Automatic Evaluation of Wheat Resistance to Fusarium Head Blight Using Dual Mask-RCNN Deep Learning Frameworks in Computer Vision

Sága, a Deep Learning Spectral Analysis Tool for Fungal Detection in Grains-A Case Study to Detect Fusarium in Winter Wheat

Fusarium head blight (FHB) is a plant disease caused by various species of the Fusarium fungus. One of the major concerns associated with Fusarium spp. is their ability to produce mycotoxins. Mycotoxin contamination in small grain cereals is a risk to human and animal health and leads to major economic losses. A reliable site-specific precise Fusarium spp. infection early warning model is, therefore, needed to ensure food and feed safety by the early detection of contamination hotspots, enabling effective and efficient fungicide applications, and providing FHB prevention management advice. Such precision farming techniques contribute to environmentally friendly production and sustainable agriculture. This study developed a predictive model, Sága, for on-site FHB detection in wheat using imaging spectroscopy and deep learning. Data were collected from an experimental field in 2021 including (1) an experimental field inoculated with Fusarium spp. (52.5 m × 3 m) and (2) a control field (52.5 m × 3 m) not inoculated with Fusarium spp. and sprayed with fungicides. Imaging spectroscopy data (hyperspectral images) were collected from both the experimental and control fields with the ground truth of Fusarium-infected ear and healthy ear, respectively. Deep learning approaches (pretrained YOLOv5 and DeepMAC on Global Wheat Head Detection (GWHD) dataset) were used to segment wheat ears and XGBoost was used to analyze the hyperspectral information related to the wheat ears and make predictions of Fusarium-infected wheat ear and healthy wheat ear. The results showed that deep learning methods can automatically detect and segment the ears of wheat by applying pretrained models. The predictive model can accurately detect infected areas in a wheat field, achieving mean accuracy and F1 scores exceeding 89%. The proposed model, Sága, could facilitate the early detection of Fusarium spp. to increase the fungicide use efficiency and limit mycotoxin contamination.

Wheat Fusarium Head Blight Automatic Non-Destructive Detection Based on Multi-Scale Imaging: A Technical Perspective

Fusarium head blight (FHB) is a major threat to global wheat production. Recent reviews of wheat FHB focused on pathology or comprehensive prevention and lacked a summary of advanced detection techniques. Unlike traditional detection and management methods, wheat FHB detection based on various imaging technologies has the obvious advantages of a high degree of automation and efficiency. With the rapid development of computer vision and deep learning technology, the number of related research has grown explosively in recent years. This review begins with an overview of wheat FHB epidemic mechanisms and changes in the characteristics of infected wheat. On this basis, the imaging scales are divided into microscopic, medium, submacroscopic, and macroscopic scales. Then, we outline the recent relevant articles, algorithms, and methodologies about wheat FHB from disease detection to qualitative analysis and summarize the potential difficulties in the practicalization of the corresponding technology. This paper could provide researchers with more targeted technical support and breakthrough directions. Additionally, this paper provides an overview of the ideal application mode of the FHB detection technologies based on multi-scale imaging and then examines the development trend of the all-scale detection system, which paved the way for the fusion of non-destructive detection technologies of wheat FHB based on multi-scale imaging.

GranoScan: an AI-powered mobile app for in-field identification of biotic threats of wheat

Capitalizing on the widespread adoption of smartphones among farmers and the application of artificial intelligence in computer vision, a variety of mobile applications have recently emerged in the agricultural domain. This paper introduces GranoScan, a freely available mobile app accessible on major online platforms, specifically designed for the real-time detection and identification of over 80 threats affecting wheat in the Mediterranean region. Developed through a co-design methodology involving direct collaboration with Italian farmers, this participatory approach resulted in an app featuring: (i) a graphical interface optimized for diverse in-field lighting conditions, (ii) a user-friendly interface allowing swift selection from a predefined menu, (iii) operability even in low or no connectivity, (iv) a straightforward operational guide, and (v) the ability to specify an area of interest in the photo for targeted threat identification. Underpinning GranoScan is a deep learning architecture named efficient minimal adaptive ensembling that was used to obtain accurate and robust artificial intelligence models. The method is based on an ensembling strategy that uses as core models two instances of the EfficientNet-b0 architecture, selected through the weighted F1-score. In this phase a very good precision is reached with peaks of 100% for pests, as well as in leaf damage and root disease tasks, and in some classes of spike and stem disease tasks. For weeds in the post-germination phase, the precision values range between 80% and 100%, while 100% is reached in all the classes for pre-flowering weeds, except one. Regarding recognition accuracy towards end-users in-field photos, GranoScan achieved good performances, with a mean accuracy of 77% and 95% for leaf diseases and for spike, stem and root diseases, respectively. Pests gained an accuracy of up to 94%, while for weeds the app shows a great ability (100% accuracy) in recognizing whether the target weed is a dicot or monocot and 60% accuracy for distinguishing species in both the post-germination and pre-flowering stage. Our precision and accuracy results conform to or outperform those of other studies deploying artificial intelligence models on mobile devices, confirming that GranoScan is a valuable tool also in challenging outdoor conditions.

