Search Results (271)

Background: Ultrasound and colour Doppler are adjuvant techniques widely used in clinical settings in obstetrics, cardiology, and others. Its use in dermatology is more incipient although it presents potential for clinical use namely in dermo-oncology. Objective: This study explores the usefulness of the combination of cutaneous ultrasound with Doppler after digital dermatoscopy in distinguishing between most common benign and malignant skin lesions, focusing on the importance of different vascular patterns. To streamline the diagnostic process, we propose a combined imaging workflow that integrates dermoscopic findings with vascular and structural data obtained via Doppler ultrasound. Methods: In total, 42 benign and malignant skin tumours were analysed in a population of 42 patients using a Fotofinder digital dermatoscopy device and a GE ultrasound machine with a high-frequency probe (20 MHz). Doppler was applied to assess lesion vascularization and identify distinct blood flow patterns. Results: Cutaneous ultrasound revealed that malignant lesions often exhibited intense and disorganized vascularization, while benign lesions displayed more ordered and peripheral blood flow patterns. In all of our cases, ultrasound with Doppler imaging clarified the uncertainties raised by dermatoscopy. Conclusions: The use of Doppler cutaneous ultrasound after digital dermatoscopy proved to be a valuable tool to aid the diagnosis in dermatology, as it improved the differential diagnosis between benign and malignant lesions, contributing to the establishment of the final diagnosis in the studied cases. Full article

Background: Ultrasound (U/S) can be used to evaluate skeletal muscle characteristics in clinical and sports settings. Handheld U/S devices have recently emerged as a cheaper and portable alternative to conventional U/S systems. However, further research is warranted on their reliability. We assessed the reliability and inter-device agreement between a handheld U/S device (Clarius L15 HD₃) and a more conventional U/S system (GE LOGIQ e) for measuring the thickness of the rectus femoris (RF) and vastus intermedius (VI). Methods: Cross-sectional images of the RF and VI muscles were obtained in 20 participants by two assessors, and on two separate occasions by one of those assessors, using the Clarius L15 HD₃ and GE LOGIQ e devices. RF and VI thickness measurements were obtained to determine the intra-rater reliability, inter-rater reliability, and inter-device agreement. Results: All intraclass correlation coefficients (ICCs) were above 0.9 for intra-rater reliability (range: 0.94 to 0.97), inter-rater reliability (ICC: 0.97), and inter-device agreement (ICC: 0.98) when comparing the two devices in assessing RF and VI thickness. For the RF, the Bland–Altman plot revealed a mean difference of 0.06 ± 0.07 cm, with limits of agreement ranging from 0.21 to −0.09, whereas for the VI, the Bland–Altman plot showed a mean difference of 0.07 ± 0.10 cm, with limits of agreement ranging from 0.27 to −0.13. Conclusions: The handheld Clarius L15 HD₃ was reliable and demonstrated high agreement with the more conventional GE LOGIQ e for assessing the thickness of the RF and VI in young, healthy adults. Full article

Gastric cancer remains the fourth leading cause of cancer-related mortality worldwide. Advanced disease is associated with a poor prognosis, emphasizing the critical importance of early diagnosis through endoscopy. In addition to prognosis, disease extent also plays a pivotal role in guiding management strategies. Therefore, accurate locoregional staging (T and N staging) is vital for optimal prognostic and therapeutic planning. Endoscopic ultrasound (EUS) has long been an essential tool in this regard, with computed tomography (CT) and, more recently, positron emission tomography–computed tomography (PET–CT) serving as alternative imaging modalities. EUS is particularly valuable in the assessment of early gastric cancer, defined as tumor invasion confined to the mucosa or submucosa. These tumors are increasingly managed by endoscopic resection techniques offering improved post-treatment quality of life. EUS has also recently been utilized in the restaging process after neoadjuvant chemotherapy, aiding in the evaluation of tumor resectability and prognosis. Its performance may be further enhanced through the application of emerging techniques such as contrast-enhanced endosonography, EUS elastography, and artificial intelligence systems. In advanced, unresectable disease, complications such as gastric outlet obstruction (GOO) severely impact patient quality of life. In this setting, EUS-guided gastroenterostomy (EUS-GE) offers a less invasive alternative to surgical gastrojejunostomy. This review summarizes and critically analyzes the role of EUS in the context of gastric cancer, highlighting its applications across different stages of the disease and evaluating its performance relative to other diagnostic modalities. Full article

