Computer-aided Diagnosis Research Articles

Research on Automatic Detection of Citrus Pests and Diseases Using Deep Neural Network Model

Citrus fruit diseases are a major cause of citrus yield decline. Deep learning methods have achieved promising results in many artificial intelligence problems, which motivates us to apply them to the challenge of recognizing citrus pests and diseases. In this paper, two progressive convolutional neural network (CNN) models are proposed. The proposed CNN models are designed to distinguish between healthy fruits and common citrus pest fruits. The first model is a four-branch parallel CNN based on a feature fusion (ODC-FFN) structure for the automatic detection of citrus diseases. The model takes the size, color, shape, and texture images of citrus surface diseases as inputs and uses a fusion feature extractor to design the four-branch network structure. Through comparison experiments with other models, its recognition accuracy reaches 94.68%. The second model is based on the first model, the multiple attention-based citrus disease classification model (ODC-MAN) is constructed by embedding spatial attention and channel attention mechanisms as feature extractors, and the convolutional layer fusion is changed to classification layer fusion, and the integrated network model is further constructed through integrated learning. The recognition accuracy is further improved to 98.21% by comparison experiments, which indicates that the integrated model using classification layer fusion is effective.

Improved Alzheimer Disease Diagnosis With a Machine Learning Approach and Neuroimaging: Case Study Development.

Alzheimer disease (AD) is a severe neurological brain disorder. While not curable, earlier detection can help improve symptoms substantially. Machine learning (ML) models are popular and well suited for medical image processing tasks such as computer-aided diagnosis. These techniques can improve the process for an accurate diagnosis of AD. In this paper, a complete computer-aided diagnosis system for the diagnosis of AD has been presented. We investigate the performance of some of the most used ML techniques for AD detection and classification using neuroimages from the Open Access Series of Imaging Studies (OASIS) and Alzheimer's Disease Neuroimaging Initiative (ADNI) datasets. The system uses artificial neural networks (ANNs) and support vector machines (SVMs) as classifiers, and dimensionality reduction techniques as feature extractors. To retrieve features from the neuroimages, we used principal component analysis (PCA), linear discriminant analysis, and t-distributed stochastic neighbor embedding. These features are fed into feedforward neural networks (FFNNs) and SVM-based ML classifiers. Furthermore, we applied the vision transformer (ViT)-based ANNs in conjunction with data augmentation to distinguish patients with AD from healthy controls. Experiments were performed on magnetic resonance imaging and positron emission tomography scans. The OASIS dataset included a total of 300 patients, while the ADNI dataset included 231 patients. For OASIS, 90 (30%) patients were healthy and 210 (70%) were severely impaired by AD. Likewise for the ADNI database, a total of 149 (64.5%) patients with AD were detected and 82 (35.5%) patients were used as healthy controls. An important difference was established between healthy patients and patients with AD (P=.02). We examined the effectiveness of the three feature extractors and classifiers using 5-fold cross-validation and confusion matrix-based standard classification metrics, namely, accuracy, sensitivity, specificity, precision, F1-score, and area under the receiver operating characteristic curve (AUROC). Compared with the state-of-the-art performing methods, the success rate was satisfactory for all the created ML models, but SVM and FFNN performed best with the PCA extractor, while the ViT classifier performed best with more data. The data augmentation/ViT approach worked better overall, achieving accuracies of 93.2% (sensitivity=87.2, specificity=90.5, precision=87.6, F1-score=88.7, and AUROC=92) for OASIS and 90.4% (sensitivity=85.4, specificity=88.6, precision=86.9, F1-score=88, and AUROC=90) for ADNI. Effective ML models using neuroimaging data could help physicians working on AD diagnosis and will assist them in prescribing timely treatment to patients with AD. Good results were obtained on the OASIS and ADNI datasets with all the proposed classifiers, namely, SVM, FFNN, and ViTs. However, the results show that the ViT model is much better at predicting AD than the other models when a sufficient amount of data are available to perform the training. This highlights that the data augmentation process could impact the overall performance of the ViT model.