Automatic Localization of Soybean Seedlings Based on Crop Signaling and Multi-View Imaging

Soybean is grown worldwide for its high protein and oil content. Weeds compete fiercely for resources, which affects soybean yields. Because of the progressive enhancement of weed resistance to herbicides and the quickly increasing cost of manual weeding, mechanical weed control is becoming the preferred method of weed control. Mechanical weed control finds it difficult to remove intra-row weeds due to the lack of rapid and precise weed/soybean detection and location technology. Rhodamine B (Rh-B) is a systemic crop compound that can be absorbed by soybeans which fluoresces under a specific excitation light. The purpose of this study is to combine systemic crop compounds and computer vision technology for the identification and localization of soybeans in the field. The fluorescence distribution properties of systemic crop compounds in soybeans and their effects on plant growth were explored. The fluorescence was mainly concentrated in soybean cotyledons treated with Rh-B. After a comparison of soybean seedlings treated with nine groups of rhodamine B solutions at different concentrations ranging from 0 to 1440 ppm, the soybeans treated with 180 ppm Rh-B for 24 h received the recommended dosage, resulting in significant fluorescence that did not affect crop growth. Increasing the Rh-B solutions reduced crop biomass, while prolonged treatment times reduced seed germination. The fluorescence produced lasted for 20 days, ensuring a stable signal in the early stages of growth. Additionally, a precise inter-row soybean plant location system based on a fluorescence imaging system with a 96.7% identification accuracy, determined on 300 datasets, was proposed. This article further confirms the potential of crop signaling technology to assist machines in achieving crop identification and localization in the field.

YOLOv8s-CGF: a lightweight model for wheat ear Fusarium head blight detection

Fusarium head blight (FHB) is a destructive disease that affects wheat production. Detecting FHB accurately and rapidly is crucial for improving wheat yield. Traditional models are difficult to apply to mobile devices due to large parameters, high computation, and resource requirements. Therefore, this article proposes a lightweight detection method based on an improved YOLOv8s to facilitate the rapid deployment of the model on mobile terminals and improve the detection efficiency of wheat FHB. The proposed method introduced a C-FasterNet module, which replaced the C2f module in the backbone network. It helps reduce the number of parameters and the computational volume of the model. Additionally, the Conv in the backbone network is replaced with GhostConv, further reducing parameters and computation without significantly affecting detection accuracy. Thirdly, the introduction of the Focal CIoU loss function reduces the impact of sample imbalance on the detection results and accelerates the model convergence. Lastly, the large target detection head was removed from the model for lightweight. The experimental results show that the size of the improved model (YOLOv8s-CGF) is only 11.7 M, which accounts for 52.0% of the original model (YOLOv8s). The number of parameters is only 5.7 × 106 M, equivalent to 51.4% of the original model. The computational volume is only 21.1 GFLOPs, representing 74.3% of the original model. Moreover, the mean average precision (mAP@0.5) of the model is 99.492%, which is 0.003% higher than the original model, and the mAP@0.5:0.95 is 0.269% higher than the original model. Compared to other YOLO models, the improved lightweight model not only achieved the highest detection precision but also significantly reduced the number of parameters and model size. This provides a valuable reference for FHB detection in wheat ears and deployment on mobile terminals in field environments.

