A Lightweight Deep Learning-Based Model for Tomato Leaf Disease Classification

Tomato leaf diseases significantly impact crop production,necessitating early detection for sustainable farming.Deep Learning(DL)has recently shown excellent results in identifying and classifying tomato leaf diseases.However,current DL methods often require substantial computational resources,hindering their application on resource-constrained devices.We propose the Deep Tomato Detection Network(DTomatoDNet),a lightweight DL-based framework comprising 19 learnable layers for efficient tomato leaf disease classification to overcome this.The Convn kernels used in the proposed(DTomatoDNet)framework is 1×1,which reduces the number of parameters and helps in more detailed and descriptive feature extraction for classification.The proposed DTomatoDNet model is trained from scratch to determine the classification success rate.10,000 tomato leaf images(1000 images per class)from the publicly accessible dataset,covering one healthy category and nine disease categories,are utilized in training the proposed DTomatoDNet approach.More specifically,we classified tomato leaf images into Target Spot(TS),Early Blight(EB),Late Blight(LB),Bacterial Spot(BS),Leaf Mold(LM),Tomato Yellow Leaf Curl Virus(YLCV),Septoria Leaf Spot(SLS),Spider Mites(SM),Tomato Mosaic Virus(MV),and Tomato Healthy(H).The proposed DTomatoDNet approach obtains a classification accuracy of 99.34%,demonstrating excellent accuracy in differentiating between tomato diseases.The model could be used on mobile platforms because it is lightweight and designed with fewer layers.Tomato farmers can utilize the proposed DTomatoDNet methodology to detect disease more quickly and easily once it has been integrated into mobile platforms by developing a mobile application.

Classification of metabolic-associated fatty liver disease subtypes based on TCM clinical phenotype

Objective:To classify the subtypes of metabolic-associated fatty liver disease(MAFLD)and provide new insights into the heterogeneity of MAFLD.Methods:Electronic medical records(EMR)of MAFLD diagnosed in accordance with the diagnostic criteria of Hubei Provincial Hospital of Traditional Chinese Medicine from 2016-2020 were included in the study.for physical annotation,and the data on each clinical phenotype was normalized according to corresponding aspirational standards.The MAFLD heterogeneous medical record network(HEMnet)was constructed using sex,age,disease diagnosis,symptoms,and Western medicine prescriptions as nodes and the co-occurrence times between phenotypes as edges.K-means clustering was used for disease classification.Relative risk(RR)was used to assess the specificity of each phenotype.Statistical methods were used to compare differences in laboratory indicators among subtypes.Results:A total of patients(12,626)with a mean age of 55.02(±14.21)years were included in the study.MAFLD can be divided into five subtypes:digestive diseases(C0),mental disorders and gynecological diseases(C1),chronic liver diseases and decompensated complications(C2),diabetes mellitus and its complications(C3),and immune joint system diseases(C4).Conclusions:Patients with MAFLD experience various symptoms and complications.The classification of MAFLD based on the HEMnet method is highly reliable.

Deep Transfer Learning Based Detection and Classification of Citrus Plant Diseases

Citrus fruit crops are among the world’s most important agricultural products,but pests and diseases impact their cultivation,resulting in yield and quality losses.Computer vision and machine learning have been widely used to detect and classify plant diseases over the last decade,allowing for early disease detection and improving agricultural production.This paper presented an automatic system for the early detection and classification of citrus plant diseases based on a deep learning(DL)model,which improved accuracy while decreasing computational complexity.The most recent transfer learning-based models were applied to the Citrus Plant Dataset to improve classification accuracy.Using transfer learning,this study successfully proposed a Convolutional Neural Network(CNN)-based pre-trained model(EfficientNetB3,ResNet50,MobiNetV2,and InceptionV3)for the identification and categorization of citrus plant diseases.To evaluate the architecture’s performance,this study discovered that transferring an EfficientNetb3 model resulted in the highest training,validating,and testing accuracies,which were 99.43%,99.48%,and 99.58%,respectively.In identifying and categorizing citrus plant diseases,the proposed CNN model outperforms other cuttingedge CNN model architectures developed previously in the literature.