Accurate diagnosis of knee joint injuries from magnetic resonance (MR) images is critical for patient care. Background/Objectives: While deep learning has advanced 3D MR image analysis, its reliance on extensive labeled datasets is a major hurdle for diverse knee pathologies. Few-shot learning (FSL) addresses this by enabling models to classify new conditions from minimal annotated examples, often leveraging knowledge from related tasks. However, creating robust 3D FSL frameworks for varied knee injuries remains challenging. Methods: We introduce MedNet-FS, a 3D FSL framework that effectively classifies knee injuries by utilizing domain-specific pre-trained weights and generalized end-to-end (GE2E) loss for discriminative embeddings. Results: MedNet-FS, with knee-MRI-specific pre-training, significantly outperformed models using generic or other medical pre-trained weights and approached supervised learning performance on internal datasets with limited samples (e.g., achieving an area under the curve (AUC) of 0.76 for ACL tear classification with k = 40 support samples on the MRNet dataset). External validation on the KneeMRI dataset revealed challenges in classifying partially torn ACL (AUC up to 0.58) but demonstrated promising performance for distinguishing intact versus fully ruptured ACLs (AUC 0.62 with k = 40). Conclusions: These findings demonstrate that tailored FSL strategies can substantially reduce data dependency in developing specialized medical imaging tools. This approach fosters rapid AI tool development for knee injuries and offers a scalable solution for data scarcity in other medical imaging domains, potentially democratizing AI-assisted diagnostics, particularly for rare conditions or in resource-limited settings. Full article

Background/Objectives: The aim of this study is to identify markers and develop a multifactorial model for characterizing extensive scar tissue after revascularization in patients with myocardial infarction (MI). Methods: A total of 123 patients with MI were examined. The patients underwent contrast-enhanced cardiac magnetic resonance imaging (MRI) with a 1.5 Tesla GE SIGNA Voyager (GE HealthCare, Chicago, IL, USA) on the 7th–10th days from the onset of the disease. At the first stage, we performed a comparative analysis and built a multifactorial model based on the examination results of 92 (75%) patients enrolled from April 2021 to October 2023. These patients formed the group used for model development, or the “modeling group”. The mass of the scar was calculated, including relative to the left ventricular (LV) myocardium mass (M_scar/LVMM, in %). Results: The first subgroup consisted of 36 (39%) patients with a large scar, denoted as “LS” (M_scar/LVMM > 20%). The second subgroup included 56 (61%) patients with a smaller scar, referred to as “SS” (M_scar/LVMM ≤ 20%). Logistic regression was used to identify independent factors affecting scar tissue size. A multifactorial model was created. This model predicts M_scar/LVMM > 20% on MRI. It uses readily available clinical parameters: high-sensitivity troponin I (HscTn I) and N-terminal pro B-type natriuretic peptide (NT-proBNP) levels, and LV relative wall thickness (RWT). We tested the multifactorial model on the “modeling group” (n = 31). The sensitivity was 63.6% and the specificity was 85.7%. Conclusions: These indicates the feasibility of its application in clinical practice. Full article

The aim of this work was to design a coil for magnetic resonance imaging (MRI) and magnetic resonance spectroscopy (MRS) to analyze the morphology of cells in vitro. This newly developed hardware, due to compatibility to the 1.5-Tesla MRI scanner (GE Healthcare, Boston, MA, USA), allows for the characterization of cell cultures in vitro. To adapt a designed coil on the 1.5-Tesla MRI scanner, some changes in hardware and software were carried out. The advantage of the designed receiving circuit is the ability to perform MRI with a resolution of 80 μm × 80 μm pixel size. Additionally, this coil can be used to visualize cell cultures and tissue sections, which, due to their small dimensions, could not be imaged on standard MRS and MRI coils at 1.5 Tesla. Full article