Melanoma skin cancer detection using mask-RCNN with modified GRU model

Introduction: Melanoma Skin Cancer (MSC) is a type of cancer in the human body; therefore, early disease diagnosis is essential for reducing the mortality rate. However, dermoscopic image analysis poses challenges due to factors such as color illumination, light reflections, and the varying sizes and shapes of lesions. To overcome these challenges, an automated framework is proposed in this manuscript. Methods: Initially, dermoscopic images are acquired from two online benchmark datasets: International Skin Imaging Collaboration (ISIC) 2020 and Human against Machine (HAM) 10000. Subsequently, a normalization technique is employed on the dermoscopic images to decrease noise impact, outliers, and variations in the pixels. Furthermore, cancerous regions in the pre-processed images are segmented utilizing the mask-faster Region based Convolutional Neural Network (RCNN) model. The mask-RCNN model offers precise pixellevel segmentation by accurately delineating object boundaries. From the partitioned cancerous regions, discriminative feature vectors are extracted by applying three pre-trained CNN models, namely ResNeXt101, Xception, and InceptionV3. These feature vectors are passed into the modified Gated Recurrent Unit (GRU) model for MSC classification. In the modified GRU model, a swish-Rectified Linear Unit (ReLU) activation function is incorporated that efficiently stabilizes the learning process with better convergence rate during training. Results and discussion: The empirical investigation demonstrate that the modified GRU model attained an accuracy of 99.95% and 99.98% on the ISIC 2020 and HAM 10000 datasets, where the obtained results surpass the conventional detection models.

WheatSpikeNet: an improved wheat spike segmentation model for accurate estimation from field imaging

Phenotyping is used in plant breeding to identify genotypes with desirable characteristics, such as drought tolerance, disease resistance, and high-yield potentials. It may also be used to evaluate the effect of environmental circumstances, such as drought, heat, and salt, on plant growth and development. Wheat spike density measure is one of the most important agronomic factors relating to wheat phenotyping. Nonetheless, due to the diversity of wheat field environments, fast and accurate identification for counting wheat spikes remains one of the challenges. This study proposes a meticulously curated and annotated dataset, named as SPIKE-segm, taken from the publicly accessible SPIKE dataset, and an optimal instance segmentation approach named as WheatSpikeNet for segmenting and counting wheat spikes from field imagery. The proposed method is based on the well-known Cascade Mask RCNN architecture with model enhancements and hyperparameter tuning to provide state-of-the-art detection and segmentation performance. A comprehensive ablation analysis incorporating many architectural components of the model was performed to determine the most efficient version. In addition, the model's hyperparameters were fine-tuned by conducting several empirical tests. ResNet50 with Deformable Convolution Network (DCN) as the backbone architecture for feature extraction, Generic RoI Extractor (GRoIE) for RoI pooling, and Side Aware Boundary Localization (SABL) for wheat spike localization comprises the final instance segmentation model. With bbox and mask mean average precision (mAP) scores of 0.9303 and 0.9416, respectively, on the test set, the proposed model achieved superior performance on the challenging SPIKE datasets. Furthermore, in comparison with other existing state-of-the-art methods, the proposed model achieved up to a 0.41% improvement of mAP in spike detection and a significant improvement of 3.46% of mAP in the segmentation tasks that will lead us to an appropriate yield estimation from wheat plants.

The NWRD Dataset: An Open-Source Annotated Segmentation Dataset of Diseased Wheat Crop

Wheat stripe rust disease (WRD) is extremely detrimental to wheat crop health, and it severely affects the crop yield, increasing the risk of food insecurity. Manual inspection by trained personnel is carried out to inspect the disease spread and extent of damage to wheat fields. However, this is quite inefficient, time-consuming, and laborious, owing to the large area of wheat plantations. Artificial intelligence (AI) and deep learning (DL) offer efficient and accurate solutions to such real-world problems. By analyzing large amounts of data, AI algorithms can identify patterns that are difficult for humans to detect, enabling early disease detection and prevention. However, deep learning models are data-driven, and scarcity of data related to specific crop diseases is one major hindrance in developing models. To overcome this limitation, in this work, we introduce an annotated real-world semantic segmentation dataset named the NUST Wheat Rust Disease (NWRD) dataset. Multileaf images from wheat fields under various illumination conditions with complex backgrounds were collected, preprocessed, and manually annotated to construct a segmentation dataset specific to wheat stripe rust disease. Classification of WRD into different types and categories is a task that has been solved in the literature; however, semantic segmentation of wheat crops to identify the specific areas of plants and leaves affected by the disease remains a challenge. For this reason, in this work, we target semantic segmentation of WRD to estimate the extent of disease spread in wheat fields. Sections of fields where the disease is prevalent need to be segmented to ensure that the sick plants are quarantined and remedial actions are taken. This will consequently limit the use of harmful fungicides only on the targeted disease area instead of the majority of wheat fields, promoting environmentally friendly and sustainable farming solutions. Owing to the complexity of the proposed NWRD segmentation dataset, in our experiments, promising results were obtained using the UNet semantic segmentation model and the proposed adaptive patching with feedback (APF) technique, which produced a precision of 0.506, recall of 0.624, and F1 score of 0.557 for the rust class.

