Optimized deep learning network for plant leaf disease segmentation and multi-classification using leaf images.

Automatic detection of plant diseases is very imperative for monitoring the plants because they are one of the major concerns in the agricultural sector. Continuous monitoring can combat diseases of plants, which contribute to production loss. In the global production of agricultural goods, the disease of plants plays a significant role and harms yield, resulting in losses for the economy, society, and environment. It seems like a difficult and time-consuming task to manually identify diseased symptoms on leaves. The majority of disease symptoms are reflected in plant leaves, but experts in laboratories spend a lot of money and time diagnosing them. The majority of the features, which affect crop superiority and amount are plant or crop diseases. Therefore, classification, segmentation, and recognition of contaminated symptoms at the starting phase of infection is indispensable. Precision agriculture employs a deep learning model to jointly address these issues. In this research, an efficient disease of plant leaf segmentation and plant leaf disease recognition model is introduced using an optimized deep learning technique. As a result, maximum testing accuracy of 94.69%, sensitivity of 95.58%, and specificity of 92.90% were attained by the optimized deep learning method.

Real-time monitoring of activated sludge flocs via enhanced mask region-based Convolutional Neural networks.

The functionality of activated sludge in wastewater treatment processes depends largely on the structural and microbial composition of its flocs, which are complex assemblages of microorganisms and their secretions. However, monitoring these flocs in real-time and consistently has been challenging due to the lack of suitable technologies and analytical methods. Here we present a laboratory setup capable of capturing instantaneous microscopic images of activated sludge, along with algorithms to interpret these images. To improve floc identification, an advanced Mask R-CNN-based segmentation that integrates a Dual Attention Network (DANet) with an enhanced Feature Pyramid Network (FPN) was used to enhance feature extraction and segmentation accuracy. Additionally, our novel PointRend module meticulously refines the contours of boundaries, significantly minimising pixel inaccuracies. Impressively, our approach achieved a floc detection accuracy of >95%. This development marks a significant advancement in real-time sludge monitoring, offering essential insights for optimising wastewater treatment operations proactively.

Smart plant disease net: Adaptive Dense Hybrid Convolution network with attention mechanism for IoT-based plant disease detection by improved optimization approach.

Plant diseases are rising nowadays. Plant diseases lead to high economic losses. Internet of Things (IoT) technology has found its application in various sectors. This led to the introduction of smart farming, in which IoT has been utilized to help identify the exact spot of the diseased affected region on the leaf from the vast farmland in a well-organized and automated manner. Thus, the main focus of this task is the introduction of a novel plant disease detection model that relies on IoT technology. The collected images are given to the Image Transmission phase. Here, the encryption task is performed by employing the Advanced Encryption Standard (AES) and also the decrypted plant images are fed to the pre-processing stage. The Mask Regions with Convolutional Neural Networks (R-CNN) are used to segment the pre-processed images. Then, the segmented images are given to the detection phase in which the Adaptive Dense Hybrid Convolution Network with Attention Mechanism (ADHCN-AM) approach is utilized to perform the detection of plant disease. From the ADHCN-AM, the final detected plant disease outcomes are obtained. Throughout the entire validation, the offered model shows 95% enhancement in terms of MCC showcasing its effectiveness over the existing approaches.

Dilated Heterogeneous Convolution for Cell Detection and Segmentation Based on Mask R-CNN.

Owing to the variable shapes, large size difference, uneven grayscale, and dense distribution among biological cells in an image, it is very difficult to accurately detect and segment cells. Especially, it is a serious challenge for some microscope imaging devices with limited resources owing to a large number of learning parameters and computational burden when using the standard Mask R-CNN. In this work, we propose a mask R-DHCNN for cell detection and segmentation. More specifically, Dilation Heterogeneous Convolution (DHConv) is proposed by designing a novel convolutional kernel structure (i.e., DHConv), which integrates the strengths of the heterogeneous kernel structure and dilated convolution. Then, the traditional homogeneous convolution structure of the standard Mask R-CNN is replaced with the proposed DHConv module to it adapt to shape and size differences encountered in cell detection and segmentation tasks. Finally, a series of comparison and ablation experiments are conducted on various biological cell datasets (such as U373, GoTW1, SIM+, and T24) to verify the effectiveness of the proposed method. The results show that the proposed method can obtain better performance than some state-of-the-art methods in multiple metrics (including AP, Precision, Recall, Dice, and PQ) while maintaining competitive FLOPs and FPS.