Abstract 2438: Bridging whole slide images and large language model for slide-level question answering

Abstract Background: Vision Language Models (VLMs), integrating large language models (LLMs) with vision encoders to enable better understanding and interaction with visual data, have broken entirely new ground in computational pathology. Recent studies have demonstrated that employing a simple linear layer as an 'adaptor' to transform image embeddings, extracted by pathology-specific vision encoders, into LLM-recognizable tokens is effective for developing patch-level VLMs in pathology. However, the gigapixel-scale size of whole-slide images (WSIs) and their pyramidal structure pose significant challenges in designing effective adaptors for slide-level analysis. In particular, different diagnostic questions and tasks at the slide level require focusing on various sub-regions at different magnifications or combining multiple regions and magnifications. Here, we aim to assess adaptors that meet these challenging demands and develop a slide-level VLM to enable slide-level question answering. Methods: We develop Llama-Path, the first general-purpose slide-level VLM, using WSIs paired with descriptions and question-answer (Q&A) pairs. First, we collect 35,943 WSIs from public databases such as TCGA and GTEx, along with corresponding pathological reports or notes, covering a wide range of tumor and tissue types. Based on these reports and notes, we curate a WSI description dataset and a WSI Q&A dataset (337,000 Q&A pairs) using GPT-4. Then, we extract hierarchical patch embeddings from each WSI by the pathology foundation model, Conch. Next, we propose and evaluate six distinct slide-level adaptors: four vision-only, and two vision-text interactive. These adaptors are finetuned with Llama-3.1-8B across two stages to develop various versions of Llama-Path: The first stage uses the WSI description dataset to provide Llama-Path with a slide-level vision understanding ability. The second stage enhances the slide-level instruction-following capability of Llama-Path with the WSI Q&A dataset. Finally, we evaluate different versions of Llama-Path on a hold-out dataset consisting of 367 tumor and non-tumor cases with 4,440 Q&A pairs. Results: All versions of Llama-Path demonstrated exceptional performance, each achieving over 90% accuracy in close-ended Q&A pairs. GPT-4 assessed open-ended performances with high accuracy, showing 36% of responses correct, 27% partially correct, and 3% incorrect. The remaining 34% could not be evaluated without access to the corresponding WSIs. The LongNet-based vision-text interactive adaptor outperformed others, likely due to its targeted capture of visual information and simultaneous optimisation of WSI embeddings. Conclusions: Our findings highlight the potential of VLMs to enhance slide-level computer-aided diagnosis systems. Results from ongoing analyses, based on pathologists’ evaluations, will be presented shortly. Citation Format: Zeyu Gao, Kai He, Weiheng Su, William McGough, Ines Prata Machado, Mercedes Jimenez-Linan, Brian Rous, Rebecca Wray, Chengzu Li, Xiaobo Pang, Tieliang Gong, Mengling Feng, Chen Li, Mireia Crispin-Ortuzar. Bridging whole slide images and large language model for slide-level question answering [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 2438.

TCMSF: A construction framework of traditional Chinese medicine syndrome ancient book knowledge graph.

Syndrome is a unique and crucial concept in traditional Chinese medicine (TCM). However, much of the syndrome knowledge lacks systematic organization and correlation, and current information technologies are unsuitable for TCM ancient texts. We aimed to develop a knowledge graph that presents this knowledge in a more orderly, structured, and semantically oriented manner, providing a foundation for computer-aided diagnosis and treatment. We developed a construction framework of TCM syndrome knowledge from ancient books, using a pre-trained model and rules (TCMSF). We conducted fine-tuning training on Enhanced Representation through Knowledge Integration (ERINE), Bidirectional Encoder Representation from Transformers (BERT) pre-trained language models, and chatGLM3-6b large language models (LLMs) for named entity recognition (NER) tasks. Furthermore, we employed the progressive entity relationship extraction method based on the dual pattern feature combination to extract and standardize entities and relationships between entities in these books. We selected Yin deficiency syndrome as a case study and constructed a model layer suitable for the expression of knowledge in these books. Compared to multiple NER methods, the combination of ERNIE and Conditional Random Fields (CRF) performs the best. By utilizing this combination, we completed the entity extraction of Yin deficiency syndrome, achieving an average F1 value of 0.77. The relationship extraction method we proposed reduces the number of incorrectly connected relationships compared to fully connected pattern layers. We successfully constructed a knowledge graph of ancient books on Yin deficiency syndrome, including over 120,000 entities and over 1.18 million relationships. We developed TCMSF in line with the knowledge characteristics of ancient TCM books and improved the accuracy of knowledge graph construction.