Segmentation of Unsound Wheat Kernels Based on Improved Mask RCNN

The grade of wheat quality depends on the proportion of unsound kernels. Therefore, the rapid detection of unsound wheat kernels is important for wheat rating and evaluation. However, in practice, unsound kernels are hand-picked, which makes the process time-consuming and inefficient. Meanwhile, methods based on traditional image processing cannot divide adherent particles well. To solve the above problems, this paper proposed an unsound wheat kernel recognition algorithm based on an improved mask RCNN. First, we changed the feature pyramid network (FPN) to a bottom-up pyramid network to strengthen the low-level information. Then, an attention mechanism (AM) module was added between the feature extraction network and the pyramid network to improve the detection accuracy for small targets. Finally, the regional proposal network (RPN) was optimized to improve the prediction performance. Experiments showed that the improved mask RCNN algorithm could identify the unsound kernels more quickly and accurately while handling adhesion problems well. The precision and recall were 86% and 91%, respectively, and the inference time on the test set with about 200 targets for each image was 7.83 s. Additionally, we compared the improved model with other existing segmentation models, and experiments showed that our model achieved higher accuracy and performance than the other models, laying the foundation for wheat grading.

Recent advances in plant disease severity assessment using convolutional neural networks

In modern agricultural production, the severity of diseases is an important factor that directly affects the yield and quality of plants. In order to effectively monitor and control the entire production process of plants, not only the type of disease, but also the severity of the disease must be clarified. In recent years, deep learning for plant disease species identification has been widely used. In particular, the application of convolutional neural network (CNN) to plant disease images has made breakthrough progress. However, there are relatively few studies on disease severity assessment. The group first traced the prevailing views of existing disease researchers to provide criteria for grading the severity of plant diseases. Then, depending on the network architecture, this study outlined 16 studies on CNN-based plant disease severity assessment in terms of classical CNN frameworks, improved CNN architectures and CNN-based segmentation networks, and provided a detailed comparative analysis of the advantages and disadvantages of each. Common methods for acquiring datasets and performance evaluation metrics for CNN models were investigated. Finally, this study discussed the major challenges faced by CNN-based plant disease severity assessment methods in practical applications, and provided feasible research ideas and possible solutions to address these challenges.

Paenibacillus polymyxa Antagonism towards Fusarium: Identification and Optimisation of Antibiotic Production

An antibiotic produced by Paenibacillus polymyxa 7F1 was studied. The 7F1 strain was isolated from the rhizosphere of a wheat field. Response surface methodology was used to optimize the physicochemical parameters. The strain showed broad-spectrum activity against several plant pathogens. Identification of the strain was realized based on 16s rRNA gene and gyrB gene sequencing. The antibiotic was optimized by one-factor-at-a-time (OFAT) and response surface methodology (RSM) approaches. The suitable antibiotic production conditions were optimized using the one-factor-at-a-time method. The individual and interaction effects of three independent variables: culture temperature, initial pH, and culture time, were optimized by Box-Behnken design. The 16SrRNA gene sequence (1239 nucleotides) and gyrB gene (1111 nucleotides) were determined for strain 7F1 and shared the highest identities to those of Paenibacillus polymyxa. The results showed the optimal fermentation conditions for antibiotics produced by Paenibacillus polymyxa 7F1 were a culture temperature of 38 °C, initial pH of 8.0, and culture time of 8 h. The antibiotics produced by Paenibacillus polymyxa 7F1 include lipopeptides such as iturin A and surfactin. The results provide a theoretical basis for the development of bacteriostatic biological agents and the control of mycotoxins.