Development of an Artificial Vision for a Parallel Manipulator Using Machine-to-Machine Technologies.

This research focuses on developing an artificial vision system for a flexible delta robot manipulator and integrating it with machine-to-machine (M2M) communication to optimize real-time device interaction. This integration aims to increase the speed of the robotic system and improve its overall performance. The proposed combination of an artificial vision system with M2M communication can detect and recognize targets with high accuracy in real time within the limited space considered for positioning, further localization, and carrying out manufacturing processes such as assembly or sorting of parts. In this study, RGB images are used as input data for the MASK-R-CNN algorithm, and the results are processed according to the features of the delta robot arm prototype. The data obtained from MASK-R-CNN are adapted for use in the delta robot control system, considering its unique characteristics and positioning requirements. M2M technology enables the robot arm to react quickly to changes, such as moving objects or changes in their position, which is crucial for sorting and packing tasks. The system was tested under near real-world conditions to evaluate its performance and reliability.

Automated estimation of stomatal number and aperture in haskap (Lonicera caerulea L.).

MAIN CONCLUSION: This study developed the reliable Mask R-CNN model to detect stomata in Lonicera caerulea. The obtained data could be utilized for evaluating some characters such as stomatal number and aperture area. The native distribution of haskap (Lonicera caerulea L.), a small-shrub species, extends through Northern Eurasia, Japan, and North America. Stomatal observation is important for plant research to evaluate the physiological status and to investigate the effect of ploidy levels on phenotypes. However, manual annotation of stomata using microscope software or ImageJ is time consuming. Therefore, an efficient method to phenotype stomata is needed. In this study, we used the Mask Regional Convolutional Neural Network (Mask R-CNN), a deep learning model, to analyze the stomata of haskap efficiently and accurately. We analyzed haskap plants (dwarf and giant phenotypes) with the same ploidy but different phenotypes, including leaf area, stomatal aperture area, stomatal density, and total number of stomata. The R-square value of the estimated stomatal aperture area was 0.92 and 0.93 for the dwarf and giant plants, respectively. The R-square value of the estimated stomatal number was 0.99 and 0.98 for the two phenotypes. The results showed that the measurements obtained using the models were as accurate as the manual measurements. Statistical analysis revealed that the stomatal density of the dwarf plants was higher than that of the giant plants, but the maximum stomatal aperture area, average stomatal aperture area, total number of stomata, and average leaf area were lower than those of the giant plants. A high-precision, rapid, and large-scale detection method was developed by training the Mask R-CNN model. This model can help save time and increase the volume of data.

Deep learning-based high-throughput detection of in vitro germination to assess pollen viability from microscopic images.

In vitro pollen germination is considered the most efficient method to assess pollen viability. The pollen germination frequency and pollen tube length, which are key indicators of pollen viability, should be accurately measured during in vitro culture. In this study, a Mask R-CNN model trained using microscopic images of tree peony (Paeonia suffruticosa) pollen has been proposed to rapidly detect the pollen germination rate and pollen tube length. To reduce the workload during image acquisition, images of synthesized crossed pollen tubes were added to the training dataset, significantly improving the model accuracy in recognizing crossed pollen tubes. At an Intersection over Union threshold of 50%, a mean average precision of 0.949 was achieved. The performance of the model was verified using 120 testing images. The R2 value of the linear regression model using detected pollen germination frequency against the ground truth was 0.909 and that using average pollen tube length was 0.958. Further, the model was successfully applied to two other plant species, indicating a good generalizability and potential to be applied widely.

Detection and Segmentation of Breast Masses Based on Multi-Layer Feature Fusion.

