Enhanced radial basis function neural network for tomato plant disease leaf image segmentation

Primary crop losses in agriculture are due to leaf diseases, which farmers cannot identify early. If the diseases are not detected early and correctly, then the farmer will have to undergo huge losses. Therefore, in the field of agriculture, the detection of leaf diseases in tomato crops plays a vital role. Recent advances in computer vision and deep learning techniques have made disease prediction easy in agriculture. Tomato crop front side leaf images are considered for research due to their high exposure to diseases. The image segmentation process assumes a significant role in identifying disease affected areas on tomato leaf images. Therefore, this paper develops an efficient tomato crop leaf disease segmentation model using an enhanced radial basis function neural network (ERBFNN). The proposed ERBFNN is enhanced using the modified sunflower optimization (MSFO) algorithm. Initially, the noise present in the images is removed by a Gaussian filter followed by CLAHE (contrast-limited adaptive histogram equalization) based on contrast enhancement and un-sharp masking. Then, color features are extracted from each leaf image and given to the segmentation stage to segment the disease portion of the input image. The performance of the proposed ERBFNN approach is estimated using different metrics such as accuracy, Jaccard coefficient (JC), Dice's coefficient (DC), precision, recall, F-Measure, sensitivity, specificity, and mean intersection over union (MIoU) and are compared with existing state-of-the-art methods of radial basis function (RBF), fuzzy c-means (FCM), and region growing (RG). The experimental results show that the proposed ERBFNN segmentation model outperformed with an accuracy of 98.92% compared to existing state-of-the-art methods like RBFNN, FCM, and RG, as well as previous research work.     

An artificial neural network approach to identify fungal diseases of cucumber (Cucumis sativus L.) plants using digital image processing

Nowadays, artificial intelligence solutions such as digital image processing and artificial neural networks (ANN) have become important applicable techniques in phytomonitoring and plant health detection systems. In this research, an autonomous device was designed and developed for detecting two types of fungi (Pseudoperonospora cubensis, Sphaerotheca fuliginea) that infect the cucumber (Cucumis sativus L.) plant leaves. This device was able to recognise the fungal diseases of plants by detecting their symptoms on plant leaves (downy mildew and powdery mildew). For leaves of cucumber inoculated with different spores of the fungi, it was possible to estimate the amount of hour post inoculation (HPI) by extracting leaves’ image parameters. Device included a dark chamber, a CCD digital camera, a thermal camera, a light dependent resistor lightening module and a personal computer. The proposed programme for precise disease detection was based on an image processing algorithm and ANN. Three textural features and two thermal parameters from the obtained images were measured and normalised. Performance of ANN model was tested successfully for disease recognition and detecting HPI in images using back-propagation supervised learning method and inspection data. Such this machine vision system can be used in robotic intelligent systems to achieve a modern farmer’s assistant in agricultural crop fields.     

An efficient algorithm for retinal blood vessel segmentation using h-maxima transform and multilevel thresholding

Retinal blood vessel detection and analysis play vital roles in early diagnosis and prevention of several diseases, such as hypertension, diabetes, arteriosclerosis, cardiovascular disease and stroke. This paper presents an automated algorithm for retinal blood vessel segmentation. The proposed algorithm takes advantage of powerful image processing techniques such as contrast enhancement, filtration and thresholding for more efficient segmentation. To evaluate the performance of the proposed algorithm, experiments were conducted on 40 images collected from DRIVE database. The results show that the proposed algorithm yields an accuracy rate of 96.5%, which is higher than the results achieved by other known algorithms.     

An efficient algorithm for retinal blood vessel segmentation using h-maxima transform and multilevel thresholding

Retinal blood vessel detection and analysis play vital roles in early diagnosis and prevention of several diseases, such as hypertension, diabetes, arteriosclerosis, cardiovascular disease and stroke. This paper presents an automated algorithm for retinal blood vessel segmentation. The proposed algorithm takes advantage of powerful image processing techniques such as contrast enhancement, filtration and thresholding for more efficient segmentation. To evaluate the performance of the proposed algorithm, experiments were conducted on 40 images collected from DRIVE database. The results show that the proposed algorithm yields an accuracy rate of 96.5%, which is higher than the results achieved by other known algorithms.     