Classification of Citrus Plant Diseases Using Deep Transfer Learning

In recent years,the field of deep learning has played an important role towards automatic detection and classification of diseases in vegetables and fruits.This in turn has helped in improving the quality and production of vegetables and fruits.Citrus fruits arewell known for their taste and nutritional values.They are one of the natural and well known sources of vitamin C and planted worldwide.There are several diseases which severely affect the quality and yield of citrus fruits.In this paper,a new deep learning based technique is proposed for citrus disease classification.Two different pre-trained deep learning models have been used in this work.To increase the size of the citrus dataset used in this paper,image augmentation techniques are used.Moreover,to improve the visual quality of images,hybrid contrast stretching has been adopted.In addition,transfer learning is used to retrain the pre-trainedmodels and the feature set is enriched by using feature fusion.The fused feature set is optimized using a meta-heuristic algorithm,the Whale Optimization Algorithm(WOA).The selected features are used for the classification of six different diseases of citrus plants.The proposed technique attains a classification accuracy of 95.7%with superior results when compared with recent techniques.

M^(2)LC-Net: A Multi-Modal Multi-Disease Long-Tailed Classification Network for Real Clinical Scenes

Leveraging deep learning-based techniques to classify diseases has attracted extensive research interest in recent years.Nevertheless,most of the current studies only consider single-modal medical images,and the number of ophthalmic diseases that can be classified is relatively small.Moreover,imbalanced data distribution of different ophthalmic diseases is not taken into consideration,which limits the application of deep learning techniques in realistic clinical scenes.In this paper,we propose a Multimodal Multi-disease Long-tailed Classification Network(M^(2)LC-Net)in response to the challenges mentioned above.M^(2)LC-Net leverages ResNet18-CBAM to extract features from fundus images and Optical Coherence Tomography(OCT)images,respectively,and conduct feature fusion to classify 11 common ophthalmic diseases.Moreover,Class Activation Mapping(CAM)is employed to visualize each mode to improve interpretability of M^(2)LC-Net.We conduct comprehensive experiments on realistic dataset collected from a Grade III Level A ophthalmology hospital in China,including 34,396 images of 11 disease labels.Experimental results demonstrate effectiveness of our proposed model M^(2)LC-Net.Compared with the stateof-the-art,various performance metrics have been improved significantly.Specifically,Cohen’s kappa coefficient κ has been improved by 3.21%,which is a remarkable improvement.

Foliar fungal disease classification in banana plants using elliptical local binary pattern on multiresolution dual tree complex wavelet transform domain

The fungal diseases in banana cause major yield losses for millions of farmers around the globe.Early detection of these diseases helps the farmers to devise successful management strategies.The characteristic leaf blade discoloration pattern at the earlier stages of infection could be used to understand the onset of each disease.This paper demonstrates a methodology for classification of three important foliar diseases in banana,using local texture features.The disease affected regions are identified using image enhancement and color segmentation.Segmented images are converted to transform domain using three image transforms(DWT,DTCWT and Ranklet transform).Feature vector is extracted from transform domain images using LBP and its variants(ELBP,MeanELBP and MedianELBP).These texture based features are applied to five popular image classifiers and comparative performance analysis is done using ten-fold cross validation procedure.Experimental results showed best classification performance for ELBP features extracted from DTCWT domain(accuracy 95.4%,precision 93.2%,sensitivity 93.0%,Fscore 93.0%and specificity 96.4%).Compared with traditional methods of feature extraction,this novel method of fusing DTCWT with ELBP features has attained high degree of accuracy in precisely detecting and classifying fungal diseases in banana at an early stage.