In breast mass detection, there are many different sizes of masses in the image. However, when the existing target detection model is directly used to detect the breast mass, it is easy to appear the phenomenon of misdetection and missed detection. Therefore, in order to improve the detection accuracy of breast masses, this paper proposed a target detection model D-Mask R-CNN based on Mask R-CNN, which is suitable for breast masses detection. Firstly, this paper improved the internal structure of FPN, and modified the lateral connection mode in the original FPN structure to dense connection. Secondly, modified the size of the anchor of RPN to improve the location accuracy of breast masses. Finally, Soft-NMS was used to replace the NMS in the original model to reduce the possibility that the correct prediction results may be eliminated during the NMS process. This paper used the CBIS-DDSM dataset for all experiments. The results showed that the mAP value of the improved model for detecting breast masses reached 0.66 in the test set, which was 0.05 higher than that of the original Mask R-CNN.

A novel approach for screening standard anteroposterior pelvic radiographs in children.

Anteroposterior pelvic radiography is the first-line imaging modality for diagnosing developmental dysplasia of the hip (DDH). Nonstandard radiographs with pelvic malposition make the correct diagnosis of DDH challenging. However, as the only method available for screening standard pelvic radiographs, traditional manual assessment is relatively laborious and potentially erroneous. We retrospectively collected 3,247 pelvic radiographs. There were 2,887 radiographs randomly selected to train and optimize the AI model. Then 362 radiographs were used to test the model's diagnostic performance. Its diagnostic accuracy was assessed using receiver operating characteristic (ROC) curves and measurement consistency using Bland-Altman plots. In 362 radiographs, the AI model's area under ROC curves, accuracy, sensitivity, and specificity for quality assessment was 0.993, 99.4% (360/362), 98.6% (138/140), and 100.0% (222/222), respectively. Compared with clinicians, the 95% limits of agreement (Bland-Altman analysis) for pelvic tilt index (PTI) and pelvic rotation index (PRI), as determined by the model, were -0.052-0.072 and -0.088-0.055, respectively. CONCLUSIONS: The artificial intelligence-assisted method was more efficient and highly consistent with clinical experts. This method can be used for real-time validation of the quality of pelvic radiographs in current picture archiving and communications systems (PACS). WHAT IS KNOWN: • Nonstandard pediatric radiographs with pelvic malposition make the correct diagnosis of developmental dysplasia of the hip (DDH) challenging. • Traditional manual assessment remains the only method available for screening standard pediatric pelvic radiographs, which is relatively laborious and potentially erroneous. WHAT IS NEW: • This study proposed an artificial intelligence-assisted model to assess the quality of pediatric pelvic radiographs accurately and efficiently. • We recommend the integration of the model into current picture archiving and communications systems (PACS) for real-time screening of standard pediatric pelvic radiographs.

Enhance the Accuracy of Landslide Detection in UAV Images Using an Improved Mask R-CNN Model: A Case Study of Sanming, China.

Extracting high-accuracy landslide areas using deep learning methods from high spatial resolution remote sensing images is a hot topic in current research. However, the existing deep learning algorithms are affected by background noise and landslide scale effects during the extraction process, leading to poor feature extraction effects. To address this issue, this paper proposes an improved mask regions-based convolutional neural network (Mask R-CNN) model to identify the landslide distribution in unmanned aerial vehicles (UAV) images. The improvement of the model mainly includes three aspects: (1) an attention mechanism of the convolutional block attention module (CBAM) is added to the backbone residual neural network (ResNet). (2) A bottom-up channel is added to the feature pyramidal network (FPN) module. (3) The region proposal network (RPN) is replaced by guided anchoring (GA-RPN). Sanming City, China was selected as the study area for the experiments. The experimental results show that the improved model has a recall of 91.4% and an accuracy of 92.6%, which is 12.9% and 10.9% higher than the original Mask R-CNN model, respectively, indicating that the improved model is more effective in landslide extraction.

Improved Mask R-CNN Multi-Target Detection and Segmentation for Autonomous Driving in Complex Scenes.