LEMOXINET: Lite ensemble MobileNetV2 and Xception models to predict plant disease

Plant diseases play a significant role in agricultural production, in which early detection of plant diseases is deemed an essential task. Current computational intelligence and computer vision methods have been promising to improve disease diagnosis. Convolutional Neural Networks (CNN) models are capable of detecting plant diseases in an agricultural field and plantation leaf images. MobileNetV2 refers to an appropriate CNN model for mobile devices with subordinate parameters and model file sizes. However, the effectiveness of MobileNetV2 requires improvement to capture more critical features. Xception refers to the extension of InceptionV3 with fewer and excellent parameters in extracting features. This research suggests an ensemble of MobileNetV2 and Xception by concatenating the extracted features to improve plant disease detection performance. This study indicated that MobileNetV2, Xception, and ensemble model achieved 97.32%, 98.30%, and 99.10% accuracy when considering the entire Plant Village dataset. Particularly, MobileNetV2 and Xception models' accuracy improved by 1.8% and 0.8%, respectively. In addition, our model captures 99.52% of all metric scores in the user-defined dataset. Our model indicated better performance than the seven state-of-the-art CNN models, both individually and in ensemble design. It can be integrated with mobile devices, providing fewer parameters and model file size than an ensemble of MobileNetV2 with InceptionResnetV2, VGG19, and VGG16.     

A deep learning-based approach for detecting plant organs from digitized herbarium specimen images

Herbarium specimens are excellent sources of botanical information to facilitate understanding and monitoring the evolution of plants and their effects on global climate change. Globally, many herbaria have undertaken digitization projects of herbarium specimens to preserve them and make them accessible in online repositories to botanists and ecologists. Automated detection of plant organs such as plant leaves, buds, flowers, and fruits on the digitized herbarium specimen images provides valuable information in various scientific contexts. We developed a deep learning approach based on the refined YOLO-V3 approach to detect plant organs within the digitized herbarium specimen images effectively. The proposed approach combines ResNet and DenseNet architectures to improve feature extraction capabilities. Also, a new scale of feature map is added to the existing scales to address the problem of YOLO-V3's low performance in detecting small plant organs. The experimental results demonstrate that our proposed approach can detect organs of different sizes within different specimens, where the precision and recall reached 94.2% and 95.5%, respectively.     

Classification of Different Tympanic Membrane Conditions Using Fused Deep Hypercolumn Features and Bidirectional LSTM

Objectives: Middle ear inflammatory diseases are global health problem that can have serious consequences such as hearing loss and speech disorders. The high cost of medical devices such as oto-endoscope and oto-microscope used by the specialists for the diagnosis of the disease prevents its widespread use. In addition, the decisions of otolaryngologists may differ due to the subjective visual examinations. For this reason, computer-aided middle ear disease diagnosis systems are needed to eliminate subjective diagnosis and high cost problems. To this aim, a hybrid deep learning approach was proposed for automatic recognition of different tympanic membrane conditions such as earwax plug, myringosclerosis, chronic otitis media and normal from the otoscopy images.Materials and methods: In this study we used public Ear Imagery dataset containing 880 otoscopy images. The proposed approach detects keypoints from the otoscopy images and following the obtained keypoint positions, extracts hypercolumn deep features from 5 different layers of the VGG 16 model. Classification of tympanic membrane conditions were realized by feeding the deep hypercolumn features to Bi-LSTM network in the form of non-time related data.Results: The performance of the proposed model was evaluated in three different color spaces as Red-Green-Blue (RGB), Hue-Saturation-Value (HSV) and Haematoxylin-Eosin-Diaminobenzidine (HED). The proposed model achieved acceptable results in all color spaces, moreover it showed a very successful performance in classifying tympanic membrane conditions especially in RGB space. Experimental studies showed that the proposed model achieved Acc of 99.06%, Sen of 98.13% and Spe of 99.38%.Conclusion: As a result, a robust model with high sensitivity was obtained for classification of tympanic membrane conditions and it was shown that Bi-LSTM network, which is generally used with time-related data, could also be used successfully with non-time related data for diagnosis of tympanic membrane conditions.     

