 , 264 ].…”

“…The genetic revolution provided by the next-generation sequencing (NGS) platforms ensures the development of approaches, such as genotyping by sequence (GBS), diversity array technology sequencing (DArTseq), ribonucleic acid sequencing (RNA-Seq), whole-genome sequencing (WGS), among others, which have improved the quality of marker technologies [ 263 , 264 ]. This led to the discovery of extensive single-nucleotide polymorphic (SNPs) markers [ 265 ] with a huge potential for pea improvements [ 233 ]. These novel platforms have already guided the identification of heritable QTLs contributing to phenotypic variance in pea resistance breeding [ 102 , 266 , 267 , 268 ].…”

Image-to-Image Translation-Based Data Augmentation for Improving Crop/Weed Classification Models for Precision Agriculture Applications

“…GANs have been effectively applied to various tasks, such as human identification [30], organ segmentation [31], and emotion classification [32]. These models have also been used for machine-vision applications in agriculture, such as generating images of specific plants [33,34], plant disease recognition [35], grain quality analysis [4], and for synthesizing images of plant seedlings [36]. A few studies have also utilized GANs to assist in deep-learning-based operations in precision weed management (Table 1).…”

Detection of Coconut Clusters Based on Occlusion Condition Using Attention-Guided Faster R-CNN for Robotic Harvesting

“…Unlike traditional computer vision solutions that relied on identifying important features and tedious feature-engineering tasks [ 16 , 17 , 18 ], deep learning uses convolutional neural networks (CNNs) to automatically learn important features within training data, resulting in a less biased model. Deep learning algorithms have shown potential in many machine-vision operations applied to agriculture [ 19 , 20 , 21 , 22 ]. Numerous studies have employed CNN-based fruit detection models to support robotic harvesting, such as in the case of apples [ 23 , 24 ], tomatoes [ 25 ], strawberries [ 26 ], mangoes [ 27 ], kiwifruit [ 28 ], and blueberries [ 29 ].…”