Search Results (9,954)

Background/Objectives: This report details a rare instance of an infant with achondroplasia developing acute tetraparesis after a cervical whiplash injury, highlighting key multidisciplinary management considerations and specific anesthetic strategies to mitigate potential risks. Case presentation: A 1-year-old boy with achondroplasia presented with acute tetraparesis after a whiplash injury. Initial craniocervical computed tomography demonstrated a reduced volume of the posterior fossa, foramen magnum stenosis, and ventriculomegaly, without any fractures or dislocations. Moreover, magnetic resonance imaging (MRI) revealed pathological signal changes in the medulla oblongata, cervical spinal cord in segments C1 and C2, and the posterior atlantoaxial ligament. After initial conservative therapy and head immobilization using a soft cervical collar, partial remission of the tetraparesis was achieved. Two weeks post-injury, microsurgical posterior fossa decompression extending to the foramen magnum and C1 laminectomy was performed under general anesthesia with intraoperative neuromonitoring. Following an unsuccessful intubation attempt using a fiberoptic bronchoscope, successful airway management was achieved using a combined technique incorporating video laryngoscopy. Venous access was secured under ultrasound guidance. The patient exhibited complete remission of neurological symptoms by the third postoperative month during follow-up. Conclusions: This case report underscores the crucial need for a multidisciplinary approach in managing children with achondroplasia, especially with foramen magnum stenosis and complex cervical spine injuries. Anesthetic management required meticulously planned airway strategies using advanced techniques like video laryngoscopy and fiberoptic bronchoscopy to reduce airway risks. It also highlights the importance of conservative therapy paired with timely neurosurgical intervention, resulting in the patient’s full recovery. Full article

The right internal jugular line (RIJL) is a type of central venous catheter (CVC) inserted into the right internal jugular vein to deliver medications and monitor vital functions in ICU patients. The placement of RIJL is routinely checked by a clinician in a chest X-ray (CXR) image to ensure its proper function and patient safety. To reduce the workload of clinicians, deep learning-based automated detection algorithms have been developed to detect CVCs in CXRs. Although RIJL is the most widely used type of CVCs, there is a paucity of investigations focused on its accurate segmentation and tip localization. In this study, we propose a deep learning system that integrates an anatomical landmark segmentation, an RIJL segmentation network, and a postprocessing function to segment the RIJL course and detect the tip with accuracy and precision. We utilized the nnU-Net framework to configure the segmentation network. The entire system was implemented on the SimpleMind Cognitive AI platform, enabling the integration of anatomical knowledge and spatial reasoning to model relationships between objects within the image. Specifically, the trachea was used as an anatomical landmark to extract a subregion in a CXR image that is most relevant to the RIJL. The subregions were used to generate cropped images, which were used to train the segmentation network. The segmentation results were recovered to original dimensions, and the most inferior point’s coordinates in each image were defined as the tip. With guidance from the anatomical landmark and customized postprocessing, the proposed method achieved improved segmentation and tip localization compared to the baseline segmentation network: the mean average symmetric surface distance (ASSD) was decreased from 2.72 to 1.41 mm, and the mean tip distance was reduced from 11.27 to 8.29 mm. Full article

The dynamics of vegetation changes and phenology serve as key indicators of interannual changes in vegetation productivity. Monitoring the changes in the Nanling grassland ecosystem using the remote sensing vegetation index is crucial for the rational development, utilization, and protection of these grassland resources. Grasslands in the hilly areas of southern China’s middle and low mountains have a high restoration efficiency due to the favorable combination of water and temperature conditions. However, the dynamic adaptation process of grassland restoration under the combined effects of climate change and human activities remains unclear. The aim of this study was to conduct continuous phenological monitoring of the Nanling grassland ecosystem, and evaluate its seasonal characteristics, trends, and the thresholds for grassland changes. The Normalized Difference Phenology Index (NDPI) values of Nanling Mountains’ grasslands from 2000 to 2021 was calculated using MOD09A1 images from the Google Earth Engine (GEE) platform. The Savitzky–Golay filter and Mann–Kendall test were applied for time series smoothing and trend analysis, and growing seasons were extracted annually using Seasonal Trend Decomposition and LOESS. A segmented regression method was then employed to detect the thresholds for grassland ecosystem restoration based on phenology and grassland cover percentage. The results showed that (1) the NDPI values increased significantly (p < 0.01) across all grassland patches, particularly in the southeast, with a notable rise from 2010 to 2014, and following an eastern to western to central trend mutation sequence. (2) the annual lower and upper NDPI thresholds of the grasslands were 0.005~0.167 and 0.572~0.727, which mainly occurred in January–March and June–September, respectively. (3) Most of the time series in the same periods showed increasing trends, with the growing season length varying from 188 to 247 days. (4) The overall potential productivity of the Nanling grassland improved. (5) The restoration of the mountain grasslands was significantly associated with the grassland coverage and mean NDPI values, with a key threshold identified at a mean NDPI value of 0.5 for 2.1% grassland coverage. This study indicates that to ensure the sustainable development and conservation of grassland ecosystems, targeted management strategies should be implemented, particularly in regions where human factors significantly influence grassland productivity fluctuations. Full article