Approach for enhancing the accuracy of semantic segmentation of chest X-ray images by edge detection and deep learning integration

IntroductionAccurate segmentation of anatomical structures in chest X-ray images remains challenging, especially for regions with low contrast and overlapping structures. This limitation significantly affects the diagnosis of cardiothoracic diseases. Existing deep learning methods often struggle with preserving structural boundaries, leading to segmentation artifacts.MethodsTo address these challenges, I propose a novel segmentation approach that integrates contour detection techniques with the U-net deep learning architecture. Specifically, the method employs Sobel and Scharr edge detection filters to enhance structural boundaries in chest X-ray images before segmentation. The pipeline involves pre-processing using contour detection, followed by segmentation with a U-net model trained to identify lungs, heart, and clavicles.ResultsExperimental evaluation demonstrated that using edge-enhancing filters, particularly the Sobel operator, leads to a marked improvement in segmentation accuracy. For lung segmentation, the model achieved an accuracy of 99.26%, a Dice coefficient of 98.88%, and a Jaccard index of 97.54%. Heart segmentation results included 99.47% accuracy and 94.14% Jaccard index, while clavicle segmentation reached 99.79% accuracy and 89.57% Jaccard index. These results consistently outperform the baseline U-net model without edge enhancement.DiscussionThe integration of contour detection methods with the U-net model significantly improves the segmentation quality of complex anatomical regions in chest X-rays. Among the tested filters, the Sobel operator proved to be the most effective in enhancing boundary information and reducing segmentation artifacts. This approach offers a promising direction for more accurate and robust computer-aided diagnosis systems in radiology.

Multimodality imaging in prostate cancer diagnosis using artificial intelligence: basic concepts and current state-of-the-art

Abstract The early diagnosis of prostate cancer (PCa) is highly recommended, as the tumor will not spread to other organs of the body and the bones. Moreover, a late diagnosis of PCa could lower the survival rate. The growing development of Artificial Intelligence (AI) and Machine Learning (ML) in medical images has led to significant improvement in PCa diagnosis. Multimodality is now commonly applied in medical imaging diagnosis, as it provides comprehensive information about a target (tissue or tumor). It has shown to be useful for advancing the clinical reliability of using medical images and ML for medical diagnostics and analysis. Hence, in this paper, a comprehensive survey is provided to explore the state-of-the-art Computer-Aided Diagnosis Systems (CADs) for PCa detection attributed to multimodality imaging, a background of PCa. different types of medical imaging used in PCa diagnosis, related clinical workflows, future perspectives, and some common limitations of related work. The review exhibits an extensive literature review done on multimodality imaging in PCa, highlights that multimodality imaging has the potential of wide applicability in diagnosis systems. It is expected that this study enhances the understanding necessary for developing CAD systems for PCa diagnosis. Additionally, it is expected to establish a great basis for developing multimodal images, the relevant datasets, some of the challenges, and future topics. Graphical Abstract

A CT-based deep learning-driven tool for automatic liver tumor detection and delineation in patients with cancer.

A CT-based deep learning-driven tool for automatic liver tumor detection and delineation in patients with cancer.

Wrist and elbow fracture detection and segmentation by artificial intelligence using point-of-care ultrasound.

Distal radius (wrist) and supracondylar (elbow) fractures are common in children presenting to Pediatric Emergency Departments (EDs). These fractures are treated conservatively or surgically depending on deformity severity. Radiographs are typically used for diagnosis but can increase wait times due to the need for radiation-safe rooms. Ultrasound (US) offers a radiation-free, faster alternative that can be performed at triage, but its noisy images are challenging to interpret. We developed an artificial intelligence (AI) technique for the automatic diagnosis of fractures at the wrist and elbow. While most AI for diagnosis focuses on classification results only, we applied a more explainable pipeline that used US bony region segmentation from a CNN as the basis of fracture detection. Our approach was validated on 3,822 wrist US images and 1487 elbow US images. We compared the fracture detection results from classification models and multi-channel segmentation models. Combining the segmentation results with the original images showed superior performance in fracture detection at the individual patient level, achieving an accuracy of 0.889 and 0.750, sensitivity of 0.818 and 1.000, and specificity of 1.000 and 0.714 on the wrist and elbow dataset respectively. Besides, the multi-channel U-Net architecture effectively detected bony fracture regions in wrist US images. These findings demonstrate that AI models can enable reliable, automatic wrist and elbow fracture detection in pediatric EDs, potentially reducing wait times and optimizing medical resource use.