CE-EEN-B0:Contour Extraction Based Extended EfficientNet-B0 for Brain Tumor Classification Using MRI Images

A brain tumor is the uncharacteristic progression of tissues in the brain.These are very deadly,and if it is not diagnosed at an early stage,it might shorten the affected patient’s life span.Hence,their classification and detection play a critical role in treatment.Traditional Brain tumor detection is done by biopsy which is quite challenging.It is usually not preferred at an early stage of the disease.The detection involvesMagneticResonance Imaging(MRI),which is essential for evaluating the tumor.This paper aims to identify and detect brain tumors based on their location in the brain.In order to achieve this,the paper proposes a model that uses an extended deep Convolutional Neural Network(CNN)named Contour Extraction based Extended EfficientNet-B0(CE-EEN-B0)which is a feed-forward neural network with the efficient net layers;three convolutional layers and max-pooling layers;and finally,the global average pooling layer.The site of tumors in the brain is one feature that determines its effect on the functioning of an individual.Thus,this CNN architecture classifies brain tumors into four categories:No tumor,Pituitary tumor,Meningioma tumor,andGlioma tumor.This network provides an accuracy of 97.24%,a precision of 96.65%,and an F1 score of 96.86%which is better than already existing pre-trained networks and aims to help health professionals to cross-diagnose an MRI image.This model will undoubtedly reduce the complications in detection and aid radiologists without taking invasive steps.

Accuracy improvement for classifying retinal OCT images by diseases using deep learning-based selective denoising approach

In ophthalmology,retinal optical coherence tomography(OCT)images with noticeable structural features help identify human eyes as healthy or diseased.The recently hot arti ficial intelligence(AI)realized this recognition process automatically.However,speckle noise in the original retinal OCT image reduces the accuracy of disease classi fication.This study presents a timesaving approach based on deep learning to improve classi fication accuracy by removing the noise from the original dataset.Firstly,four pre-trained convolutional neural networks(CNNs)from the ImageNet Large Scale Visual Recognition Challenge(ILSVRC)were trained to classify the original images into two categories:The noise reduction required(NRR)and the noise-free(NF)images.Among the CNNs,VGG19 BN performed best with 98%accuracy and 99%recall.Then,we used the block-matching and 3D filtering(BM3D)algorithm to denoise the NRR images.Those noise-removed NRR and the NF images form the processed dataset.The quality of images in the dataset is prominently ameliorated after denoising,which is valid to improve the models'performance.The original and processed datasets were tested on the four pre-trained CNNs to evaluate the effectiveness of our proposed approach.We have compared the CNNs,and the results show the performance of the CNNs trained with the processed dataset is improved by an average of 2.04%,5.19%,and 5.10%under overall accuracy(OA),Macro F1-score,and Micro F1-score,respectively.Especially for DenseNet161,the OA is improved to 98.14%.Our proposed method demonstrates its effectiveness in improving classi fication accuracy and opens a new solution to reduce denoising time-consuming for large datasets.

Evaluation of the Sensitivity and Specificity of the New Clinical Diagnostic and Classification Criteria for Kashin-Beck Disease,an Endemic Osteoarthritis,in China

This study aimed to evaluate the sensitivity and specificity of the new clinical diagnostic and classification criteria for Kashin-Beck disease （KBD） using six clinical markers： flexion of the distal part of fingers, deformed fingers, enlarged finger joints, shortened fingers, squat down, and dwarfism. One-third of the total population in Linyou County was sampled by stratified random sampling.

SW-Net: A novel few-shot learning approach for disease subtype prediction

Few-shot learning is becoming more and more popular in many fields,especially in the computer vision field.This inspires us to introduce few-shot learning to the genomic field,which faces a typical few-shot problem because some tasks only have a limited number of samples with high-dimensions.The goal of this study was to investigate the few-shot disease sub-type prediction problem and identify patient subgroups through training on small data.Accurate disease subtype classification allows clinicians to efficiently deliver investigations and interventions in clinical practice.We propose the SW-Net,which simulates the clinical process of extracting the shared knowledge from a range of interrelated tasks and generalizes it to unseen data.Our model is built upon a simple baseline,and we modified it for genomic data.Supportbased initialization for the classifier and transductive fine-tuning techniques were applied in our model to improve prediction accuracy,and an Entropy regularization term on the query set was appended to reduce over-fitting.Moreover,to address the high dimension and high noise issue,we future extended a feature selection module to adaptively select important features and a sample weighting module to prioritize high-confidence samples.Experiments on simulated data and The Cancer Genome Atlas meta-dataset show that our new baseline model gets higher prediction accuracy compared to other competing algorithms.