PyCoCa:A quantifying tool of carbon content in airway macrophage for assessment the internal dose of particles

Given the lack of a comprehensive understanding of the complex metabolism and variable exposure environment, carbon particles in macrophages have become a potentially valuable biomarker to assess the exposure level of atmospheric particles, such as black carbon. However, the tedious and subjective quantification method limits the application of carbon particles as a valid biomarker. Aiming to obtain an accurate carbon particles quantification method, the deep learning and binarization algorithm were implemented to develop a quantitative tool for carbon content in airway macrophage (CCAM), named PyCoCa. Two types of macrophages, normal and foamy appearance, were applied for the development of PyCoCa. In comparison with the traditional methods, PyCoCa significantly improves the identification efficiency for over 100 times. Consistency assessment with the gold standard revealed that PyCoCa exhibits outstanding prediction ability with the Interclass Correlation Coefficient (ICC) values of over 0.80. And a proper fresh dye will enhance the performance of PyCoCa (ICC = 0.89). Subsequent sensitivity analysis confirmed an excellent performance regarding accuracy and robustness of PyCoCa under high/low exposure environments (sensitivity > 0.80). Furthermore, a successful application of our quantitative tool in cohort studies indicates that carbon particles induce macrophage foaming and the foaming decrease the carbon particles internalization in reverse. Our present study provides a robust and efficient tool to accurately quantify the carbon particles loading in macrophage for exposure assessment.

SlypNet: Spikelet-based yield prediction of wheat using advanced plant phenotyping and computer vision techniques

The application of computer vision in agriculture has already contributed immensely to restructuring the existing field practices starting from the sowing to the harvesting. Among the different plant parts, the economic part, the yield, has the highest importance and becomes the ultimate goal for the farming community. It depends on many genetic and environmental factors, so this curiosity about knowing the yield brought several precise pre-harvest prediction methods using different ways. Out of those techniques, non-invasive yield prediction techniques using computer vision have been proved to be the most efficient and trusted platform. This study developed a novel methodology, called SlypNet, using advanced deep learning networks, i.e., Mask R-CNN and U-Net, which can extract various plant morphological features like spike and spikelet from the visual image of the wheat plant and provide a high-throughput yield estimate with great precision. Mask R-CNN outperformed previous networks in spike detection by its precise detection performance with a mean average precision (mAP) of 97.57%, a F1 score of 0.67, and an MCC of 0.91 by overcoming several natural field constraints like overlapping and background interference, variable resolution, and high bushiness of plants. The spikelet detection module's accuracy and consistency were tested with about 99% validation accuracy of the model and the least error, i.e., a mean square error of 1.3 from a set of typical and complex views of wheat spikes. Spikelet yield cumulatively showed the probable production capability of each plant. Our method presents an integrated deep learning platform of spikelet-based yield prediction comprising spike and spikelet detection, leading to higher precision over the existing methods.

Deep Learning Diagnostics of Gray Leaf Spot in Maize under Mixed Disease Field Conditions

Maize yields worldwide are limited by foliar diseases that could be fungal, oomycete, bacterial, or viral in origin. Correct disease identification is critical for farmers to apply the correct control measures, such as fungicide sprays. Deep learning has the potential for automated disease classification from images of leaf symptoms. We aimed to develop a classifier to identify gray leaf spot (GLS) disease of maize in field images where mixed diseases were present (18,656 images after augmentation). In this study, we compare deep learning models trained on mixed disease field images with and without background subtraction. Performance was compared with models trained on PlantVillage images with single diseases and uniform backgrounds. First, we developed a modified VGG16 network referred to as “GLS_net” to perform binary classification of GLS, which achieved a 73.4% accuracy. Second, we used MaskRCNN to dynamically segment leaves from backgrounds in combination with GLS_net to identify GLS, resulting in a 72.6% accuracy. Models trained on PlantVillage images were 94.1% accurate at GLS classification with the PlantVillage testing set but performed poorly with the field image dataset (55.1% accuracy). In contrast, the GLS_net model was 78% accurate on the PlantVillage testing set. We conclude that deep learning models trained with realistic mixed disease field data obtain superior degrees of generalizability and external validity when compared to models trained using idealized datasets.