Vision-based target detection and segmentation has been an important research content for environment perception in autonomous driving, but the mainstream target detection and segmentation algorithms have the problems of low detection accuracy and poor mask segmentation quality for multi-target detection and segmentation in complex traffic scenes. To address this problem, this paper improved the Mask R-CNN by replacing the backbone network ResNet with the ResNeXt network with group convolution to further improve the feature extraction capability of the model. Furthermore, a bottom-up path enhancement strategy was added to the Feature Pyramid Network (FPN) to achieve feature fusion, while an efficient channel attention module (ECA) was added to the backbone feature extraction network to optimize the high-level low resolution semantic information graph. Finally, the bounding box regression loss function smooth L1 loss was replaced by CIoU loss to speed up the model convergence and minimize the error. The experimental results showed that the improved Mask R-CNN algorithm achieved 62.62% mAP for target detection and 57.58% mAP for segmentation accuracy on the publicly available CityScapes autonomous driving dataset, which were 4.73% and 3.96%% better than the original Mask R-CNN algorithm, respectively. The migration experiments showed that it has good detection and segmentation effects in each traffic scenario of the publicly available BDD autonomous driving dataset.

An Improved Mask R-CNN Micro-Crack Detection Model for the Surface of Metal Structural Parts.

Micro-crack detection is an essential task in critical equipment health monitoring. Accurate and timely detection of micro-cracks can ensure the healthy and stable service of equipment. Aiming at improving the low accuracy of the conventional target detection model during the task of detecting micro-cracks on the surface of metal structural parts, this paper built a micro-cracks dataset and explored a detection performance optimization method based on Mask R-CNN. Firstly, we improved the original FPN structure, adding a bottom-up feature fusion path to enhance the information utilization rate of the underlying feature layer. Secondly, we added the methods of deformable convolution kernel and attention mechanism to ResNet, which can improve the efficiency of feature extraction. Lastly, we modified the original loss function to optimize the network training effect and model convergence rate. The ablation comparison experiments shows that all the improvement schemes proposed in this paper have improved the performance of the original Mask R-CNN. The integration of all the improvement schemes can produce the most significant performance improvement effects in recognition, classification, and positioning simultaneously, thus proving the rationality and feasibility of the improved scheme in this paper.

Automatic Spine Segmentation and Parameter Measurement for Radiological Analysis of Whole-Spine Lateral Radiographs Using Deep Learning and Computer Vision.

Radiographic examination is essential for diagnosing spinal disorders, and the measurement of spino-pelvic parameters provides important information for the diagnosis and treatment planning of spinal sagittal deformities. While manual measurement methods are the golden standard for measuring parameters, they can be time consuming, inefficient, and rater dependent. Previous studies that have used automatic measurement methods to alleviate the downsides of manual measurements showed low accuracy or could not be applied to general films. We propose a pipeline for automated measurement of spinal parameters by combining a Mask R-CNN model for spine segmentation with computer vision algorithms. This pipeline can be incorporated into clinical workflows to provide clinical utility in diagnosis and treatment planning. A total of 1807 lateral radiographs were used for the training (n = 1607) and validation (n = 200) of the spine segmentation model. An additional 200 radiographs, which were also used for validation, were examined by three surgeons to evaluate the performance of the pipeline. Parameters automatically measured by the algorithm in the test set were statistically compared to parameters measured manually by the three surgeons. The Mask R-CNN model achieved an average precision at 50% intersection over union (AP50) of 96.2% and a Dice score of 92.6% for the spine segmentation task in the test set. The mean absolute error values of the spino-pelvic parameters measurement results were within the range of 0.4° (pelvic tilt) to 3.0° (lumbar lordosis, pelvic incidence), and the standard error of estimate was within the range of 0.5° (pelvic tilt) to 4.0° (pelvic incidence). The intraclass correlation coefficient values ranged from 0.86 (sacral slope) to 0.99 (pelvic tilt, sagittal vertical axis).

Prognosticating various acute covid lung disorders from COVID-19 patient using chest CT Images.

