Search Results (2,117)

Prostate cancer is the second most common cancer in men and a leading cause of death worldwide. Early detection is vital, as it often presents with vague symptoms such as nocturia and poor urinary stream. Diagnostic tools like PSA tests, ultrasound, PET-CT, and mpMRI are essential for prostate cancer management. The PI-RADS system helps assess malignancy risk based on imaging. While mpMRI, which includes T1, T2, DWI, and dynamic contrast-enhanced imaging (DCE), is the standard, bpMRI offers a contrast-free alternative using only T2 and DWI. This reduces costs, acquisition time, and the risk of contrast-related side effects but has limitations in detecting higher-risk PI-RADS 3 and 4 lesions. This study compared bpMRI’s diagnostic accuracy to mpMRI, focusing on prostate volume and PI-RADS scoring. Both methods showed strong inter-rater agreement for prostate volume (ICC 0.9963), confirming bpMRI’s reliability in this aspect. However, mpMRI detected more complex conditions, such as periprostatic fat infiltration and iliac lymphadenopathy, which bpMRI missed. While bpMRI offers advantages like reduced cost and no contrast use, it is less effective for higher-risk lesions, making mpMRI more comprehensive. Full article

The epidemic of avian influenza outbreaks, especially high-pathogenicity avian influenza (HPAI), which causes respiratory disease and death, is a disaster in poultry. The outbreak of HPAI in 2014–2015 caused the loss of 60 million chickens and turkeys. The most recent HPAI outbreak, ongoing since 2021, has led to the loss of over 50 million chickens so far in the US and Canada. Farm biosecurity management practices have been used to prevent the spread of the virus. However, existing practices related to controlling the transmission of the virus through wild birds, especially waterfowl, are limited. For instance, ducks were considered hosts of avian influenza viruses in many past outbreaks. The objectives of this study were to develop a machine vision framework for tracking wild birds and test the performance of deep learning models in the detection of wild birds on poultry farms. A deep learning framework based on computer vision was designed and applied to the monitoring of wild birds. A night vision camera was used to collect data on wild bird near poultry farms. In the data, there were two main wild birds: the gadwall and brown thrasher. More than 6000 pictures were extracted through random video selection and applied in the training and testing processes. An overall precision of 0.95 ([email protected]) was reached by the model. The model is capable of automatic and real-time detection of wild birds. Missed detection mainly came from occlusion because the wild birds tended to hide in grass. Future research could be focused on applying the model to alert to the risk of wild birds and combining it with unmanned aerial vehicles to drive out detected wild birds. Full article

We describe the case of a 63-year-old man with pontocerebellar hypoplasia without the claustrum (CL). The patient had a history of cerebral palsy, intelligent disability, cerebellar atrophy, and seizures since birth. At age 61, brain computed tomography (CT) revealed significant cerebellar and brainstem atrophy. At age 63, he was admitted to our hospital for aspiration pneumonia. Although he was treated with medications, including antibiotics, he died one month after admission. The autopsy revealed a total brain weight of 815 g, with the small-sized frontal lobe, cerebellum, and pons. The cross-section of the fourth ventricle had a slit-like appearance, rather than the typical diamond shape. In addition, bilateral CLs were not observed. Apart from CL, no other missing brain tissue or cells could be identified. Microscopic examinations disclosed neurofibrillary tangles in the hippocampus but not in the cortex; however, neither senile plaques nor Lewy bodies were detected. No acquired lesions, including cerebral infarction, hemorrhage, or necrosis, were noted. We pathologically diagnosed the patient with pontocerebellar hypoplasia without CL. As there have been no prior reports of pontocerebellar hypoplasia lacking CL in adults, this case may represent a new subtype. Congenital CL deficiency is likely associated with abnormalities in brain development. CL may play a role in seizure activity, and the loss of bilateral CLs does not necessarily result in immediate death. Further studies are needed to clarify the functions of CL. Full article