Recognition method of soybean leaf diseases using residual neural network based on transfer learning

Leaf disease is an important factor restricting the high quality and high yield of the soybean plant. Insufficient control of soybean diseases will destroy the local ecological environment and break the stability of the food chain. To overcome the low accuracy in recognizing soybean leaf diseases using traditional deep learning models and complexity in chemical analysis operations, in this study, a recognition model of soybean leaf diseases was proposed based on an improved deep learning model. First, four types of soybean diseases (Septoria Glycines Hemmi, Soybean Brown Leaf Spot, Soybean Frogeye Leaf Spot, and Soybean Phyllosticta Leaf Spot) were taken as research objects. Second, image preprocessing and data expansion of original images were carried out using image registration, image segmentation, region calibration and data enhancement. The data set containing 53, 250 samples was randomly divided into the training set, verification set, and test set according to the ratio of 7:2:1. Third, the convolution layer weight of the pre-training model based on the ImageNet open data set was transferred to the convolution layer of the ResNet18 model to reconstruct the global average pooling layer and the fully connected layer for constructing recognition model of TRNet18 model. Finally, the recognition accuracy of the four leaf diseases reached 99.53%, the Macro-F1 was 99.54%, and the average recognition time was 0.047184 s. Compared with AlexNet, ResNet18, ResNet50, and TRNet50 models, the recognition accuracy and Macro-F1 of the TRNet18 model were improved by 6.03% and 5.99% respectively, and the model recognition time was saved by 16.67%, The results showed that the proposed TRNet18 model had higher classification accuracy and stronger robustness, which can not only provide a reference for accurate recognition of other crop diseases, but also be transplanted to the mobile terminal for recognition of crop leaf diseases.     

A diabetic retinopathy detection method using an improved pillar K-means algorithm

The paper presents a new approach for medical image segmentation. Exudates are a visible sign of diabetic retinopathy that is the major reason of vision loss in patients with diabetes. If the exudates extend into the macular area, blindness may occur. Automated detection of exudates will assist ophthalmologists in early diagnosis. This segmentation process includes a new mechanism for clustering the elements of high-resolution images in order to improve precision and reduce computation time. The system applies K-means clustering to the image segmentation after getting optimized by Pillar algorithm; pillars are constructed in such a way that they can withstand the pressure. Improved pillar algorithm can optimize the K-means clustering for image segmentation in aspects of precision and computation time. This evaluates the proposed approach for image segmentation by comparing with Kmeans and Fuzzy C-means in a medical image. Using this method, identification of dark spot in the retina becomes easier and the proposed algorithm is applied on diabetic retinal images of all stages to identify hard and soft exudates, where the existing pillar K-means is more appropriate for brain MRI images. This proposed system help the doctors to identify the problem in the early stage and can suggest a better drug for preventing further retinal damage.     

Automated Detection Framework of the Calcified Plaque with Acoustic Shadowing in IVUS Images

Intravascular Ultrasound (IVUS) is one ultrasonic imaging technology to acquire vascular cross-sectional images for the visualization of the inner vessel structure. This technique has been widely used for the diagnosis and treatment of coronary artery diseases. The detection of the calcified plaque with acoustic shadowing in IVUS images plays a vital role in the quantitative analysis of atheromatous plaques. The conventional method of the calcium detection is manual drawing by the doctors. However, it is very time-consuming, and with high inter-observer and intra-observer variability between different doctors. Therefore, the computer-aided detection of the calcified plaque is highly desired. In this paper, an automated method is proposed to detect the calcified plaque with acoustic shadowing in IVUS images by the Rayleigh mixture model, the Markov random field, the graph searching method and the prior knowledge about the calcified plaque. The performance of our method was evaluated over 996 in-vivo IVUS images acquired from eight patients, and the detected calcified plaques are compared with manually detected calcified plaques by one cardiology doctor. The experimental results are quantitatively analyzed separately by three evaluation methods, the test of the sensitivity and specificity, the linear regression and the Bland-Altman analysis. The first method is used to evaluate the ability to distinguish between IVUS images with and without the calcified plaque, and the latter two methods can respectively measure the correlation and the agreement between our results and manual drawing results for locating the calcified plaque in the IVUS image. High sensitivity (94.68%) and specificity (95.82%), good correlation and agreement (>96.82% results fall within the 95% confidence interval in the Student t-test) demonstrate the effectiveness of the proposed method in the detection of the calcified plaque with acoustic shadowing in IVUS images.     