DCATNet: polyp segmentation with deformable convolution and contextual-aware attention network

Polyp segmentation is crucial in computer-aided diagnosis but remains challenging due to the complexity of medical images and anatomical variations. Current state-of-the-art methods struggle with accurate polyp segmentation due to the variability in size, shape, and texture. These factors make boundary detection challenging, often resulting in incomplete or inaccurate segmentation. To address these challenges, we propose DCATNet, a novel deep learning architecture specifically designed for polyp segmentation. DCATNet is a U-shaped network that combines ResNetV2-50 as an encoder for capturing local features and a Transformer for modeling long-range dependencies. It integrates three key components: the Geometry Attention Module (GAM), the Contextual Attention Gate (CAG), and the Multi-scale Feature Extraction (MSFE) block. We evaluated DCATNet on five public datasets. On Kvasir-SEG and CVC-ClinicDB, the model achieved mean dice scores of 0.9351 and 0.9444, respectively, outperforming previous state-of-the-art (SOTA) methods. Cross-validation further demonstrated its superior generalization capability. Ablation studies confirmed the effectiveness of each component in DCATNet. Integrating GAM, CAG, and MSFE effectively improves feature representation and fusion, leading to precise and reliable segmentation results. These findings underscore DCATNet’s potential for clinical application and can be used for a wide range of medical image segmentation tasks.

Gemini Molecular Assembly Colocalization (GOAL): Accurate and Efficient Fusion Genotyping for Chronic Myeloid Leukemia Intelligent Diagnosis.

RNA small fragment aberrances are associated with diseases by mediating a range of pathogenesis and pathological processes. DNA assembly-based barcoding and amplification technologies are currently being actively explored for RNA in situ analysis. However, these modular integrated DNA assembly processes are inevitably accompanied with false positive signals caused by unexpected misassembly. Completely avoiding this phenomenon through simple and universal methods is challenging. Here, a novel dual-input to dual-output in situ analysis paradigm is proposed, aiming to improve target specificity through co-recognition (dual-input) and to eliminate false positive misassembly through fluorescent signal co-localization (dual-output). Based on this paradigm, Gemini molecular assembly co-localization (GOAL) in situ imaging system is launched to accurately distinguish the fusion gene subtypes associated with chronic myeloid leukemia (CML), and to precisely report the proportion of minimum residual cancer cells in clinical samples by intelligent co-localization counting and sorting. GOAL achieves highly sensitive and accurate genotyping recognition of 0.01% CML tumor cells and realizes fully automatic rapid diagnosis with a customized Intelligent Cell Image Sorter(iCis). iCis-assisted GOAL represents an innovative and versatile molecular toolkit for accurate, rapid, user-friendly, and professional-independent profiling of cancer cells with RNA small fragment aberrances, providing efficient clinical decision support for disease diagnosis.

Telemedicine in ophthalmology.

Since its beginnings in the 1970s, telemedicine has advanced extensively. Telemedicine is now more accessible and powerful than ever thanks to developments in medical imaging, Internet accessibility, advancements in telecommunications infrastructure, exponential growth in computing power, and related computer-aided diagnoses. This is especially true in the field of ophthalmology. With the COVID19 pandemic serving as acatalyst for the widespread adoption and acceptance of teleophthalmology, new models of healthcare provision integrating telemedicine are needed to meet the challenges of the modern world. The demand for ophthalmic services is growing globally due to population growth, aging, and ashortage of ophthalmologists. In this review, we discuss the development and use of telemedicine in the field of ophthalmology and shed light on the benefits and drawbacks of teleophthalmology.