Automatic ship detection is a crucial task within the domain of maritime transportation management. With the progressive success of convolutional neural networks (CNNs), a number of advanced CNN models have been presented in order to detect ships. Although these detection models have achieved marked performance, several undesired results may occur under complex maritime conditions, such as missed detections, false positives, and low detection accuracy. Moreover, the existing detection models endure large number of parameters and heavy computation cost. To deal with these problems, we suggest a lightweight ship model of detection called DSSM–LightNet based upon the improved YOLOv8n. First, we introduce a lightweight Dual Convolutional (DualConv) into the model to lower both the number of parameters and the computational complexity. The principle is that DualConv combines two types of convolution kernels, 3x3 and 1x1, and utilizes group convolution techniques to effectively reduce computational costs while processing the same input feature map channels. Second, we propose a Slim-neck structure in the neck network, which introduces GSConv and VoVGSCSP modules to construct an efficient feature-fusion layer. This fusion strategy helps the model better capture the features of targets of different sizes. Meanwhile, a spatially enhanced attention module (SEAM) is leveraged to integrate with a Feature Pyramid Network (FPN) and the Slim-neck to achieve simple yet effective feature extraction, minimizing information loss during feature fusion. CIoU may not accurately reflect the relative positional relationship between bounding boxes in some complex scenarios. In contrast, MPDIoU can provide more accurate positional information in bounding-box regression by directly minimizing point distance and considering comprehensive loss. Therefore, we utilize the minimum point distance IoU (MPDIoU) rather than the Complete Intersection over Union (CIoU) Loss to further enhance the detection precision of the suggested model. Comprehensive tests carried out on the publicly accessible SeaShips dataset have demonstrated that our model greatly exceeds other algorithms in relation to their detection accuracy and efficiency, while reserving its lightweight nature. Full article

This work was conducted mainly to provide a healthy and safe monitoring system for the elderly living in the home environment. In this paper, two different target fall detection schemes are proposed based on whether the target is visible or not. When the target is visible, a vision-based fall detection algorithm is proposed, where an image of the target captured by a camera is transmitted to the improved You Only Look Once version 5s (YOLOv5s) model for posture detection. In contrast, when the target is invisible, a WiFi-based fall detection algorithm is proposed, where channel state information (CSI) signals are used to estimate the target’s posture with an improved long short-term memory (LSTM) model. In the improved YOLOv5s model, adaptive picture scaling technology named Letterbox is used to maintain consistency in the aspect ratio of images in the dataset, and the weighted bidirectional feature pyramid (BiFPN) and the attention mechanisms of squeeze-and-excitation (SE) and coordinate attention (CA) modules are added to the Backbone network and Neck network, respectively. In the improved LSTM model, the Hampel filter is used to eliminate the noise from CSI signals and the convolutional neural network (CNN) model is combined with the LSTM to process the image made from CSI signals, and thus the object of the improved LSTM model at a point in time is the analysis of the amplitude of 90 CSI signals. The final monitoring result of the health status of the target is the result of combining the fall detection of the improved YOLOv5s and LSTM models with the physiological information of the target. Experimental results show the following: (1) the detection precision, recall rate, and average precision of the improved YOLOv5s model are increased by 7.2%, 9%, and 7.6%, respectively, compared with the original model, and there is almost no missed detection of the target; (2) the detection accuracy of the improved LSTM model is improved by 15.61%, 29.36%, and 52.39% compared with the original LSTM, CNN, and neural network (NN) models, respectively, while the convergence speed is improved by 90% compared with the original LSTM model; and (3) the proposed algorithm can meet the requirements of accurate, real-time, and stable applications of health monitoring. Full article