An Efficient Disease Detection Technique of Rice Leaf Using AlexNet

As nearly half of the people in the world live on rice, so the rice leaf disease detection is very important for our agricultural sector. Many researchers worked on this problem and they achieved different results according to their applied techniques. In this paper, we applied AlexNet technique to detect the three prevalence rice leaf diseases termed as bacterial blight, brown spot as well as leaf smut and got a remarkable outcome rather than the previous works. AlexNet is a special type of classification technique of deep learning. This paper shows more than 99% accuracy due to adjusting an efficient technique and image augmentation.

Traditional Medicine Diagnostic Codes in ICD-11 and Alternative Diagnostic Classifications in the Mainstream Healthcare

In 2018,the 11^(th) Edition of the International Classification of Diseases(ICD-11)defined a diagnostic code list for standard traditional medicine(TM)conditions.The codes improve patient safety by providing more comprehensive and accurate medical records for hospitals in the Western Pacific Region.In these facilities,TM is often a standard of care for those populations.In several mainstream media sources,writers are circumventing evidence-based peer-reviewed medical literature by unduly influencing public opinion and,in this case,against the new ICD-11 codes.The dangers imposed by the transgression of popular writing onto the discipline of peer-reviewed works are present since best practices in medical record-keeping will fail without the inclusion of TM in the ICD-11 codes.Such failures directly affect the health of the patients and policymakers in regions where TM and conventional medicine are combined.This article investigates the boundaries between substantial evidence and popular opinion.In this era where media is used to manipulate evidence,the reader’s use of sound judgment and critical thought are thwarted.This article also challenges three controversial themes in pop literature,including the threat to endangered species,increased patient risk,and contaminants in the TM.These themes are made without evidence and are,in fact,of flawed logic.There is no reason to assume that improved medical record-keeping and knowledge of patient cases increase risks.

Operational definitions and measurement of externalizing behavior problems:An integrative review including research models and clinical diagnostic systems

Measurement of externalizing disorders such as antisocial disorders,attentiondeficit/hyperactivity disorder or borderline disorder have relevant implications for the daily lives of people with these disorders.While the Diagnostic and Statistical Manual of Mental Disorders(DSM)and the International Classification of Diseases(ICD)have provided the diagnostic framework for decades,recent dimensional frameworks question the categorical approach of psychopathology,inherent in traditional nosotaxies.Tests and instruments develop under the DSM or ICD framework preferentially adopt this categorical approach,providing diagnostic labels.In contrast,dimensional measurement instruments provide an individualized profile for the domains that comprise the externalizing spectrum,but are less widely used in practice.Current paper aims to review the operational definitions of externalizing disorders defined under these different frameworks,revise the different measurement alternatives existing,and provide an integrative operational definition.First,an analysis of the operational definition of externalizing disorders among the DSM/ICD diagnostic systems and the recent Hierarchical Taxonomy of Psychopathology(HiTOP)model is carried out.Then,in order to analyze the coverage of operational definitions found,a description of measurement instruments among each conceptualization is provided.Three phases in the development of the ICD and DSM diagnosis systems can be observed with direct implications for measurement.ICD and DSM versions have progressively introduced systematicity,providing more detailed descriptions of diagnostic criteria and categories that ease the measurement instrument development.However,it is questioned whether the DSM/ICD systems adequately modelize externalizing disorders,and therefore their measurement.More recent theoretical approaches,such as the HiTOP model seek to overcome some of the criticism raised towards the classification systems.Nevertheless,several issues concerning this model raise mesasurement challenges.A revision of the instruments underneath each approach shows incomplete coverage of externalizing disorders among the existing instruments.Efforts to bring nosotaxies together with other theoretical models of psychopathology and personality are still needed.The integrative operational definition of externalizing disorders provided may help to gather clinical practice and research.

Is Takotsubo cardiomyopathy still looking for its own nosological identity?

Despite several efforts to provide a proper nosological framework for Takotsubo cardiomyopathy(TCM),this remains an unresolved matter in clinical practice.Several clinical,pathophysiologic and histologic findings support the conceivable hypothesis that TCM could be defined as a unique pathologic entity,rather than a distinct subset of myocardial infarction with non-obstructive coronary arteries.Further investigations are needed in order to define TCM with the most appropriate disease taxonomy.