The size and morphology of the grains of a material and their distribution have a significant impact on the mechanical properties of the material (and their further application). Based on the data obtained from image analysis, it is possible to modify the microstructure of materials. Within the formation of a eutectic, borides occur along the austenite grain boundary. The cell size can be managed by technological process (forming) or by adding chemical elements. In this paper, a method of measuring the cell size of a hypoeutectic Fe-B-C alloy across the entire examined cross-section of the sample was researched by creating a mosaic from individual frames. Sample preparation allowing clear grain boundary visibility was essential. It was observed that the most effective results were achieved with quenched microstructures etched using Klemm I color etchant. A Zeiss optic microscope with AxioVision software (AxioVision SE64 Rel. 4.9.1.) was used for image acquisition, and mosaics were created using MosaiX software. This study revealed that, before further processing, images must be segmented to address color inconsistencies using average grayscale values. This preprocessing step enabled precise cell size analysis through an algorithm implemented in Scilab. The developed methodology was used to create sample maps for determining the grain size and its distribution in the Fe-B alloy. This automated approach provides a comprehensive dataset, enabling detailed analysis of both individual images and the entire sample. Manual grain size measurements were performed for verification, and statistical analysis demonstrated a close correspondence between the results. The results confirmed a significant impact of the added alloying elements on microstructural homogeneity in hypoeutectic Fe-B-C alloys. Homogeneity decreases with the addition of alloying elements such as chromium and vanadium, while tungsten contributes to a more stable grain size. A low gradient value shows small grain size changes from the core to the edge in the cross-section. Furthermore, the results show that higher amounts of chromium increase the average grain size values. The results demonstrate that automated methods allow for comprehensive analysis of the entire sample, enabling precise determination of grain size and other properties across the entire object rather than only on subjectively selected areas. This approach effectively eliminates the influence of human error, ensuring more reliable and consistent data. Full article

An accurate and efficient detection method for harvesting is crucial for the development of automated harvesting robots in short-cycle, high-yield facility tomato cultivation environments. This study focuses on cherry tomatoes, which grow in clusters, and addresses the complexity and reduced detection speed associated with the current multi-step processes that combine target detection with segmentation and traditional image processing for clustered fruits. We propose YOLO-Picking Point (YOLO-PP), an improved cherry tomato picking point detection network designed to efficiently and accurately identify stem keypoints on embedded devices. YOLO-PP employs a C2FET module with an EfficientViT branch, utilizing parallel dual-path feature extraction to enhance detection performance in dense scenes. Additionally, we designed and implemented a Spatial Pyramid Squeeze Pooling (SPSP) module to extract fine features and capture multi-scale spatial information. Furthermore, a new loss function based on Inner-CIoU was developed specifically for keypoint tasks to further improve detection efficiency.The model was tested on a real greenhouse cherry tomato dataset, achieving an accuracy of 95.81%, a recall rate of 98.86%, and mean Average Precision (mAP) scores of 99.18% and 98.87% for mAP50 and mAP50-95, respectively. Compared to the DEKR, YOLO-Pose, and YOLOv8-Pose models, the mAP value of the YOLO-PP model improved by 16.94%, 10.83%, and 0.81%, respectively. The proposed algorithm has been implemented on NVIDIA Jetson edge computing devices, equipped with a human–computer interaction interface. The results demonstrate that the proposed Improved Picking Point Detection Network exhibits excellent performance and achieves real-time accurate detection of cherry tomato harvesting tasks in facility agriculture. Full article