A Lightweight Model for Wheat Ear Fusarium Head Blight Detection Based on RGB Images

Detection of the Fusarium head blight (FHB) is crucial for wheat yield protection, with precise and rapid FHB detection increasing wheat yield and protecting the agricultural ecological environment. FHB detection tasks in agricultural production are currently handled by cloud servers and utilize unmanned aerial vehicles (UAVs). Hence, this paper proposed a lightweight model for wheat ear FHB detection based on UAV-enabled edge computing, aiming to achieve the purpose of intelligent prevention and control of agricultural disease. Our model utilized the You Only Look Once version 4 (YOLOv4) and MobileNet deep learning architectures and was applicable in edge devices, balancing accuracy, and FHB detection in real-time. Specifically, the backbone network Cross Stage Partial Darknet53 (CSPDarknet53) of YOLOv4 was replaced by a lightweight network, significantly decreasing the network parameters and the computing complexity. Additionally, we employed the Complete Intersection over Union (CIoU) and Non-Maximum Suppression (NMS) to regress the loss function to guarantee the detection accuracy of FHB. Furthermore, the loss function incorporated the focal loss to reduce the error caused by the unbalanced positive and negative sample distribution. Finally, mixed-up and transfer learning schemes enhanced the model’s generalization ability. The experimental results demonstrated that the proposed model performed admirably well in detecting FHB of the wheat ear, with an accuracy of 93.69%, and it was somewhat better than the MobileNetv2-YOLOv4 model (F1 by 4%, AP by 3.5%, Recall by 4.1%, and Precision by 1.6%). Meanwhile, the suggested model was scaled down to a fifth of the size of the state-of-the-art object detection models. Overall, the proposed model could be deployed on UAVs so that wheat ear FHB detection results could be sent back to the end-users to intelligently decide in time, promoting the intelligent control of agricultural disease.

Two-Stage Convolutional Neural Networks for Diagnosing the Severity of Alternaria Leaf Blotch Disease of the Apple Tree

In many parts of the world, apple trees suffer from severe foliar damage each year due to infection of Alternaria blotch (Alternaria alternata f. sp. Mali), resulting in serious economic losses to growers. Traditional methods for disease detection and severity classification mostly rely on manual labor, which is slow, labor-intensive and highly subjective. There is an urgent need to develop an effective protocol to rapidly and accurately evaluate disease severity. In this study, DeeplabV3+, PSPNet and UNet were used to assess the severity of apple Alternaria leaf blotch. For identifications of leaves and disease areas, the dataset with a total of 5382 samples was randomly split into 74% (4004 samples) for model training, 9% (494 samples) for validation, 8% (444 samples) for testing and 8% (440 samples) for overall testing. Apple leaves were first segmented from complex backgrounds using the deep-learning algorithms with different backbones. Then, the recognition of disease areas was performed on the segmented leaves. The results showed that the PSPNet model with MobileNetV2 backbone exhibited the highest performance in leaf segmentation, with precision, recall and MIoU values of 99.15%, 99.26% and 98.42%, respectively. The UNet model with VGG backbone performed the best in disease-area prediction, with a precision of 95.84%, a recall of 95.54% and a MIoU value of 92.05%. The ratio of disease area to leaf area was calculated to assess the disease severity. The results showed that the average accuracy for severity classification was 96.41%. Moreover, both the correlation coefficient and the consistency correlation coefficient were 0.992, indicating a high agreement between the reference values and the value that the research predicted. This study proves the feasibility of rapid estimation of the severity of apple Alternaria leaf blotch, which will provide technical support for precise application of pesticides.

Objective Phenotyping of Root System Architecture Using Image Augmentation and Machine Learning in Alfalfa (Medicago sativa L.)