The global spread of coronavirus illness has surged dramatically, resulting in a catastrophic pandemic situation. Despite this, accurate screening remains a significant challenge due to difficulties in categorizing infection regions and the minuscule difference between typical pneumonia and COVID (Coronavirus Disease) pneumonia. Diagnosing COVID-19 using the Mask Regional-Convolutional Neural Network (Mask R-CNN) is proposed to classify the chest computerized tomographic (CT) images into COVID-positive and COVID-negative. Covid-19 has a direct effect on the lungs, causing damage to the alveoli, which leads to various lung complications. By fusing multi-class data, the severity level of the patients can be classified using the meta-learning few-shot learning technique with the residual network with 50 layers deep (ResNet-50) as the base classifier. It has been tested with the outcome of COVID positive chest CT image data. From these various classes, it is possible to predict the onset possibilities of acute COVID lung disorders such as sepsis, acute respiratory distress syndrome (ARDS), COVID pneumonia, COVID bronchitis, etc. The first method of classification is proposed to diagnose whether the patient is affected by COVID-19 or not; it achieves a mean Average Precision (mAP) of 91.52% and G-mean of 97.69% with 98.60% of classification accuracy. The second method of classification is proposed for the detection of various acute lung disorders based on severity provide better performance in all the four stages, the average accuracy is of 95.4%, the G-mean for multiclass achieves 94.02%, and the AUC is 93.27% compared with the cutting-edge techniques. It enables healthcare professionals to correctly detect severity for potential treatments.

Visual Sorting of Express Packages Based on the Multi-Dimensional Fusion Method under Complex Logistics Sorting.

Visual sorting of express packages is faced with many problems such as the various types, complex status, and the changeable detection environment, resulting in low sorting efficiency. In order to improve the sorting efficiency of packages under complex logistics sorting, a multi-dimensional fusion method (MDFM) for visual sorting in actual complex scenes is proposed. In MDFM, the Mask R-CNN is designed and applied to detect and recognize different kinds of express packages in complex scenes. Combined with the boundary information of 2D instance segmentation from Mask R-CNN, the 3D point cloud data of grasping surface is accurately filtered and fitted to determining the optimal grasping position and sorting vector. The images of box, bag, and envelope, which are the most common types of express packages in logistics transportation, are collected and the dataset is made. The experiments with Mask R-CNN and robot sorting were carried out. The results show that Mask R-CNN achieves better results in object detection and instance segmentation on the express packages, and the robot sorting success rate by the MDFM reaches 97.2%, improving 2.9, 7.5, and 8.0 percentage points, respectively, compared to baseline methods. The MDFM is suitable for complex and diverse actual logistics sorting scenes, and improves the efficiency of logistics sorting, which has great application value.

CellSeg: a robust, pre-trained nucleus segmentation and pixel quantification software for highly multiplexed fluorescence images.

BACKGROUND: Algorithmic cellular segmentation is an essential step for the quantitative analysis of highly multiplexed tissue images. Current segmentation pipelines often require manual dataset annotation and additional training, significant parameter tuning, or a sophisticated understanding of programming to adapt the software to the researcher's need. Here, we present CellSeg, an open-source, pre-trained nucleus segmentation and signal quantification software based on the Mask region-convolutional neural network (R-CNN) architecture. CellSeg is accessible to users with a wide range of programming skills. RESULTS: CellSeg performs at the level of top segmentation algorithms in the 2018 Kaggle Data Challenge both qualitatively and quantitatively and generalizes well to a diverse set of multiplexed imaged cancer tissues compared to established state-of-the-art segmentation algorithms. Automated segmentation post-processing steps in the CellSeg pipeline improve the resolution of immune cell populations for downstream single-cell analysis. Finally, an application of CellSeg to a highly multiplexed colorectal cancer dataset acquired on the CO-Detection by indEXing (CODEX) platform demonstrates that CellSeg can be integrated into a multiplexed tissue imaging pipeline and lead to accurate identification of validated cell populations. CONCLUSION: CellSeg is a robust cell segmentation software for analyzing highly multiplexed tissue images, accessible to biology researchers of any programming skill level.

Implementation and Practice of Deep Learning-Based Instance Segmentation Algorithm for Quantification of Hepatic Fibrosis at Whole Slide Level in Sprague-Dawley Rats.