A Hybrid Deep Learning Model for Predicting Molecular Subtypes of Human Breast Cancer Using Multimodal Data

BackgroundThe prediction of breast cancer subtypes plays a key role in the diagnosis and prognosis of breast cancer. In recent years, deep learning (DL) has shown good performance in the intelligent prediction of breast cancer subtypes. However, most of the traditional DL models use single modality data, which can just extract a few features, so it cannot establish a stable relationship between patient characteristics and breast cancer subtypes.DatasetWe used the TCGA-BRCA dataset as a sample set for molecular subtype prediction of breast cancer. It is a public dataset that can be obtained through the following link: https://portal.gdc.cancer.gov/projects/TCGA-BRCAMethodsIn this paper, a Hybrid DL model based on the multimodal data is proposed. We combine the patient's gene modality data with image modality data to construct a multimodal fusion framework. According to the different forms and states, we set up feature extraction networks respectively, and then we fuse the output of the two feature networks based on the idea of weighted linear aggregation. Finally, the fused features are used to predict breast cancer subtypes. In particular, we use the principal component analysis to reduce the dimensionality of high-dimensional data of gene modality and filter the data of image modality. Besides, we also improve the traditional feature extraction network to make it show better performance.ResultsThe results show that compared with the traditional DL model, the Hybrid DL model proposed in this paper is more accurate and efficient in predicting breast cancer subtypes. Our model achieved a prediction accuracy of 88.07% in 10 times of 10-fold cross-validation. We did a separate AUC test for each subtype, and the average AUC value obtained was 0.9427. In terms of subtype prediction accuracy, our model is about 7.45% higher than the previous average.     

Pine pest detection using remote sensing satellite images combined with a multi-scale attention-UNet model

Pest monitoring of forest areas is essential to pest control. The existing remote sensing satellite image methods have been widely used in detecting pine wilt disease due to their low cost and large detection range. However, most existing methods for pine wilt disease detection are based on multi-phase remote sensing satellite imagery and use manually designed features or machine learning-based algorithms. This makes these methods time-consuming and does not allow early detection of pest-infested forests and can also lead to further spread of the disease. In addition, machine learning-based algorithms can have poor detection performance and generalization ability. To address these shortcomings, this paper uses the pine forest in the Qingyuan area of Liaoning Province in China as a study area to analyze the physiological characteristics of pine pests based on the aerial photography data collected by a Quadrotor-type unmanned aerial vehicle (UAV). By combining these data with the artificial field survey data, the pest-infested areas of forest are marked in the Landsat 8 satellite remote sensing (SRS) images. Further, an end-to-end automatic pest detection framework is designed based on a multi-scale attention-UNet (MA-UNet) model and monophasic images. In addition, the detection performance of the developed model is further optimized using the data augmentation technique to extend the labeled dataset. Compared with the traditional model, the proposed model achieves a much better recall rate of 57.38% in detecting pest-infested forest areas, while the recall rates of the Support Vector Machine (SVM), UNet, attention-UNet, and MedT models are 14.38%, 49.33%, 48.02%, and 33.64%, respectively. According to the results, the proposed model can achieve timely detection and screening of pest-infested forest areas, improving forest management efficiency.     

A robust deep attention dense convolutional neural network for plant leaf disease identification and classification from smart phone captured real world images