Active breeding programs specifically for root system architecture (RSA) phenotypes remain rare; however, breeding for branch and taproot types in the perennial crop alfalfa is ongoing. Phenotyping in this and other crops for active RSA breeding has mostly used visual scoring of specific traits or subjective classification into different root types. While image-based methods have been developed, translation to applied breeding is limited. This research is aimed at developing and comparing image-based RSA phenotyping methods using machine and deep learning algorithms for objective classification of 617 root images from mature alfalfa plants collected from the field to support the ongoing breeding efforts. Our results show that unsupervised machine learning tends to incorrectly classify roots into a normal distribution with most lines predicted as the intermediate root type. Encouragingly, random forest and TensorFlow-based neural networks can classify the root types into branch-type, taproot-type, and an intermediate taproot-branch type with 86% accuracy. With image augmentation, the prediction accuracy was improved to 97%. Coupling the predicted root type with its prediction probability will give breeders a confidence level for better decisions to advance the best and exclude the worst lines from their breeding program. This machine and deep learning approach enables accurate classification of the RSA phenotypes for genomic breeding of climate-resilient alfalfa.

Applications of Fluorescence Spectroscopy, RGB- and MultiSpectral Imaging for Quality Determinations of White Meat: A Review

Fluorescence spectroscopy, color imaging and multispectral imaging (MSI) have emerged as effective analytical methods for the non-destructive detection of quality attributes of various white meat products such as fish, shrimp, chicken, duck and goose. Based on machine learning and convolutional neural network, these techniques can not only be used to determine the freshness and category of white meat through imaging and analysis, but can also be used to detect various harmful substances in meat products to prevent stale and spoiled meat from entering the market and causing harm to consumer health and even the ecosystem. The development of quality inspection systems based on such techniques to measure and classify white meat quality parameters will help improve the productivity and economic efficiency of the meat industry, as well as the health of consumers. Herein, a comprehensive review and discussion of the literature on fluorescence spectroscopy, color imaging and MSI is presented. The principles of these three techniques, the quality analysis models selected and the research results of non-destructive determinations of white meat quality over the last decade or so are analyzed and summarized. The review is conducted in this highly practical research field in order to provide information for future research directions. The conclusions detail how these efficient and convenient imaging and analytical techniques can be used for non-destructive quality evaluation of white meat in the laboratory and in industry.

Wheat-Net: An Automatic Dense Wheat Spike Segmentation Method Based on an Optimized Hybrid Task Cascade Model

Precise segmentation of wheat spikes from a complex background is necessary for obtaining image-based phenotypic information of wheat traits such as yield estimation and spike morphology. A new instance segmentation method based on a Hybrid Task Cascade model was proposed to solve the wheat spike detection problem with improved detection results. In this study, wheat images were collected from fields where the environment varied both spatially and temporally. Res2Net50 was adopted as a backbone network, combined with multi-scale training, deformable convolutional networks, and Generic ROI Extractor for rich feature learning. The proposed methods were trained and validated, and the average precision (AP) obtained for the bounding box and mask was 0.904 and 0.907, respectively, and the accuracy for wheat spike counting was 99.29%. Comprehensive empirical analyses revealed that our method (Wheat-Net) performed well on challenging field-based datasets with mixed qualities, particularly those with various backgrounds and wheat spike adjacence/occlusion. These results provide evidence for dense wheat spike detection capabilities with masking, which is useful for not only wheat yield estimation but also spike morphology assessments.

Evaluation of Ischemic Penumbra in Stroke Patients Based on Deep Learning and Multimodal CT

In order to investigate the value of multimodal CT for quantitative assessment of collateral circulation, ischemic semidark zone, core infarct volume in patients with acute ischemic stroke (AIS), and prognosis assessment in intravenous thrombolytic therapy, segmentation model which is based on the self-attention mechanism is prone to generate attention coefficient maps with incorrect regions of interest. Moreover, the stroke lesion is not clearly characterized, and lesion boundary is poorly differentiated from normal brain tissue, thus affecting the segmentation performance. To address this problem, a primary and secondary path attention compensation network structure is proposed, which is based on the improved global attention upsampling U-Net model. The main path network is responsible for performing accurate lesion segmentation and outputting segmentation results. Likewise, the auxiliary path network generates loose auxiliary attention compensation coefficients, which compensate for possible attention coefficient errors in the main path network. Two hybrid loss functions are proposed to realize the respective functions of main and auxiliary path networks. It is experimentally demonstrated that both the improved global attention upsampling U-Net and the proposed primary and secondary path attention compensation networks show significant improvement in segmentation performance. Moreover, patients with good collateral circulation have a small final infarct area volume and a good clinical prognosis after intravenous thrombolysis. Quantitative assessment of collateral circulation and ischemic semidark zone by multimodal CT can better predict the clinical prognosis of intravenous thrombolysis.