A survey of automated International Classification of Diseases coding:development,challenges,and applications

The International Classification of Diseases(ICD)is an international standard and tool for epidemiological in-vestigation,health management,and clinical diagnosis with a fundamental role in intelligent medical care.The assignment of ICD codes to health-related documents has become a focus of academic research,and numerous studies have developed the process of ICD coding from manual to automated work.In this survey,we review the developmental history of this task in recent decades in depth,from the rules-based stage,through the traditional machine learning stage,to the neural-network-based stage.Various methods have been introduced to solve this problem by using different techniques,and we report a performance comparison of different methods on the pub-licly available Medical Information Mart for Intensive Care dataset.Next,we summarize four major challenges of this task:(1)the large label space,(2)the unbalanced label distribution,(3)the long text of documents,and(4)the interpretability of coding.Various solutions that have been proposed to solve these problems are analyzed.Further,we discuss the applications of ICD coding,from mortality statistics to payments based on disease-related groups and hospital performance management.In addition,we discuss different ways of considering and evaluat-ing this task,and how it has been transformed into a learnable problem.We also provide details of the commonly used datasets.Overall,this survey aims to provide a reference and possible prospective directions for follow-up research work.

Pattern Classification of Enterovirus 71-Associated Hand, Foot, and Mouth Disease in Chinese Medicine: A Retrospective Study in 433 Cases

Objective： To determine whether patterns of enterovirus 71（EV71）-associated hand, foot, and mouth disease（HFMD） were classified based on symptoms and signs, and explore whether individual characteristics were correlated with membership in particular pattern. Methods： Symptom-based latent class analysis（LCA） was used to determine whether patterns of EV71-HFMD existed in a sample of 433 cases from a clinical data warehouse system. Logistic regression was then performed to explore whether demographic, and laboratory data were associated with pattern membership. Results： LCA demonstrated a two-subgroup solution with an optimal fit, deduced according to the Bayesian Information Criterion minima. Hot pattern（59.1% of all patients） was characterized by a very high fever and high endorsement rates for classical HFMD symptoms（i.e., rash on the extremities, blisters, and oral mucosa lesions）. Non-hot pattern（40.9% of all patients） was characterized by classical HFMD symptoms. The multiple logistic regression results suggest that white blood cell counts and aspartate transaminase were positively correlated with the hot pattern（adjust odds ratio=1.07, 95% confidence interval： 1.006–1.115; adjust odds ratio=1.051, 95% confidence interval： 1.019–1.084; respectively）. Conclusions： LCA on reported symptoms and signs in a retrospective study allowed different subgroups with meaningful clinical correlates to be defined. These findings provide evidence for targeted prevention and treatment interventions.

Representation of Specific Diagnosis for Low Back Pain Using the 11^(th) Revision of International Classification of Diseases and Related Health Problems: Perspectives of Conventional Medicine and Traditional Medicine

Background:The 11th revision of the International Classification of Diseases and Related Health Problems(ICD-11)was released on June 18,2018,by the World Health Organization and will come into effect on January 1,2022.Apart from the chapters on the classification of diseases in the conventional medicine(CM),a new chapter,traditional medicine(TM)conditions–Module 1,was added.Low back pain(LBP)is one of the common reasons for the physician visits.The classification codes for LBP in the ICD-11 are vital to documenting accurate clinical diagnoses.Methods:The qualitative case study method was adopted.The secondary use data for 100 patients were randomly selected using the ICD-11 online interface to find the classification codes for both the CM section and the TM Conditions–Module 1(TM1)section for LBP diagnosis.Results:Of the 27 codes obtained from the CM section,six codes were not relevant to LBP,whereas the other 21 codes represented diagnoses of LBP and its related diseases or syndromes.In the TM1 section,six codes for different patterns and disorders represented the diagnoses for LBP from the TM perspective.Conclusion:This study indicates that specific diagnoses of LBP can be represented by the combination of CM classification codes and TM1 classification codes in the ICD-11;the CM codes represent specific and accurate clinical diagnoses for LBP,whereas the TM1 codes add more accuracy to the diagnoses of different patterns from the TM perspective.