Periapical radiographs are routinely used in dental practice for diagnosis and treatment planning purposes. However, they often suffer from artifacts, distortions, and superimpositions, which can lead to potential misinterpretations. Thus, an automated detection system is required to overcome these challenges. Artificial intelligence (AI) has been revolutionizing various fields, including medicine and dentistry, by facilitating the development of intelligent systems that can aid in performing complex tasks such as diagnosis and treatment planning. The purpose of the present study was to verify the diagnostic performance of an AI system for the automatic detection of teeth, caries, implants, restorations, and fixed prosthesis on periapical radiographs. A dataset comprising 1000 periapical radiographs collected from 500 adult patients was analyzed by an AI system and compared with annotations provided by two oral and maxillofacial radiologists. A strong correlation (R > 0.5) was observed between AI perception and observers 1 and 2 in carious teeth (0.7–0.73), implants (0.97–0.98), restored teeth (0.85–0.89), teeth with fixed prosthesis (0.92–0.94), and missing teeth (0.82–0.85). The automatic detection by the AI system was comparable to the oral radiologists and may be useful for automatic identification in periapical radiographs. Full article

Detecting small objects in images poses significant challenges due to their limited pixel representation and the difficulty in extracting sufficient features, often leading to missed or false detections. To address these challenges and enhance detection accuracy, this paper presents an improved small object detection algorithm, CRL-YOLOv5. The proposed approach integrates the Convolutional Block Attention Module (CBAM) attention mechanism into the C3 module of the backbone network, which enhances the localization accuracy of small objects. Additionally, the Receptive Field Block (RFB) module is introduced to expand the model’s receptive field, thereby fully leveraging contextual information. Furthermore, the network architecture is restructured to include an additional detection layer specifically for small objects, allowing for deeper feature extraction from shallow layers. When tested on the VisDrone2019 small object dataset, CRL-YOLOv5 achieved an mAP50 of 39.2%, representing a 5.4% improvement over the original YOLOv5, effectively boosting the detection precision for small objects in images. Full article

Background/Objectives: Posterior circulation stroke (PCS) poses a diagnostic challenge due to the diverse and subtle clinical manifestations. While the FAST (Face, Arms, Speech, Time) mnemonic has proven effective in identifying anterior circulation stroke, its sensitivity to posterior events is less clear. Recently, the addition of Balance and Eyes to the mnemonic has been proposed as a more comprehensive tool for stroke recognition. Despite this, evidence directly comparing the effectiveness of BE-FAST and FAST in identifying PCS remains limited. Methods: A retrospective analysis was performed on stroke calls at a comprehensive stroke centre, Sydney, Australia. BE-FAST symptoms first assessed at an emergency department triage were recorded, along with automated acute computerised tomography perfusion (CTP) imaging findings. Haemorrhagic strokes were excluded from analysis. An ischaemic stroke diagnosis was confirmed 48–72 h later with magnetic resonance imaging (MRI) brain. The performance of 1. BE-FAST and FAST and 2. BE-FAST and CTP in the hyperacute detection of posterior circulation ischaemic stroke was compared. Results: Out of 164 identified ischaemic infarcts confirmed on MRIs, 46 were PCS. Of these, 27 were FAST-positive, while 45 were BE-FAST-positive. Overall, BE-FAST demonstrated a higher sensitivity compared to FAST in identifying PCS (97.8 vs. 58.7) but suffered from a lower specificity (10.0 vs. 39.8). Notably, 39.1% (n = 18) of patients with PCS would have been missed if only FAST were used. Furthermore, of the 26 PCS negative on CTP, 25 were BE-FAST-positive, and 14 were FAST-positive. Conclusions: The incorporation of Balance and Eye assessments into the FAST protocol improves PCS detection, although may yield more false positives. Full article

This study presents an improved data-centric approach to short-term water demand forecasting using univariate time series from water reservoir levels. The dataset comprises water level recordings from 21 reservoirs in Eastern Thessaloniki collected over 15 months via a SCADA system provided by the water company EYATH S.A. The methodology involves data preprocessing, anomaly detection, data imputation, and the application of predictive models. Techniques such as the Interquartile Range method and moving standard deviation are employed to identify and handle anomalies. Missing values are imputed using LSTM networks optimized through the Optuna framework. This study emphasizes a data-centric approach in deep learning, focusing on improving data quality before model application, which has proven to enhance prediction accuracy. This strategy is crucial, especially in regions where reservoirs are the primary water source, and demand distribution cannot be solely determined by flow meter readings. LSTM, Random Forest Regressor, ARIMA, and SARIMA models are utilized to extract and analyze water level trends, enabling more accurate future water demand predictions. Results indicate that combining deep learning techniques with traditional statistical models significantly improves the accuracy and reliability of water demand predictions, providing a robust framework for optimizing water resource management. Full article