The widespread deployment of deep neural networks (DNNs) in critical real-time applications has spurred significant research into their security and robustness. A key vulnerability identified is that DNN decisions can be maliciously altered by introducing carefully crafted noise into the input data, leading to erroneous predictions. This is known as an adversarial attack. In this paper, we propose a novel detection framework leveraging segmentation masks and image segmentation techniques to identify adversarial attacks on DNNs, particularly in the context of autonomous driving systems. Our defense technique considers two levels of adversarial detection. The first level mainly detects adversarial inputs with large perturbations using the U-net model and one-class support vector machine (SVM). The second level of defense proposes a dynamic segmentation algorithm based on the k-means algorithm and a verifier model that controls the final prediction of the input image. To evaluate our approach, we comprehensively compare our method to the state-of-the-art feature squeeze method under a white-box attack, using eleven distinct adversarial attacks across three benchmark and heterogeneous data sets. The experimental results demonstrate the efficacy of our framework, achieving overall detection rates exceeding 96% across all adversarial techniques and data sets studied. It is worth mentioning that our method enhances the detection rates of FGSM and BIM attacks, reaching average detection rates of 95.65% as opposed to 62.63% in feature squeezing across the three data sets. Full article

The operative field and exposure in minimally invasive cardiac surgery (MICS) are limited. Meticulous preoperative planning and intraoperative visualization are crucial. We present our initial experience with HoloLens^® 2 as an intraoperative guide during MICS procedures: aortic valve replacement (AVR) via right anterior small thoracotomy, coronary artery bypass graft surgery (CABG) via left anterior small thoracotomy (LAST), and pulmonary valve replacement (PVR) via LAST. Three-dimensional (3D) segmentations were performed using the patient’s computer tomography (CT) data subsequently rendered into a 3D hologram on the HoloLens^® 2. The holographic image was then superimposed on the patient lying on the operating table, using the xiphoid and the clavicle as landmarks, and was used as a real-time anatomical image guide for the surgery. The incision site marking made using HoloLens^® 2 differed by one intercostal space from the marking made using a conventional surgeon’s mental reconstructed image from the patient’s preoperative imaging and was found to be a more appropriate site of entry into the chest for the structure of interest. The transparent visor of the HoloLens^® 2 provided unobstructed views of the operating field. A mixed reality (MR) device could contribute to preoperative surgical planning and intraoperative real-time image guidance, which facilitates the understanding of anatomical relationships. MR has the potential to improve surgical precision, decrease risk, and enhance patient safety. Full article

Immunohistochemical (IHC) detection is crucial in diagnosing lung cancer. Interleukin-24 (IL-24) is a valuable marker in IHC analysis, aiding in tumor characterization and prognostication. However, current manual scoring methods are labor-intensive, imprecise, and subjective, leading to inconsistencies among observers. Automated scoring methods also have limitations, such as poor segmentation and lack of interpretability. In this paper, we introduce RMD-Net, a novel scoring network framework specifically designed for IL-24 scoring in lung cancer. The framework incorporates a regional attention mechanism and a multi-channel scoring network. Initially, diagnostic region identification and segmentation are accomplished by integrating the diagnostic regional spatial attention module into the fully convolutional network. Subsequently, we employ the Adaptive Multi-Thresholding algorithm to derive expert, strong feature description maps. Finally, the attention-guided IHC images and expert feature description maps are fed into a multi-channel scoring network. Its backbone includes feature fusion layers and scoring layers to ensure the accuracy and interpretability of the final result. To the best of our knowledge, this is the first system that directly employs lung cancer IL-24 IHC images as input and combines both expert-derived features and deep-learning abstract features to produce clinical scores. Our dataset is sourced from the Institute of Life Sciences and Bioengineering at Beijing Jiaotong University. The experimental results demonstrate that the proposed method achieves an IL-24 score precision of 89.25%, an F1 score of 89.00, and an accuracy of 95.94%, outperforming other state-of-the-art methods. This contribution has the potential to advance clinical diagnosis and treatment strategies for lung cancer. Full article

Monitoring changes in lake area using remote sensing imagery and artificial intelligence algorithms is essential for assessing regional ecological balance. However, most current semantic segmentation models primarily rely on the visible light spectrum for feature extraction, which fails to fully utilize the multi-spectral characteristics of remote sensing images. Therefore, this leads to issues such as blurred segmentation of lake boundaries in the imagery, the loss of small water body targets, and incorrect classification of water bodies. Additionally, the practical applicability of existing algorithms is limited, and their performance under real-world conditions requires further investigation. To address these challenges, this paper introduces SCR-Net, a water body identification model designed for multi-spectral remote sensing images. SCR-Net employs a dual-channel encoding–decoding mechanism and alters the number of channels used for reading image data, enhancing feature learning for lakes while focusing on extracting information about the water body target locations, thereby ensuring accurate segmentation. Trained on multi-spectral remote sensing images, the model leverages the unique spectral properties of these images to improve segmentation accuracy. Extensive validation on two datasets demonstrates that SCR-Net outperforms state-of-the-art models in terms of segmentation accuracy. Based on the validation using this dataset, Daihai Lake in Inner Mongolia was additionally selected as a case study to calculate the lake area, providing valuable insights for interdisciplinary research in ecological environment monitoring and remote sensing image processing. Full article