A review of imaging techniques for plant disease detection

Agriculture is the basis of every economy worldwide.Crop production is one of the major factors affecting domestic market condition in any country.Agricultural production is also a major prerequisite of economic development,be it any part of any country.It plays a crucial role as it even provides raw material,employment and food to different citizens.A lot of issues are responsible for estimated crop production varying in different parts of the world.Some of these include overutilization of chemical fertilizers,presence of chemicals in water supply,uneven distribution of rainfall,different soil fertility and others.Other than these issues one of the commonly faced challenges across the globe equally includes destruction of themajor part of production due to diseases.After providing effective resources to the fields,major section of the production is diminished by the presence of diseases in the plants grown.This leads to focus on effective ways of detection of disease in plants.Presence of various diseases in plant is a major concern among farmers.Plant diseases acts as a major threat to small scale farmers as they lead tomajor destruction in overall food supply.To provide effectivemeasures for detection and avoidance of the destruction requires an early identification of type of plant disease present.In recent timemajorwork is being done for the identification of plant disease presents in varied parts of theworld affection varied crops.Majorwork is being done in the domain of identification of causing factors of these diseases.Someof the diseases are marked by the presence of viruses while some are resultant of fungal infection.This becomes a major issuewhen the causing factor is not traceable before it has already spread to major production section.This paper brings a review on effective use of different imaging techniques and computer vision approaches for the identification and classification of plant diseases.Detection of Plant disease is initiated with image acquisition followed by pre-processingwhile using the process of segmentation.It is further accompanied by different techniques used for feature extraction alongwith classification.In this Paper we present the Current Trends and Challenges for detection of plant disease using computer vision and advance imaging technique.

Few-shot learning for biotic stress classification of coffee leaves

In the last few years,deep neural networks have achieved promising results in several fields.However,one of the main limitations of these methods is the need for large-scale datasets to properly generalize.Few-shot learning methods emerged as an attempt to solve this shortcoming.Among the few-shot learning methods,there is a class of methods known as embedding learning or metric learning.These methods tackle the classification problem by learning to compare,needing fewer training data.One of the main problems in plant diseases and pests recognition is the lack of large public datasets available.Due to this difficulty,the field emerges as an intriguing application to evaluate the few-shot learning methods.The field is also relevant due to the social and economic importance of agriculture in several countries.In this work,datasets consisting of biotic stresses in coffee leaves are used as a case study to evaluate the performance of few-shot learning in classification and severity estimation tasks.We achieved competitive results compared with the ones reported in the literature in the classification task,with accuracy values close to 96%.Furthermore,we achieved superior results in the severity estimation task,obtaining 6.74%greater accuracy than the baseline.

Therapeutic strategy for traumatic instability of subaxial cervical spine

Background A simple, safe and effective therapeutic strategy for traumatic instability of the subaxial cervical spine, as well as its prognostic assessment, is still controversial. Methods The therapeutic options for 83 patients of traumatic instability of the subaxial cervical spine, whose average age was 35 years, were determined, according to the Allen-Ferguson classification, general health and concomitant traumatic conditions, neurological function, position of compression materials, concomitant traumatic disc herniation/damage, concomitant locked-facet dislocation, the involved numbers and position, and the patients＇ economic conditions. An anterior, posterior or combination approach was used to decompress and reconstruct the cervical spine. No operations with an anterior-posterior-anterior approach were performed. Results The average follow-up was three years and nine months. Distraction-flexion and compression-flexion were the most frequent injury subtypes. There were 46, 28 and 9 cases of anterior, posterior and combination operations, respectively. The average score of the Japanese Orthopaedics Association, visual analog scale and American Spinal Cord Injury Association （ASIA） motor index improved from 11.2, 7.8 and 53.5, respectively, before operation, to 15.3, 2.6 and 67.8, respectively, at final follow-up. For incomplete spinal cord injury （SCI）, the average ASIA neurological function scale was improved by 1-2 levels. Patients with complete SCI had no neurological recovery, but recovery of nerve root function occurred to different extents. After surgery, radiological parameters improved to different extents. Fusion was achieved in all patients and 12 developed complications. Conclusions The best surgical strategy should be determined by the type of subaxial cervical injury, patients＇ general health, local pathological anatomy and neurological function.