In this study, Lu_2.5Y_0.5(Al_2.5Ga_2.5)O₁₂ (LuYAGG) single-crystal scintillators doped with terbium ions (Tb³⁺) at concentrations of 0.5, 1, 5, and 10 mol% were successfully synthesized using the floating zone method. The structural, optical, photoluminescence (PL), and scintillation properties of the Tb³⁺-doped crystals were systematically investigated with a focus on their potential for high-performance scintillator applications. X-ray diffraction (XRD) confirmed the formation of a pure garnet phase without any secondary phases, indicating the successful incorporation of Tb³⁺ into the LuYAGG lattice. Optical transmittance spectra revealed high transparency in the visible range. Photoluminescence measurements showed characteristic Tb³⁺ emission peaks, with the strongest green emission observed from the ⁵D₄ → ⁷F₅ transition, particularly for the 5 mol% sample. The PL decay curves further confirmed that this concentration offers a favorable balance between radiative efficiency and minimal non-radiative losses. Under γ-ray excitation, the 5 mol% Tb³⁺-doped crystal exhibited the highest light yield, surpassing the performance of other concentrations and even outperforming Bi₄Ge₃O₁₂ (BGO) in relative comparison, with an estimated yield of approximately 60,000 photons/MeV. Scintillation decay time analysis revealed that the 5 mol% sample also possessed the fastest decay component, indicating its superior capability for radiation detection. Although 10 mol% Tb³⁺ still showed good performance, slight quenching effects were observed, while lower concentrations (0.5 and 1 mol%) suffered from longer decay and lower emission efficiency due to limited activator density. These findings clearly identify with 5 mol% Tb³⁺ as the optimal dopant level in LuYAGG single crystals, offering a synergistic combination of high light yield and excellent optical transparency. This work highlights the strong potential of LuYAGG:Tb³⁺ as a promising candidate for the next-generation scintillator materials used in medical imaging, security scanning, and high-energy physics applications. Full article

Background/Objectives: This research presents a novel analytical method for breast tumor characterization and tissue classification by leveraging intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) combined with hyperspectral imaging techniques and deep learning. Traditionally, dynamic contrast-enhanced MRI (DCE-MRI) is employed for breast tumor diagnosis, but it involves gadolinium-based contrast agents, which carry potential health risks. IVIM imaging extends conventional diffusion-weighted imaging (DWI) by explicitly separating the signal decay into components representing true molecular diffusion ($D$) and microcirculation of capillary blood (pseudo-diffusion or $D*$). This separation allows for a more comprehensive, non-invasive assessment of tissue characteristics without the need for contrast agents, thereby offering a safer alternative for breast cancer diagnosis. The primary purpose of this study was to evaluate different methods for breast tumor characterization using IVIM-DWI data treated as hyperspectral image stacks. Dice similarity coefficients and Jaccard indices were specifically used to evaluate the spatial segmentation accuracy of tumor boundaries, confirmed by experienced physicians on dynamic contrast-enhanced MRI (DCE-MRI), emphasizing detailed tumor characterization rather than binary diagnosis of cancer. Methods: The data source for this study consisted of breast MRI scans obtained from 22 patients diagnosed with mass-type breast cancer, resulting in 22 distinct mass tumor cases analyzed. MR images were acquired using a 3T MRI system (Discovery MR750 3.0 Tesla, GE Healthcare, Chicago, IL, USA) with axial IVIM sequences and a bipolar pulsed gradient spin echo sequence. Multiple b-values ranging from 0 to 2500 s/mm² were utilized, specifically thirteen original b-values (0, 15, 30, 45, 60, 100, 200, 400, 600, 1000, 1500, 2000, and 2500 s/mm²), with the last four b-value images replicated once for a total of 17 bands used in the analysis. The methodology involved several steps: acquisition of multi-b-value IVIM-DWI images, image pre-processing, including correction for motion and intensity inhomogeneity, treating the multi-b-value data as hyperspectral image stacks, applying hyperspectral techniques like band expansion, and evaluating three tumor detection methods: kernel-based constrained energy minimization (KCEM), iterative KCEM (I-KCEM), and deep neural networks (DNNs). The comparisons were assessed by evaluating the similarity of the detection results from each method to ground truth tumor areas, which were manually drawn on DCE-MRI images and confirmed by experienced physicians. Similarity was quantitatively measured using the Dice similarity coefficient and the Jaccard index. Additionally, the performance of the detectors was evaluated using 3D-ROC analysis and its derived criteria (AUC_OD, AUC_TD, AUC_BS, AUC_TD−BS, AUC_ODP, AUC_SNPR). Results: The findings objectively demonstrated that the DNN method achieved superior performance in breast tumor detection compared to KCEM and I-KCEM. Specifically, the DNN yielded a Dice similarity coefficient of 86.56% and a Jaccard index of 76.30%, whereas KCEM achieved 78.49% (Dice) and 64.60% (Jaccard), and I-KCEM achieved 78.55% (Dice) and 61.37% (Jaccard). Evaluation using 3D-ROC analysis also indicated that the DNN was the best detector based on metrics like target detection rate and overall effectiveness. The DNN model further exhibited the capability to identify tumor heterogeneity, differentiating high- and low-cellularity regions. Quantitative parameters, including apparent diffusion coefficient ($ADC$), pure diffusion coefficient ($D$), pseudo-diffusion coefficient ($D*$), and perfusion fraction ($PF$), were calculated and analyzed, providing insights into the diffusion characteristics of different breast tissues. Analysis of signal intensity decay curves generated from these parameters further illustrated distinct diffusion patterns and confirmed that high cellularity tumor regions showed greater water molecule confinement compared to low cellularity regions. Conclusions: This study highlights the potential of combining IVIM-DWI, hyperspectral imaging techniques, and deep learning as a robust, safe, and effective non-invasive diagnostic tool for breast cancer, offering a valuable alternative to contrast-enhanced methods by providing detailed information about tissue microstructure and heterogeneity without the need for contrast agents. Full article