Plant diseases cause significant food loss and hence economic loss around the globe. Therefore, automatic plant disease identification is a primary task to take proper medications for controlling the spread of the diseases. Large variety of plants species and their dissimilar phytopathological symptoms call for the implementation of supervised machine learning techniques for efficient and reliable disease identification and classification. With the development of deep learning strategies, convolutional neural network (CNN) has paved its way for classification of multiple plant diseases by extracting rich features. However, several characteristics of the input images especially captured in real world environment, viz. complex or indistinguishable background, presence of multiple leaves with the diseased leaf, small lesion area, solemnly affect the robustness and accuracy of the CNN modules. Available strategies usually applied standard CNN architectures on the images captured in the laboratory environment and very few have considered practical in-field leaf images for their studies. However, those studies are limited with very limited number of plant species. Therefore, there is need of a robust CNN module which can successfully recognize and classify the dissimilar leaf health conditions of non-identical plants from the in-field RGB images. To achieve the above goal, an attention dense learning (ADL) mechanism is proposed in this article by merging mixed sigmoid attention learning with the basic dense learning process of deep CNN. The basic dense learning process derives new features at higher layer considering all lower layer features and that provides fast and efficient training process. Further, the attention learning process amplifies the learning ability of the dense block by discriminating the meaningful lesion portions of the images from the background areas. Other than adding an extra layer for attention learning, in the proposed ADL block the output features from higher layer dense learning are used as an attention mask to the lower layers. For an effective and fast classification process, five ADL blocks are stacked to build a new CNN architecture named DADCNN-5 for obtaining classification robustness and higher testing accuracy. Initially, the proposed DADCNN-5 module is applied on publicly available extended PlantVillage dataset to classify 38 different health conditions of 14 plant species from 54,305 images. Classification accuracy of 99.93% proves that the proposed CNN module can be used for successful leaf disease identification. Further, the efficacy of the DADCNN-5 model is checked after performing stringent experiments on a new real world plant leaf database, created by the authors. The new leaf database contains 10,851 real-world RGB leaf images of 17 plant species for classifying their 44 distinguished health conditions. Experimental outcomes reveal that the proposed DADCNN-5 outperforms the existing machine learning and standard CNN architectures, and achieved 97.33% accuracy. The obtained sensitivity, specificity and false positive rate values are 96.57%, 99.94% and 0.063% respectively. The module takes approximately 3235 min for training process and achieves 99.86% of training accuracy. Visualization of Class activation mapping (CAM) depicts that DADCNN-5 is able to learn distinguishable features from semantically important regions (i.e. lesion regions) on the leaves. Further, the robustness of the DADCNN-5 is established after experimenting with augmented and noise contaminated images of the practical database.     

Detection method for Convallaria keiskei colonies in Hokkaido,Japan, by combining CNN and FCM using UAV-based remote sensing data

The Convallaria keiskei, a plant species indigenous to Japan, is on the verge of extinction. In the past, they have been manually protected and managed. Unmanned aerial vehicles (UAVs), which are already being applied in various fields, such as agriculture, surveying, and logistics, can be applied to automate this task. Image processing and machine learning techniques applied on images obtained from UAVs can automate Convallaria keiskei classification, help to estimate the increase in colony numbers, and reduce the detection cost. In a previous study, a flower number estimation method that combines image processing and a convolutional neural network (CNN) was proposed. However, leaf regions similar to flower regions were misidentified as flower regions, and the accuracy was reduced. Therefore, in this study, a method was investigated to reduce the number of false positives by excluding areas similar to the flower regions. Specifically, a novel detection method combining image processing, CNN, and fuzzy c-means is proposed. To validate the proposed method, it was compared with the previous method as well as the method in which k-means was used instead of fuzzy c-means. All results were evaluated using flower distribution maps marked by field workers. The proposed method improved the F-measure by up to 22.0% compared with the previous method. Application of the proposed method to orthorectified images facilitates the understanding of flower populations over a wide range of areas, which can contribute to the conservation and management of the species.     

Automatic Detection of Diseased Tomato Plants Using Thermal and Stereo Visible Light Images

Accurate and timely detection of plant diseases can help mitigate the worldwide losses experienced by the horticulture and agriculture industries each year. Thermal imaging provides a fast and non-destructive way of scanning plants for diseased regions and has been used by various researchers to study the effect of disease on the thermal profile of a plant. However, thermal image of a plant affected by disease has been known to be affected by environmental conditions which include leaf angles and depth of the canopy areas accessible to the thermal imaging camera. In this paper, we combine thermal and visible light image data with depth information and develop a machine learning system to remotely detect plants infected with the tomato powdery mildew fungus Oidium neolycopersici. We extract a novel feature set from the image data using local and global statistics and show that by combining these with the depth information, we can considerably improve the accuracy of detection of the diseased plants. In addition, we show that our novel feature set is capable of identifying plants which were not originally inoculated with the fungus at the start of the experiment but which subsequently developed disease through natural transmission.     