Imaging Spectroscopy and Machine Learning for Intelligent Determination of Potato and Sweet Potato Quality

Imaging spectroscopy has emerged as a reliable analytical method for effectively characterizing and quantifying quality attributes of agricultural products. By providing spectral information relevant to food quality properties, imaging spectroscopy has been demonstrated to be a potential method for rapid and non-destructive classification, authentication, and prediction of quality parameters of various categories of tubers, including potato and sweet potato. The imaging technique has demonstrated great capacities for gaining rapid information about tuber physical properties (such as texture, water binding capacity, and specific gravity), chemical components (such as protein, starch, and total anthocyanin), varietal authentication, and defect aspects. This paper emphasizes how recent developments in spectral imaging with machine learning have enhanced overall capabilities to evaluate tubers. The machine learning algorithms coupled with feature variable identification approaches have obtained acceptable results. This review briefly introduces imaging spectroscopy and machine learning, then provides examples and discussions of these techniques in tuber quality determinations, and presents the challenges and future prospects of the technology. This review will be of great significance to the study of tubers using spectral imaging technology.

A Crop Image Segmentation and Extraction Algorithm Based on Mask RCNN

The wide variety of crops in the image of agricultural products and the confusion with the surrounding environment information makes it difficult for traditional methods to extract crops accurately and efficiently. In this paper, an automatic extraction algorithm is proposed for crop images based on Mask RCNN. First, the Fruits 360 Dataset label is set with Labelme. Then, the Fruits 360 Dataset is preprocessed. Next, the data are divided into a training set and a test set. Additionally, an improved Mask RCNN network model structure is established using the PyTorch 1.8.1 deep learning framework, and path aggregation and features are added to the network design enhanced functions, optimized region extraction network, and feature pyramid network. The spatial information of the feature map is saved by the bilinear interpolation method in ROIAlign. Finally, the edge accuracy of the segmentation mask is further improved by adding a micro-fully connected layer to the mask branch of the ROI output, employing the Sobel operator to predict the target edge, and adding the edge loss to the loss function. Compared with FCN and Mask RCNN and other image extraction algorithms, the experimental results demonstrate that the improved Mask RCNN algorithm proposed in this paper is better in the precision, Recall, Average precision, Mean Average Precision, and F1 scores of crop image extraction results.

DeepCob: precise and high-throughput analysis of maize cob geometry using deep learning with an application in genebank phenomics

BACKGROUND

Maize cobs are an important component of crop yield that exhibit a high diversity in size, shape and color in native landraces and modern varieties. Various phenotyping approaches were developed to measure maize cob parameters in a high throughput fashion. More recently, deep learning methods like convolutional neural networks (CNNs) became available and were shown to be highly useful for high-throughput plant phenotyping. We aimed at comparing classical image segmentation with deep learning methods for maize cob image segmentation and phenotyping using a large image dataset of native maize landrace diversity from Peru.

RESULTS

Comparison of three image analysis methods showed that a Mask R-CNN trained on a diverse set of maize cob images was highly superior to classical image analysis using the Felzenszwalb-Huttenlocher algorithm and a Window-based CNN due to its robustness to image quality and object segmentation accuracy ([Formula: see text]). We integrated Mask R-CNN into a high-throughput pipeline to segment both maize cobs and rulers in images and perform an automated quantitative analysis of eight phenotypic traits, including diameter, length, ellipticity, asymmetry, aspect ratio and average values of red, green and blue color channels for cob color. Statistical analysis identified key training parameters for efficient iterative model updating. We also show that a small number of 10-20 images is sufficient to update the initial Mask R-CNN model to process new types of cob images. To demonstrate an application of the pipeline we analyzed phenotypic variation in 19,867 maize cobs extracted from 3449 images of 2484 accessions from the maize genebank of Peru to identify phenotypically homogeneous and heterogeneous genebank accessions using multivariate clustering.

CONCLUSIONS

Single Mask R-CNN model and associated analysis pipeline are widely applicable tools for maize cob phenotyping in contexts like genebank phenomics or plant breeding.