Computer-aided diagnosis of Haematologic disorders detection based on spatial feature learning networks using blood cell images

Analyzing biomedical images is vital in permitting the highest-performing imaging and numerous medical applications. Determining the analysis of the disease is an essential stage in handling the patients. Similarly, the statistical value of blood tests, the personal data of patients, and an expert estimation are necessary to diagnose a disease. With the growth of technology, patient-related information is attained rapidly and in big sizes. Currently, numerous physical methods exist to evaluate and forecast blood cancer utilizing the microscopic health information of white blood cell (WBC) images that are stable for prediction and cause many deaths. Machine learning (ML) and deep learning (DL) have aided the classification and collection of patterns in data, foremost in the growth of AI methods employed in numerous haematology fields. This study presents a novel Computer-Aided Diagnosis of Haematologic Disorders Detection Based on Spatial Feature Learning Networks with Hybrid Model (CADHDD-SFLNHM) approach using Blood Cell Images. The main aim of the CADHDD-SFLNHM approach is to enhance the detection and classification of haematologic disorders. At first, the Sobel filter (SF) technique is utilized for preprocessing to improve the quality of blood cell images. Additionally, the modified LeNet-5 model is used in the feature extractor process to capture the essential characteristics of blood cells relevant to disorder classification. The convolutional neural network and bi-directional gated recurrent unit with attention (CNN-BiGRU-A) method is employed to classify and detect haematologic disorders. Finally, the CADHDD-SFLNHM model implements the pelican optimization algorithm (POA) method to fine-tune the hyperparameters involved in the CNN-BiGRU-A method. The experimental result analysis of the CADHDD-SFLNHM model was accomplished using a benchmark database. The performance validation of the CADHDD-SFLNHM model portrayed a superior accuracy value of 97.91% over other techniques.

Multiscale transformers and multi-attention mechanism networks for pathological nuclei segmentation

Pathology nuclei segmentation is crucial of computer-aided diagnosis in pathology. However, due to the high density, complex backgrounds, and blurred cell boundaries, it makes pathology cell segmentation still a challenging problem. In this paper, we propose a network model for pathology image segmentation based on a multi-scale Transformer multi-attention mechanism. To solve the problem that the high density of cell nuclei and the complexity of the background make it difficult to extract features, a dense attention module is embedded in the encoder, which improves the learning of the target cell information to minimize target information loss; Additionally, to solve the problem of poor segmentation accuracy due to the blurred cell boundaries, the Multi-scale Transformer Attention module is embedded between encoder and decoder, improving the transfer of the boundary feature information and makes the segmented cell boundaries more accurate. Experimental results on MoNuSeg, GlaS and CoNSeP datasets demonstrate the network’s superior accuracy.

BLS-GAN: A Deep Layer Separation Framework for Eliminating Bone Overlap in Conventional Radiographs

Conventional radiography is the widely used imaging technology in diagnosing, monitoring, and prognosticating musculoskeletal (MSK) diseases because of its easy availability, versatility, and cost-effectiveness. Bone overlaps are prevalent in conventional radiographs, and can impede the accurate assessment of bone characteristics by radiologists or algorithms, posing significant challenges to conventional clinical diagnosis and computer-aided diagnosis. This work initiated the study of a challenging scenario - bone layer separation in conventional radiographs, in which separate overlapped bone regions enable the independent assessment of the bone characteristics of each bone layer and lay the groundwork for MSK disease diagnosis and its automation. This work proposed a Bone Layer Separation GAN (BLS-GAN) framework that can produce high-quality bone layer images with reasonable bone characteristics and texture. This framework introduced a reconstructor based on conventional radiography imaging principles, which achieved efficient reconstruction and mitigates the recurrent calculations and training instability issues caused by soft tissue in the overlapped regions. Additionally, pre-training with synthetic images was implemented to enhance the stability of both the training process and the results. The generated images passed the visual Turing test, and improved performance in downstream tasks. This work affirms the feasibility of extracting bone layer images from conventional radiographs, which holds promise for leveraging layer separation technology to facilitate more comprehensive analytical research in MSK diagnosis, monitoring, and prognosis.