Statistical guidance for experimental design and data analysis of mutation detection in rare monogenic mendelian diseases by exome sequencing

Recently, whole-genome sequencing, especially exome sequencing, has successfully led to the identification of causal mutations for rare monogenic Mendelian diseases. However, it is unclear whether this approach can be generalized and effectively applied to other Mendelian diseases with high locus heterogeneity. Moreover, the current exome sequencing approach has limitations such as false positive and false negative rates of mutation detection due to sequencing errors and other artifacts, but the impact of these limitations on experimental design has not been systematically analyzed. To address these questions, we present a statistical modeling framework to calculate the power, the probability of identifying truly disease-causing genes, under various inheritance models and experimental conditions, providing guidance for both proper experimental design and data analysis. Based on our model, we found that the exome sequencing approach is well-powered for mutation detection in recessive, but not dominant, Mendelian diseases with high locus heterogeneity. A disease gene responsible for as low as 5% of the disease population can be readily identified by sequencing just 200 unrelated patients. Based on these results, for identifying rare Mendelian disease genes, we propose that a viable approach is to combine, sequence, and analyze patients with the same disease together, leveraging the statistical framework presented in this work.     

Detection and classification of chilli leaf disease using a squeeze-and-excitation-based CNN model

Chilli leaf disease has a destructive effect on the chilli crop yield. Chilli leaf disease can result in a significant decrease in both the quantity and quality of the chilli crop. Early detection, perfect identification and accurately diagnosing the disease will aid in increasing the profit of the cultivator. However, after a comprehensive survey investigation, we discovered that no studies have been previously conducted to compare the classification performance of machine learning and deep learning for the chilli leaf disease classification problem. In this study, five main leaf diseases i.e. down curl of a leaf, Geminivirus, Cercospora leaf spot, yellow leaf disease, and up curl disease were identified, and images were captured using a digital camera and are labelled. These diseases were classified using 12 different pretrained deep learning networks (AlexNet, DarkNet53, DenseNet201, EfficientNetb0, InceptionV3, MobileNetV2, NasNetLarge, ResNet101, ShuffleNet, SqueezeNet, VGG19, and XceptionNet) using chilli leaf data with and without augmentation using deep learning transfer. Performance metrics such as accuracy, recall, precision, F1-score, specificity, and misclassification were calculated for each network. VGG19 had the best accuracy (83.54%) without augmentation, and DarkNet53 had the best result (98.82%) with augmentation among all pretrained deep learning networks in our self-built chilli leaf dataset. The result was enhanced by designing a squeeze-and-excitation-based convolutional neural network (SECNN) model. The model was tested on a chilli leaf dataset with different input sizes and mini-batch sizes. The proposed model produced the best accuracy of 98.63% and 99.12% without and with augmentation, respectively. The SECNN model was also tested on different datasets from the PlantVillage data, including apple, cherry, corn, grape, peach, pepper, potato, strawberry, and tomato leaves, separately and with the chilli dataset. The proposed model achieved an accuracy of 99.28% in classifying 43 different classes of plant leaf datasets.     

Convolutional neural network‐based malaria diagnosis from focus stack of blood smear images acquired using custom‐built slide scanner

The present paper introduces a focus stacking‐based approach for automated quantitative detection of Plasmodium falciparum malaria from blood smear. For the detection, a custom designed convolutional neural network (CNN) operating on focus stack of images is used. The cell counting problem is addressed as the segmentation problem and we propose a 2‐level segmentation strategy. Use of CNN operating on focus stack for the detection of malaria is first of its kind, and it not only improved the detection accuracy (both in terms of sensitivity [97.06%] and specificity [98.50%]) but also favored the processing on cell patches and avoided the need for hand‐engineered features. The slide images are acquired with a custom‐built portable slide scanner made from low‐cost, off‐the‐shelf components and is suitable for point‐of‐care diagnostics. The proposed approach of employing sophisticated algorithmic processing together with inexpensive instrumentation can potentially benefit clinicians to enable malaria diagnosis.