Explore the vast range of titles available.

Detecting brain tumors in medical imaging is challenging, requiring precise and rapid diagnosis. Deep learning techniques have shown encouraging results in this field. However, current models require significant computer resources and are computationally demanding. To overcome these constraints, we suggested a new deep learning architecture named Lightweight-CancerNet, designed to detect brain tumors efficiently and accurately. The proposed framework utilizes MobileNet architecture as the backbone and NanoDet as the primary detection component, resulting in a notable mean average precision (mAP) of 93.8% and an accuracy of 98%. In addition, we implemented enhancements to minimize computing time without compromising accuracy, rendering our model appropriate for real-time object detection applications. The framework’s ability to detect brain tumors with different image distortions has been demonstrated through extensive tests combining two magnetic resonance imaging (MRI) datasets. This research has shown that our framework is both resilient and reliable. The proposed model can improve patient outcomes and facilitate decision-making in brain surgery while contributing to the development of deep learning in medical imaging.

Ex vivo Fusion Confocal Microscopy (eFuCM) is a promising new technique for real-time histological diagnosis, requiring minimal tissue preparation and avoiding tissue waste. This study aimed to evaluate the feasibility of eFuCM in identifying key liver biopsy lesions and patterns, and to assess the impact of eFuCM reading experience on diagnostic accuracy. Twenty-three fresh liver biopsies were analyzed using eFuCM to produce H&E-like digital images, which were reviewed by two pathologists and compared with a conventional H&E diagnosis. The liver architecture was clearly visible on the eFuCM images. Pathologist 1, with no prior eFuCM experience, achieved a substantial agreement with the H&E diagnosis (κ = 0.65), while Pathologist 2, with eFuCM experience, reached almost perfect agreement (κ = 0.88). However, lower agreement levels were found in the evaluation of inflammation. Importantly, tissue preparation for eFuCM did not compromise subsequent conventional histological processing. These findings suggest that eFuCM has great potential as a time- and material-saving tool in liver pathology, though its diagnostic accuracy improves with pathologist experience, indicating that there is a learning curve related to its use.

This article presents a single model active fault detection and isolation system (SMAC-FDI) which is designed to efficiently detect and isolate a faulty actuator in a system, such as a small (unmanned) aircraft. This FDI system is based on a single and simple aerodynamic model of an aircraft in order to generate some residuals, as soon as an actuator fault occurs. These residuals are used to trigger an active strategy based on artificial exciting signals that searches within the residuals for the signature of an actuator fault. Fault isolation is carried out through an innovative mechanism that does not use the previous residuals but the actuator control signals directly. In addition, the paper presents a complete parameter-tuning strategy for this FDI system. The novel concepts are backed-up by simulations of a small unmanned aircraft experiencing successive actuator failures. The robustness of the SMAC-FDI method is tested in the presence of model uncertainties, realistic sensor noise and wind gusts. Finally, the paper concludes with a discussion on the computational efficiency of the method and its ability to run on small microcontrollers.

The mortality rate has risen due to the increase in number of cardiac patients in recent times due to the lack of unawareness of the symptoms. This work mainly aims to detect the anomalies of the rhythmic conditions of the pulse derived from the electrocardiogram (ECG) pattern based on correlation and the method of mapping. As this device is a programmable one and a real-time application wearable system on the wrist which is physically connected to the veins, it continuously monitors the photoplethysmography (PPG) pattern based on certain parameters and rhythmic conditions, it ensures whether the patient is under the safe condition or not. The salient features of PPG waveform are extracted with respect to various abnormal categories of ECG beats subdivided into various time durations of one, two and three. The PPG pattern using various feature extraction and the correlation transforms with the signal processing application. The extracted features help to find the skipped beat with irregularities of the rhythm will activate the emergency condition protocol in the device. The location of the patient with a critical condition is sent to the nearest health centre. This innovation is a portable one and a user-friendly application which can save many lives in the society.

As is eminent, lung cancer is one of the death frightening syndromes among people in present cases. The earlier diagnosis and treatment of lung cancer can increase the endurance rate of the affected people. But, the structure of the cancer cell makes the diagnosis process more challenging, in which the most of the cells are superimposed. By adopting the efficient image processing techniques, the diagnosis process can be made effective, earlier and accurate, where the time aspect is extremely decisive. With those considerations, the main objective of this work is to propose a region based Fuzzy C-Means Clustering (FCM) technique for segmenting the lung cancer region and the Support Vector Machine (SVM) based classification for diagnosing the cancer stage, which helps in clinical practice in significant way to increase the morality rate. Moreover, the proposed ECM-CSD (Efficient Classification Model for Cancer Stage Diagnosis) uses Computed Tomography (CT) lung images for processing, since it poses higher imaging sensitivity, resolution with good isotopic acquisition in lung nodule identification. With those images, the pre-processing has been made with Gaussian Filter for smoothing and Gabor Filter for enhancement. Following, based on the extracted image features, the effective segmentation of lung nodules is performed using the FCM based clustering. And, the stages of cancer are identified based on the SVM classification technique. Further, the model is analyzed with MATLAB tool by incorporating the LIDC-IDRI lung CT images clinical dataset. The comparative experiments show the efficiency of the proposed model in terms of the performance evaluation factors like increased accuracy and reduced error rate.