In this paper, we propose a deep learning model based on dual-branch learning with a hybrid attention mechanism for meeting challenges in the underutilization of features in ophthalmic image diagnosis and the limited generalization ability of traditional single modal deep learning models when using imbalanced data. Firstly, a dual-branch architecture layout is designed, in which the left and right branches use residual blocks to deal with the features of a 2D image and 3D volume, respectively. Secondly, a frequency domain transform-driven hybrid attention module is innovated, which consists of frequency domain attention, spatial attention, and channel attention, respectively, to solve the problem of inefficiency in network feature extraction. Finally, through a multi-scale grouped attention fusion mechanism, the local details and global structure information of the bimodal modalities are integrated, which solves the problem of the inefficiency of fusion caused by the heterogeneity of modal features. The experimental results show that the accuracy of MOD-Net improved by 1.66% and 1.14% over GeCoM-Net and ViT-2SPN, respectively. It can be concluded that the model effectively mines the deep correlation features of multimodal images through the hybrid attention mechanism, which provides a new paradigm for the intelligent diagnosis of ophthalmic diseases. Full article

Two-dimensional speckle-tracking echocardiography (2D-STE) is an advanced imaging technique that offers quantitative insights into myocardial function by analyzing the motion of speckles created during ultrasound–tissue interactions. This study aims to evaluate the reliability of 2D-STE by examining the impact of key technical parameters on global longitudinal strain (GLS) measurement accuracy and comparing two speckle-tracking analysis methods provided by GE Healthcare: quantitative analysis of the 2D strain (2D strain) and automated function imaging (AFI). The prospective study consisted of two cohorts. In the first cohort, including 16 healthy dogs, the influence of frame rate, heart rate variation, zoom, transducer frequency, and image foreshortening on speckle-tracking values was assessed. In the second cohort, which included 10 healthy dogs, 2D-STE parameters were obtained with the 2D strain and AFI to assess agreement between the methods and observer variability. Our findings indicate that foreshortening (p < 0.01, Cohen’s d: 0.52, CI: −17.81 to −24.83) and heart rate variability (p = 0.02, Cohen’s d: 0.72, CI: −18.07 to −26.23) significantly affect speckle-tracking measurements. While zoom, frame rate, and frequency did not show a significant impact. Additionally, while the 2D strain and AFI exhibited a strong correlation, a significant systematic bias was identified, with AFI underestimating strain values compared to the 2D strain. Intra- and inter-observer coefficients of variation (CV) were below 9% for both methods, supporting their reliability. These findings emphasize the need to optimize image acquisition and selection criteria, which enhances the accuracy and reliability of the speckle-tracking analysis. Full article

Radiation therapy is a standard of care treatment for patients with glioblastoma. However, patients’ survival rate is dismal, with nearly all patients experiencing disease progression after treatment. Enriched iron content associated with increased transferrin receptor (TfR) expression is an indicator of poor glioblastoma patient outcomes; however, the underlying contributions to tumor progression remain elusive. The goal of this present study is to understand how iron metabolism in glioma contributes to radiation-induced glioblastoma cell motility. U251 and a doxycycline-inducible ferritin heavy chain overexpressing U251 (U251 FtH⁺) cell line were used. For in vitro studies, cells were irradiated with 2 Gy using a ³⁷Cs source, and after 72 h, atomic force microscopy (AFM) nanoindentation was employed to assess changes in cell stiffness following irradiation. Cell motility was studied using temporal confocal microscopy. For in vivo studies, U251 cells were grown in the rear flanks of female nude athymic mice, and the tumor was irradiated with five fractions of 2 Gy (10 Gy). The tumors were then imaged using a GE 7T small animal MRI to assess changes in T2* MRI, and colorimetric analysis of labile iron was performed using ferrozine. Following irradiation, a biomechanical shift characterized by decreased cell stiffness along with increased cell motility occurred in U251 cells, which corresponded to increased TfR expression. FtH overexpression completely reversed the enhanced cell motility following irradiation. Irradiation of U251 tumors induced the same iron metabolic shift. Interestingly, the change in labile iron in U251 tumors corresponded with an increase in T2* relaxation times, suggesting that T2* mapping may serve as a surrogate marker for assessing radiation-induced changes in iron metabolism. Full article