Ship contour extraction is vital for extracting the geometric features of ships, providing comprehensive information essential for ship recognition. The main factors affecting the contour extraction performance are speckle noise and amplitude inhomogeneity, which can lead to over-segmentation and missed detection of ship edges. Polarimetric synthetic aperture radar (PolSAR) images contain rich target scattering information. Under different transmitting and receiving polarization, the amplitude and phase of pixels can be different, which provides the potential to meet the uniform requirement. This paper proposes a novel ship contour extraction framework from PolSAR images based on polarization modulation. Firstly, the image is partitioned into the foreground and background using a super-pixel unsupervised clustering approach. Subsequently, an optimization criterion for target amplitude modulation to achieve uniformity is designed. Finally, the ship’s contour is extracted from the optimized image using an edge-detection operator and an adaptive edge extraction algorithm. Based on the contour, the geometric features of ships are extracted. Moreover, a PolSAR ship contour extraction dataset is established using Gaofen-3 PolSAR images, combined with expert knowledge and automatic identification system (AIS) data. With this dataset, we compare the accuracy of contour extraction and geometric features with state-of-the-art methods. The average errors of extracted length and width are reduced to 20.09 m and 8.96 m. The results demonstrate that the proposed method performs well in both accuracy and precision. Full article

A Brain–Computer Interface (BCI) processes and converts brain signals to provide commands to output devices to carry out certain tasks. The main purpose of BCIs is to replace or restore the missing or damaged functions of disabled people, including in neuromuscular disorders like Amyotrophic Lateral Sclerosis (ALS), cerebral palsy, stroke, or spinal cord injury. Hence, a BCI does not use neuromuscular output pathways; it bypasses traditional neuromuscular pathways by directly interpreting brain signals to command devices. Scientists have used several techniques like electroencephalography (EEG) and intracortical and electrocorticographic (ECoG) techniques to collect brain signals that are used to control robotic arms, prosthetics, wheelchairs, and several other devices. A non-invasive method of EEG is used for collecting and monitoring the signals of the brain. Implementing EEG-based BCI technology in home automation systems may facilitate a wide range of tasks for people with disabilities. It is important to assist and empower individuals with paralysis to engage with existing home automation systems and gadgets in this particular situation. This paper proposes a home security system to control a door and a light using an EEG-based BCI. The system prototype consists of the EMOTIV Insight™ headset, Raspberry Pi 4, a servo motor to open/close the door, and an LED. The system can be very helpful for disabled people, including arm amputees who cannot close or open doors or use a remote control to turn on or turn off lights. The system includes an application made in Flutter to receive notifications on a smartphone related to the status of the door and the LEDs. The disabled person can control the door as well as the LED using his/her brain signals detected by the EMOTIV Insight™ headset. Full article

Trichinellosis is a major foodborne zoonotic disease responsible for 41 human cases, according to the European Union One Health Zoonoses Report. In southern Spain, a quality management system (QMS) was applied to satellite laboratories (SLs) that conduct meat inspections of Trichinella spp. ensuring excellence practices. This study aimed to determine how eventual deviations from standard procedures may influence risk levels using Canonical Discriminant Analysis (CDA). Data were collected during slaughterhouses and game handling establishments’ official audits in 18 SLs located in the provinces of Cordoba and Seville during a 6-year period. Technical requirement deviations regarding technique and trial information, such as performing tests or calculations incorrectly or not following technical procedures, significantly increased risk level differences. Imminent risk levels were detected if the above-mentioned deviations arose. Quality assurance compromising deviations were responsible for 1150 times risk level differences, suggesting finding such may be critical for risk determination. A lack of significant influence of records and documents compromising deviations (incomplete forms or missing-erroneous or illegible data) was found. These results strengthen Trichinella spp. control strategies by pinpointing crucial aspects within QMS that require improvement, particularly in addressing deviations related to technique, trial information, and quality assurance procedures to mitigate associated risks effectively. Full article