Development of Neural Networks for Deep Learning Provides Optimized Prostate Cancer Diagnosis along with Precise and Early Detection Capabilities

Introduction: Prostate cancer continues to be the leading cause of male fatalities requiring advanced and early diagnosis methods. The complexityresenter immune response after COVID-19 vaccination in senior patients. Neural networks stand as promising deep learning models for dealing with current healthcare diagnostic problems. The research investigates an improved neural network structure which unites convolutional neural networks (CNNs) for image analysis and recurrent neural networks (RNNs) for sequential clinical data interpretation. The proposed model utilizes multimodal data fusion which results in better accuracy of prostate cancer diagnosis. Objective: The research seeks to establish an optimized deep learning diagnostic system for prostate cancer through the integration of CNNs for image analysis and RNNs for clinical data interpretation sequences. Computer-aided prostate cancer diagnosis requires better accuracy and reliability through the integration of multiple data types. The research addresses diagnostic explainability through explainable AI (XAI) methods to enable healthcare professionals to understand AI model decisions with clarity. The rates of false positives and false negatives need minimization to increase the detection effectiveness of prostate cancer. The research evaluates the proposed model's performance by comparing it to standard diagnostic methods consisting of Bayesian networks and Naïve Bayes classifiers to prove its better handling of medical data heterogeneity. Method: Training of the proposed neural network occurs through data made up of diverse information including MRI scans and histopathological images and clinicopathological data. The data preprocessing stage contains normalization together with augmentation methods in addition to feature extraction components to maximize learning effectiveness. Hospital executives utilize high-resolution medical image-processing with CNNs to extract necessary tumor characteristics from images. Sequential clinical information is managed by RNNs while they extract temporal patterns which bear diagnostic significance. Standard evaluation metrics like accuracy and the set of sensitivity, specificity and F1-score are used for training and validating the combined model. Results: The experimental examination reveals that the proposed neural method achieves superior diagnostic performance when compared to established diagnostic techniques regarding accuracy levels and both sensitivity and specificity indices. The CNN segment successfully extracts tumor-related information from MRI scans and digital pathology pictures and the RNN part advances the diagnostic precision through sequence-based clinical data inspection. The integrated diagnostic system effectively decreases wrong test results which leads to better diagnostic accuracy. Conclusion: The presented research demonstrates deep learning's capability to advance prostate cancer diagnostic procedures. Combining CNNs with RNNs allows the proposed diagnostic system to perform better than traditional approaches. Programmable artificial intelligence technologies deliver transparent models thus making them easier for clinicians to use. The study confirms AI diagnostic solutions offer prompt proper diagnosis which brings about improved clinical results.

Leveraging ensemble convolutional neural networks and metaheuristic strategies for advanced kidney disease screening and classification

To address the public health issue of renal failure and the global shortage of nephrologists, an AI-based system has been developed to automatically identify kidney diseases. Recent advancements in machine learning, deep learning (DL), and artificial intelligence (AI) have unlocked new possibilities in healthcare. By harnessing these technologies, we can analyze data to gain insights into symptoms and patterns, ultimately facilitating remote patient care. To create an AI-based diagnosis system for kidney disease, this paper focused on the three major categories of kidney diseases: stones, cysts, and tumors, which were collected and annotated on 12,446 computed tomography (CT) whole abdomen and urogram images. To effectively aid in the automatic identification and diagnosis of kidney diseases, a novel DL model built on the transfer-learning (TL) technology is implemented in this work. DL models are designed to focus on problems, whereas TL uses the knowledge acquired while resolving one issue to another pertinent issue. The proposed model combines multiple DL models to improve overall performance by leveraging the strengths of different architectures, ensembles can enhance accuracy, robustness, and generalization. It enhances the features extracted from MobileNet-V2, ResNet50, and EfficientNet-B0 networks using metaheuristic algorithms and bidirectional long-short-term memory (Bi-LSTM) from the CT image. MobileNetV2, ResNet50, and EfficientNet-B0 hyperparameters have been optimized using a modified grey wolf optimization (GWO) approach for better performance. The suggested model’s performance has been measured using five assessment metrics: accuracy, sensitivity, specificity, precision, and area under the ROC curve (AUC) and achieved 99.85% accuracy, 99.8% sensitivity, 99.3% specificity, 98.1% precision, and 1.0 AUC.