The rapid adoption of robotic-assisted total knee arthroplasty (RATKA) has resulted in pre-operative CT scans becoming more readily available. After the segmentation and identification of landmarks by trained segmentation specialists, the Mako SmartRobotics^TM software generates measurements of interest for the calculation of the arithmetic hip-knee-ankle axis (aHKA), joint line obliquity (JLO), and the Coronal Plane Alignment of the Knee (CPAK) phenotype. The aim of this study is to ascertain how closely correlated these two sets of readings are and whether the CPAK distribution is altered when comparing both modalities. A retrospective radiological study was undertaken on 500 knees (367 patients: 133 bilateral, 234 unilateral) comparing the CT-based software-generated measurements of patients undergoing RATKA using the Stryker Mako system against manual measurements derived from long limb radiographs (LLRs). There were statistically significant differences between the average measurements of the LDFA (0.27 ± 2.95, p = 0.045), MPTA (1.15 ± 2.20, p < 0.001), aHKA (1.41 ± 3.85, p < 0.001) and JLO (0.89 ± 3.50, p < 0.001), with CT measurements having higher mean readings for LDFA, lower readings for MPTA, more varus aHKA and increased apex distal JLO. Despite this, correlation was moderately good: LDFA (r = 0.409, p < 0.001), MPTA (r = 0.683, p < 0.001), aHKA (r = 0.595, p < 0.001) and JLO (r = 0.456, p < 0.001). The CPAK distribution was also significantly different. LLRs underestimate the degree of constitutional varus and JLO compared to CT-based software-generated measurements, with a resultant increase in CPAK Types I and IV when using CT measurements. Despite moderately good correlation between both imaging modalities, there remains a statistically significant difference between them. Full article

Breast cancer is one of the most prevalent cancers among women, with early detection playing a critical role in improving survival rates. This study introduces a novel transformer-based explainable model for breast cancer lesion segmentation (TEBLS), aimed at enhancing the accuracy and interpretability of breast cancer lesion segmentation in medical imaging. TEBLS integrates a multi-scale information fusion approach with a hierarchical vision transformer, capturing both local and global features by leveraging the self-attention mechanism. This model addresses the limitations of existing segmentation methods, such as the inability to effectively capture long-range dependencies and fine-grained semantic information. Additionally, TEBLS incorporates visualization techniques to provide insights into the segmentation process, enhancing the model’s interpretability for clinical use. Experiments demonstrate that TEBLS outperforms traditional and existing deep learning-based methods in segmenting complex breast cancer lesions with variations in size, shape, and texture, achieving a mean DSC of 81.86% and a mean AUC of 97.72% on the CBIS-DDSM test set. Our model not only improves segmentation accuracy but also offers a more explainable framework, which has the potential to be used in clinical settings. Full article

This study examines the impact of seabed conditions on image segmentation for seabed target images acquired via side-scan sonar during sea experiments. The dataset comprised cylindrical target images overlying on two seabed types, mud and sand, categorized accordingly. The deep learning algorithm (U-NET) was utilized for image segmentation. The analysis focused on two key factors influencing segmentation performance: the weighting method of the cross-entropy loss function and the combination of datasets categorized by seabed type for training, validation, and testing. The results revealed three key findings. First, applying equal weights to the loss function yielded better segmentation performance compared to pixel-frequency-based weighting. This improvement is indicated by Intersection over Union (IoU) for the highlight class in dataset 2 (0.41 compared to 0.37). Second, images from the mud area were easier to segment than those from the sand area. This was due to the clearer intensity contrast between the target highlight and background. This difference is indicated by the IoU for the highlight class (0.63 compared to 0.41). Finally, a network trained on a combined dataset from both seabed types improved segmentation performance. This improvement was observed in challenging conditions, such as sand areas. In comparison, a network trained on a single-seabed dataset showed lower performance. The IoU values for the highlight class in sand area images are as follows: 0.34 for training on mud, 0.41 for training on sand, and 0.45 for training on both. Full article