The manuscript introduces an innovative framework for expiration date recognition aimed at improving accessibility for visually impaired individuals. The study underscores the pivotal role of convolutional neural networks (CNNs) in addressing complex challenges, such as variations in typography and image degradation. The system attained an F1-score of 0.9303 for the detection task and an accuracy of 97.06% for the recognition model, with a total inference time of 63 milliseconds on a single GeForce GTX 1080 GPU. A comparative analysis of quantized models—FP32, FP16, and INT8—emphasizes the trade-offs in inference speed, energy efficiency, and accuracy on mobile devices. The experimental results indicate that the FP16 model operating in CPU mode achieves an optimal equilibrium between precision and energy consumption, underscoring its suitability for resource-constrained environments. Full article

The MIPI (Mobile Industry Processor Interface) Alliance provides a security framework for in-vehicle network connections between sensors and processing electronic control units (ECUs). One approach within this framework is data integrity verification for sensors with limited hardware resources. In this paper, the security risks associated with image sensor data are described. Adversarial examples (AEs) targeting the MIPI interface can induce misclassification, making image data integrity verification essential. A CMOS image sensor with a message authentication code (CIS-MAC) is then proposed as a defense mechanism starting from the image sensor to protect image data from malicious manipulations, such as AE attacks. Evaluation results of the physically unclonable function (PUF) response and random number, which are utilized for generating the cryptographic key and MAC tag, are presented using a 2 Mpixel CMOS image sensor. The area of the CIS-MAC circuit is estimated based on a Verilog HDL design and synthesis using a 0.18 μm CMOS process. Various hash topologies are evaluated to select a hash function suitable for key generation and MAC tag generation within the CMOS image sensor. The estimated area of the CIS-MAC circuit is 67 kGE and $0.86{\mathrm{mm}}^2$, demonstrating feasibility for implementation in a CMOS image sensor typically fabricated using analog process technology. Full article

Printed circuit boards (PCBs) are an indispensable part of electronic products, and their quality is crucial to the operational integrity and functional reliability of these products. Currently, existing PCB defect detection models are beset with issues such as excessive model size and parameter complexity, rendering them ill-equipped to meet the requirements for lightweight deployment on mobile devices. To address this challenge, this paper proposes a lightweight detection model, GESC-YOLO, developed through modifications to the YOLOv8n architecture. First, a new lightweight module, C2f-GE, is designed to replace the C2f module of the backbone network, which effectively reduces the computational parameters, and at the same time increases the number of channels of the feature map to enhance the feature extraction capability of the model. Second, the neck network employs the lightweight hybrid convolution GSConv. By integrating it with the VoV-GSCSP module, the Slim-neck structure is constructed. This approach not only guarantees detection precision but also enables model lightweighting and a reduction in the number of parameters. Finally, the coordinate attention is introduced into the neck network to decompose the channel attention and aggregate the features, which can effectively retain the spatial information and thus improve the detection and localization accuracy of tiny defects (defect area less than 1% of total image area) in PCB defect images. Experimental results demonstrate that, in contrast to the original YOLOv8n model, the GESC-YOLO algorithm boosts the mean Average Precision (mAP) of PCB surface defects by 0.4%, reaching 99%. Simultaneously, the model size is reduced by 25.4%, the parameter count is cut down by 28.6%, and the computational resource consumption is reduced by 26.8%. This successfully achieves the harmonization of detection precision and model lightweighting. Full article

Herbal medicines have significant industrial value in East Asia. Zizyphus jujuba Mill. var. spinosa, used in Korea for treating insomnia, is often confused with Zizyphus mauritiana Lam., which has unverified medicinal properties yet is sold at premium prices. This misclassification undermines consumer trust and poses health risks. This study proposes a deep learning-based classification system trained on RGB-GE data, combining grayscale and edge-detected images with RGB inputs to enhance feature extraction while reducing color-dependency. Our method achieves superior generalization while maintaining cost-effectiveness. The system incorporates Grad-CAM for model interpretation and reliability. By comparing accuracy and speed across basicCNN, DenseNet, and InceptionV3 models, we identified an optimal solution for on-site herbal medicine classification, achieving 98.36% accuracy with basicCNN, ensuring reliable quality control. Full article