Research on ECG Classification Algorithm Based on Wavelet Transform Noise Reduction and Random Forest

Electrocardiogram (ECG) signal classification is a critical task in arrhythmia diagnosis, and its accuracy directly affects the effectiveness of clinical decision-making. However, ECG signals usually contain noise and have uneven category distribution, which poses a great challenge to the classification task. To this end, this study proposes a classification method for ECG signals based on wavelet noise reduction and random forests. Specifically, we first remove the noise from the signals using the wavelet transform, then we select an oversampling technique to alleviate the problem of category imbalance, and finally we use a random forest model to train the classification. We conducted comparative experiments to demonstrate the significant advantages of our algorithm in the ECG signal classification task. In addition, to validate the effectiveness of the proposed method, we designed ablation experiments to demonstrate the important role of wavelet transform noise reduction and oversampling in improving the model performance. This paper proposes a method which obviously improves the accuracy of ECG signal classification, and at the same time provides reliable technical support for the automatic diagnosis of cardiac arrhythmia.

Plant Disease Detection Using Deep Learning

Background: Agriculture is a vital sector, providing livelihood and food for a large population. Ensuring plant health is essential for sustainable crop production. Need and Methods: This work proposes a deep learning-based system using Convolutional Neural Networks (CNNs) for automatic detection of plant diseases from leaf images. The model identifies symptoms early, thus supporting timely treatment and reducing crop loss. Results: The system accurately detects plant diseases, recommends suitable fertilizers, and displays real-time sensor data such as temperature and humidity, all on a monitoring interface. Conclusion: Deep learning enables fast, accurate, and automated disease detection, improving crop health and agricultural productivity.

Improving ultrasound image classification accuracy of liver tumors using deep learning model with hepatitis virus infection information.

In recent years, computer-aided diagnosis (CAD) using deep learning methods for medical images has been studied. Although studies have been conducted to classify ultrasound images of tumors of the liver into four categories (liver cysts (Cyst), liver hemangiomas (Hemangioma), hepatocellular carcinoma (HCC), and metastatic liver cancer (Meta)), no studies with additional information for deep learning have been reported. Therefore, we attempted to improve the classification accuracy of ultrasound images of hepatic tumors by adding hepatitis virus infection information to deep learning. Four combinations of hepatitis virus infection information were assigned to each image, plus or minus HBs antigen and plus or minus HCV antibody, and the classification accuracy was compared before and after the information was input and weighted to fully connected layers. With the addition of hepatitis virus infection information, accuracy changed from 0.574 to 0.643. The F1-Score for Cyst, Hemangioma, HCC, and Meta changed from 0.87 to 0.88, 0.55 to 0.57, 0.46 to 0.59, and 0.54 to 0.62, respectively, remaining the same for Hemangioma but increasing for the rest. Learning hepatitis virus infection information showed the highest increase in the F1-Score for HCC, resulting in improved classification accuracy of ultrasound images of hepatic tumors.

Deep Learning-Based Automated Detection of Diabetic Eye Disease: A Novel Approach for Early Diagnosis

Eye diseases are common issues that arise in people with diabetes. Early detection and treatment of these diseases can help in preventing vision loss. Diabetic Eye disease (DED) is becoming impossible to analyse and examine manually, as the number of cases increases. In an earlier stage, changes in eye anatomy variations are often undetectable to the human eye because the features are subtle in nature. The major strains based on the restricted specialist resources are caused by a lot of fundus images whereas the manual examination is hardly possible. Hence, the likeability of deep learning in real-world applications is considered whereas this research investigated deep learning-based approaches to detect the DED at an earlier stage and solve currently encountered problems. Therefore, a novel Deep Convolutional Transfer Learning-based Crossover Harbor Whisker Seal (DCTL-CHW) algorithm is proposed in this article for the automatic detection and classification of diabetic eye diseases. These advanced steps involved in the proposed approach include image pre-processing, data augmentation, DED feature extraction and segmentation, model fine-tuning, and selection of model optimization are employed to evolve an improved system. Hence, the analysis results of examining the various retinal images state that the performances are better than those of all other approaches in terms of effective early diagnosis of DED. The analysis shows that the accuracy, and precision, attained from DCTL-CHW are 96.56%, and 96.51%, respectively.