Eye diseases can affect vision and well-being, so early, accurate diagnosis is crucial to prevent serious impairment. Deep learning models have shown promise for automating the diagnosis of eye diseases from images. However, current methods mostly use single-model architectures, including convolutional neural networks (CNNs), which might not adequately capture the long-range spatial correlations and local fine-grained features required for classification. To address these limitations, this study proposes a multi-stage framework for eye diseases (MST-EDS), including two stages: hybrid and stacking models in the categorization of eye illnesses across four classes: normal, diabetic_retinopathy, glaucoma, and cataract, utilizing a benchmark dataset from Kaggle. Hybrid models are developed based on Transformer models: Vision Transformer (ViT), Data-efficient Image Transformer (DeiT), and Swin Transformer are used to extract deep features from images, Principal Component Analysis (PCA) is used to reduce the complexity of extracted features, and Machine Learning (ML) models are used as classifiers to enhance performance. In the stacking model, the outputs of the best hybrid models are stacked, and they are used to train and evaluate meta-learners to improve classification performance. The experimental results show that the MST-EDS-RF model recorded the best performance compared to individual Transformer and hybrid models, with 97.163% accuracy.

Leukemia diagnosis with medical imaging necessitates the development of highly accurate and individualized models that uphold data privacy among institutions. This research proposes a framework named FedPerLoRA-Health, a communication-efficient federated learning framework that combines federated personalization and low rank adaptation with EfficientNet architectures for personalized leukemia detection. The proposed PerFLR-EffNet algorithm holds the structural efficiency of EfficientNet variants B0 and B2 as backbone models, facilitating parameter-efficient updates and local personalization across diverse client datasets. Within this framework, personalized layers undergo local training, whereas LoRA-adapted global layers are disseminated to reduce communication overhead. The proposed method is assessed on a Blood Cells Cancer Acute Lymphoblastic Leukemia (ALL) dataset with classification-based metrics such as accuracy, precision, recall and F1-score and federated learning-based metrics such as communication cost and convergence rate. The efficiency of the proposed model is analysed by comparing it with the baseline models such as centralized EfficientNetB0 and EfficientNetB2 without personalized Federation. Experimental results indicate that PerFLR-EffNet attains a better average classification accuracy of 98.67% and also proves to be communication efficient by reporting reduced number of trainable parameters and a reduction in communication overhead by 88.12% when compared with the baseline models.

Accurate dental diagnosis is essential for effective treatment planning and improving patient outcomes, particularly in identifying various dental diseases, such as cavities, fillings, implants, and impacted teeth. This study proposes a new hybrid model that integrates the strengths of the data-efficient image transformer (DeiT) and convolutional attention network (CoAtNet) to enhance diagnostic accuracy. Our approach’s first step involves preprocessing dental radiographic images to improve their quality and enhance feature extraction. The model employs a cross-attention fusion mechanism that aligns and merges feature representations from DeiT and CoAtNet, leveraging their unique capabilities to capture relevant patterns in the data. A stacking classifier, comprising base classifiers such as support vector machines (SVM), eXtreme gradient boosting (XGBoost), and multilayer perceptron (MLP), optimizes classification performance by combining predictions from multiple models. The proposed model demonstrates superior performance, achieving an accuracy of 96%, a precision of 96.5%, 96.1% for sensitivity, 96.4% for specificity, and 96.3% for Dice similarity coefficient, thus showcasing its effectiveness in the automatic diagnosis of dental diseases.

GeneXpert-based testing with Xpert MTB/RIF or Ultra assays is essential for tuberculosis diagnosis. However, testing may be affected by cartridge and staff shortages. More efficient testing strategies could help, especially during the coronavirus disease pandemic. We searched the literature to systematically review whether GeneXpert-based testing of pooled sputum samples achieves sensitivity and specificity similar to testing individual samples; this method could potentially save time and preserve the limited supply of cartridges. From 6 publications, we found 2-sample pools using Xpert MTB/RIF had 87.5% and 96.0% sensitivity (average sensitivity 94%; 95% CI 89.0%-98.0%) (2 studies). Four-sample pools averaged 91% sensitivity with Xpert MTB/RIF (2 studies) and 98% with Ultra (2 studies); combining >4 samples resulted in lower sensitivity. Two studies reported that pooling achieved 99%-100% specificity and 27%-31% in cartridge savings. Our results show that pooling may improve efficiency of GeneXpert-based testing.

We report the design of the NHS-Galleri trial (ISRCTN91431511), aiming to establish whether a multi-cancer early detection (MCED) test that screens asymptomatic individuals for cancer can reduce late-stage cancer incidence. This randomised controlled trial has invited approximately 1.5 million persons and enrolled over 140,000 from the general population of England (50–77 years; ≥3 years without cancer diagnosis or treatment; not undergoing investigation for suspected cancer). Blood is being collected at up to three annual visits. Following baseline blood collection, participants are randomised 1:1 to the intervention (blood tested by MCED test) or control (blood stored) arm. Only participants in the intervention arm with a cancer signal detected have results returned and are referred for urgent investigations and potential treatment. Remaining participants in both arms stay blinded and return for their next visit. Participants are encouraged to continue other NHS cancer screening programmes and seek help for new or unusual symptoms. The primary objective is to demonstrate a statistically significant reduction in the incidence rate of stage III and IV cancers diagnosed in the intervention versus control arm 3–4 years after randomisation. NHS-Galleri will help determine the clinical utility of population screening with an MCED test.