Exponential development in artificial intelligence or deep learning technology has resulted in more trials to systematically determine the pathological diagnoses using whole slide images (WSIs) in clinical and nonclinical studies. In this study, we applied Mask Regions with Convolution Neural Network (Mask R-CNN), a deep learning model that uses instance segmentation, to detect hepatic fibrosis induced by N-nitrosodimethylamine (NDMA) in Sprague-Dawley rats. From 51 WSIs, we collected 2011 cropped images with hepatic fibrosis annotations. Training and detection of hepatic fibrosis via artificial intelligence methods was performed using Tensorflow 2.1.0, powered by an NVIDIA 2080 Ti GPU. From the test process using tile images, 95% of model accuracy was verified. In addition, we validated the model to determine whether the predictions by the trained model can reflect the scoring system by the pathologists at the WSI level. The validation was conducted by comparing the model predictions in 18 WSIs at 20× and 10× magnifications with ground truth annotations and board-certified pathologists. Predictions at 20× showed a high correlation with ground truth (R2 = 0.9660) and a good correlation with the average fibrosis rank by pathologists (R2 = 0.8887). Therefore, the Mask R-CNN algorithm is a useful tool for detecting and quantifying pathological findings in nonclinical studies.

Research on Vehicle Lane Change Warning Method Based on Deep Learning Image Processing.

In order to improve vehicle driving safety in a low-cost manner, we used a monocular camera to study a lane-changing warning algorithm for highway vehicles based on deep learning image processing technology. We improved the mask region-based convolutional neural network for vehicle target detection. Suitable anchor frame ratios were obtained by means of K-means++ method clustering for 66,389 vehicle targets with the width/height ratio, which is one more set of anchor frames than the original setting, so as to ensure that the generation accuracy of candidate frames can be improved without sacrificing more network performance. Using the vehicle target annotation set, we trained the vehicle targets. Through the analysis of indicators for mean average precision, a new set of anchor frames was added to improve the accuracy of vehicle target detection. Based on the improved vehicle detection network and an end-to-end lane detection network in series, we proposed an algorithm for the detection of highway vehicle lane-changing behavior with the first-person perspective by summing the inter-frame change rates in the vehicle lane-changing data pool. After the identification and verification of the marked lane-changing picture sequences, a lane-changing detection accuracy rate of 94.5% was achieved.

Study on Accuracy Improvement of Slope Failure Region Detection Using Mask R-CNN with Augmentation Method.

We proposed an automatic detection method of slope failure regions using a semantic segmentation method called Mask R-CNN based on a deep learning algorithm to improve the efficiency of damage assessment in the event of slope failure disaster. There is limited research on detecting landslides by deep learning, and the lack of training data is an important issue to be resolved, as aerial photographs are not taken with sufficient frequency during a disaster. This study attempts to use CutMix-based augmentation to improve detection accuracy. We also compare the detection results obtained by augmentation of multiple patterns. In the comparison of the not augmented data case, the recall increased by 0.186 in the case using the augmented data with the shape of the slope failure region maintained. When the image data was augmented while maintaining the shape of the slope failure region, the recall score indicated the low oversights in the prediction result is 0.701. This is an increase of 0.186 compared to the case where no augmentation was performed. In addition, the F1 score was 0.740, this also increased by 0.139, and high values were obtained for other indicators. Therefore, the method proposed in this study is greatly useful for grasping slope failure regions because of the detection with high accuracy, as described above.

Development of a Large-Scale Roadside Facility Detection Model Based on the Mapillary Dataset.

The detection of road facilities or roadside structures is essential for high-definition (HD) maps and intelligent transportation systems (ITSs). With the rapid development of deep-learning algorithms in recent years, deep-learning-based object detection techniques have provided more accurate and efficient performance, and have become an essential tool for HD map reconstruction and advanced driver-assistance systems (ADASs). Therefore, the performance evaluation and comparison of the latest deep-learning algorithms in this field is indispensable. However, most existing works in this area limit their focus to the detection of individual targets, such as vehicles or pedestrians and traffic signs, from driving view images. In this study, we present a systematic comparison of three recent algorithms for large-scale multi-class road facility detection, namely Mask R-CNN, YOLOx, and YOLOv7, on the Mapillary dataset. The experimental results are evaluated according to the recall, precision, mean F1-score and computational consumption. YOLOv7 outperforms the other two networks in road facility detection, with a precision and recall of 87.57% and 72.60%, respectively. Furthermore, we test the model performance on our custom dataset obtained from the Japanese road environment. The results demonstrate that models trained on the Mapillary dataset exhibit sufficient generalization ability. The comparison presented in this study aids in understanding the strengths and limitations of the latest networks in multiclass object detection on large-scale street-level datasets.