Background: Unilateral basal ganglia calcinosis (BGC) is a rare radiological finding that can be diagnosed on computed tomography (CT) and magnetic resonance imaging (MRI) but often presents challenges for clinicians and radiologists in determining its underlying cause. So far, only a few potential causes that could explain unilateral BGC have been described in the literature. Case Report: A 54-year-old Caucasian male was admitted to a tertiary university hospital due to the sudden onset of speech impairment and right-sided weakness. The patient had no significant medical history prior to this event. Non-enhanced computed tomography (NECT) of the brain revealed no evidence of acute ischemia; CT angiography (CTA) showed acute left middle cerebral artery (MCA) M2 segment occlusion. CT perfusion (CTP) maps revealed an extensive penumbra-like lesion, which is potentially reversible upon achieving successful recanalization. However, a primary neoplastic tumor with calcifications in the basal ganglia was initially interpreted as the potential cause; therefore, acute stroke treatment with intravenous thrombolysis was contraindicated. A follow-up CT examination at 24 h revealed an ischemic lesion localized to the left insula, predominantly involving the left parietal lobe and the superior gyrus of the left temporal lobe. Subsequent gadolinium-enhanced brain MRI revealed small blood vessels draining into the subependymal periventricular veins on the left basal ganglia. Digital subtraction angiography was conducted, confirming the diagnosis of venous angioma. Conclusions: Unilateral BGC caused by venous angioma is a rare entity with unclear pathophysiological mechanisms and heterogeneous clinical presentation. It may mimic conditions such as intracerebral hemorrhage or hemorrhagic brain tumors, complicating acute stroke management, as demonstrated in this case. Surrounding tissue calcification may provide a valuable radiological clue in diagnosing venous angiomas DVAs and vascular malformations. Full article

This study tackles the challenge of precise wood log counting, where applications of the proposed methodology can span from automated approaches for materials management, surveillance, and safety science to wood traffic monitoring, wood volume estimation, and others. We introduce an approach leveraging Conditional Generative Adversarial Networks (cGANs) for eucalyptus log segmentation in images, incorporating specialized image processing techniques to handle noise and intersections, coupled with the Connected Components Algorithm for efficient counting. To support this research, we created and made publicly available a comprehensive database of 466 images containing approximately 13,048 eucalyptus logs, which served for both training and validation purposes. Our method demonstrated robust performance, achieving an average Accuracypixel of 96.4% and Accuracylogs of 92.3%, with additional measures such as F1 scores ranging from 0.879 to 0.933 and IoU values between 0.784 and 0.875, further validating its effectiveness. The implementation proves to be efficient with an average processing time of 0.713 s per image on an NVIDIA T4 GPU, making it suitable for real-time applications. The practical implications of this method are significant for operational forestry, enabling more accurate inventory management, reducing human errors in manual counting, and optimizing resource allocation. Furthermore, the segmentation capabilities of the model provide a foundation for advanced applications such as eucalyptus stack volume estimation, contributing to a more comprehensive and refined analysis of forestry operations. The methodology’s success in handling complex scenarios, including intersecting logs and varying environmental conditions, positions it as a valuable tool for practical applications across related industrial sectors. Full article

Underwater fish image segmentation is a crucial technique in marine fish monitoring. However, typical underwater fish images often suffer from issues such as color distortion, low contrast, and blurriness, primarily due to the complex and dynamic nature of the marine environment. To enhance the accuracy of underwater fish image segmentation, this paper introduces an innovative neural network model that combines the attention mechanism with a feature pyramid module. After the backbone network processes the input image through convolution, the data pass through the enhanced feature pyramid module, where it is iteratively processed by multiple weighted branches. Unlike conventional methods, the multi-scale feature extraction module that we designed not only improves the extraction of high-level semantic features but also optimizes the distribution of low-level shape feature weights through the synergistic interactions of the branches, all while preserving the inherent properties of the image. This novel architecture significantly boosts segmentation accuracy, offering a new solution for fish image segmentation tasks. To further enhance the model’s robustness, the Mix-up and CutMix data augmentation techniques were employed. The model was validated using the Fish4Knowledge dataset, and the experimental results demonstrate that the model achieves a Mean Intersection over Union (MIoU) of 95.1%, with improvements of 1.3%, 1.5%, and 1.7% in the MIoU, Mean Pixel Accuracy (PA), and F1 score, respectively, compared to traditional segmentation methods. Additionally, a real fish image dataset captured in deep-sea environments was constructed to verify the practical applicability of the proposed algorithm. Full article