When missing reliable comparables, estimating inappropriately is a high risk in the use of both market-oriented and income approach methods. Therefore, it is useful to identify effective alternatives in accordance with the estimation method to arrive at the estimated value in the absence of comparables. This paper examines the use of the asking price for estimating the market value of a fruit tree orchard, missing comparable data of similar assets. The analysis was conducted by considering two different scenarios. In the first, asking prices from the same segment of the land to be estimated were used in two market-oriented appraisal methods: the General Appraisal System (GAS) and the Nearest Neighbors Appraisal Technique (NNAT). In both these approaches, market prices were replaced with detected asking prices. The second scenario was based on the use of the Remote Segments Approach (RSA). The comparison was conducted between the market segment of the fruit orchard to be valued and other comparison market segments, consisting of three other species of fruit trees, grown in the same area where the fruit orchard to be estimated is located. The results showed that in the first scenario, the estimated value appeared to be unreliable and excessively high compared to actual market conditions. Using the segment comparison method, which applies asking prices for the purpose of determining the capitalization rate, produced more reliable results. The appraisal also appeared more objective, transparent, and consistent with valuation standards. In the presence of similar limiting conditions, RSA can be an effective support to the activity of the appraiser in the valuation process of agricultural land. Full article

Conventional radiography is widely used for postmortem foetal imaging, but its role in diagnosing congenital anomalies is debated. This study aimed to assess the effectiveness of X-rays in detecting skeletal abnormalities and guiding genetic analysis and counselling. This is a retrospective analysis of all post-abortion diagnostic imaging studies conducted at a centre serving a population of over 300,000 inhabitants from 2008 to 2023. The data were analysed using descriptive statistics. X-rays of 81 aborted foetuses (total of 308 projections; mean: 3.8 projections/examination; SD: 1.79) were included. We detected 137 skeletal anomalies. In seven cases (12.7%), skeletal anomalies identified through radiology were missed by prenatal sonography. The autopsy confirmed radiological data in all cases except for two radiological false positives. Additionally, radiology failed to identify a case of syndactyly, which was revealed by anatomopathology. X-ray is crucial for accurately classifying skeletal abnormalities, determining the causes of spontaneous abortion, and guiding the request for genetic counselling. Formal training for both technicians and radiologists, as well as multidisciplinary teamwork, is necessary to perform X-ray examinations on aborted foetuses and interpret the results effectively. Full article

Tomato blight significantly threatened tomato yield and quality, making precise disease detection essential for modern agricultural practices. Traditional segmentation models often struggle with over-segmentation and missed segmentation, particularly in complex backgrounds and with diverse lesion morphologies. To address these challenges, we proposed Unet with Vision Mamba and ConvNeXt (VMC-Unet), an asymmetric segmentation model for quantitative analysis of tomato blight. Built on the Unet framework, VMC-Unet integrated a parallel feature-aware backbone combining ConvNeXt, Vision Mamba, and Atrous Spatial Pyramid Pooling (ASPP) modules to enhance spatial feature focusing and multi-scale information processing. During decoding, Vision Mamba was hierarchically embedded to accurately recover complex lesion morphologies through refined feature processing and efficient up-sampling. A joint loss function was designed to optimize the model’s performance. Extensive experiments on both tomato epidemic and public datasets demonstrated VMC-Unet superior performance, achieving 97.82% pixel accuracy, 87.94% F1 score, and 86.75% mIoU. These results surpassed those of classical segmentation models, underscoring the effectiveness of VMC-Unet in mitigating over-segmentation and under-segmentation while maintaining high segmentation accuracy in complex backgrounds. The consistent performance of the model across various datasets further validated its robustness and generalization potential, highlighting its applicability in broader agricultural settings. Full article