استكشف المجموعة الواسعة من العناوين المتاحة.

Colorectal cancer (CRC) constitutes the third most commonly diagnosed cancer in males and the second in females. Precise histopathological classification of CRC tissue pathology is the cornerstone not only for diagnosis but also for patients’ management decision making. An automated system able to accurately classify different CRC tissue regions may increase diagnostic precision and alleviate clinical workload. However, tissue classification is a challenging task due to the variability in morphological and textural characteristics present in histopathology images. In this study, an artificial neural network was trained to classify between eight classes of CRC tissue image patches derived from a public dataset with 5000 CRC histopathology image tiles. A total of 532 multi-level pathomics features examined at different scales were extracted by visual descriptors such as local binary patterns, wavelet transforms and Gabor filters. An exhaustive evaluation involving a variety of wavelet families and parameters was performed in order to shed light on the impact of scale on pathomics based CRC tissue differentiation. Our model achieved a performance accuracy of 95.3% with tenfold cross validation demonstrating superior performance compared to 87.4% reported in recent studies. Furthermore, we experimentally showed that the first and the second levels of the wavelet approximations can be used without compromising classification performance.

Pulmonary large cell neuroendocrine carcinoma (P-LCNEC) is a rare, poorly differentiated, non-small cell malignancy within the spectrum of neuroendocrine tumors (NETs) of the lung. Despite sharing several similarities with small cell lung cancer (SCLC) in their clinical, immunohistopathological, genomic, and prognostic features, it is a distinct and biologically heterogeneous entity with challenging diagnostic and therapeutic requirements. Given the lack of prospective, randomized data to guide management, it is common practice to pursue thoracic surgery for resectable tumors according to the guidelines for non-small cell lung cancer (NSCLC) and implement systemic chemotherapy as early as at stage I, similar to the treatment of SCLC. However, important issues, such as the optimal timing and combination of therapeutic modalities, the most effective type of chemotherapy for advanced-stage disease, and the benefit from prophylactic cranial irradiation, remain debated. Accumulating evidence from retrospective, molecular profiling studies supports the existence of at least two P-LCNEC subtypes, most notably a SCLC-like and a NSCLC-like phenotype, which presumably underlie the observed differential sensitivity to platinum-based regimens and warrant further validation as predictive biomarkers of efficacy. Furthermore, several potentially actionable, driver molecular alterations have been identified, offering implications for personalized treatment approaches, including targeted therapies and immunotherapy. The current review discusses open questions on the diagnosis and management of P-LCNEC, as well as recent advances in its genomic and transcriptomic characterization that create promising therapeutic opportunities.

Potentially suspicious breast neoplasms could be masked by high tissue density, thus increasing the probability of a false‑negative diagnosis. Furthermore, differentiating breast tissue type enables patient pre‑screening stratification and risk assessment. In this study, we propose and evaluate advanced machine learning methodologies aiming at an objective and reliable method for breast density scoring from routine mammographic images. The proposed image analysis pipeline incorporates texture [Gabor filters and local binary pattern (LBP)] and gradient‑based features [histogram of oriented gradients (HOG) as well as speeded‑up robust features (SURF)]. Additionally, transfer learning approaches with ImageNet trained weights were also used for comparison, as well as a convolutional neural network (CNN). The proposed CNN model was fully trained on two open mammography datasets and was found to be the optimal performing methodology (AUC up to 87.3%). Thus, the findings of this study indicate that automated density scoring in mammograms can aid clinical diagnosis by introducing artificial intelligence‑powered decision‑support systems and contribute to the 'democratization' of healthcare by overcoming limitations, such as the geographic location of patients or the lack of expert radiologists.

Silicon carbide (SiC) MOSFETs tend to become one of the main switching elements in power electronics applications of medium- and high-power density. Usually, SiC MOSFETs are connected in parallel to increase power rating. Unfortunately, unequal current sharing between power devices occurs due to mismatches in the technical parameters between devices and the layout of the power circuit. This current imbalance causes different current stress upon power switches, raising concerns about power system reliability. For over a decade, various methods and techniques have been proposed for balancing the currents between parallel-connected SiC MOSFETs. However, most of these methods cannot be implemented unless the deviation between the technical parameters of semiconductor switches is known. This requirement increases the system cost because screening methods are extremely costly and time-consuming. In addition, most techniques aim at suppressing only the transient current imbalance. In this paper, a simple but innovative current balancing technique is proposed, without the need of screening any power device. The proposed technique consists of an open-loop system capable of balancing the currents between two parallel-connected SiC MOSFETs, with the aid of two active gate drivers and an FPGA, actively and independently of the cause. Experimental test results validate that the proposed open-loop method can successfully achieve suppression of current imbalance between parallel-connected SiC MOSFETs, proving its durability and validity level.

To address the current lack of dynamic susceptibility contrast magnetic resonance imaging (DSC–MRI)-based radiomics to predict isocitrate dehydrogenase (IDH) mutations in gliomas, we present a multicenter study that featured an independent exploratory set for radiomics model development and external validation using two independent cohorts. The maximum performance of the IDH mutation status prediction on the validation set had an accuracy of 0.544 (Cohen’s kappa: 0.145, F1-score: 0.415, area under the curve-AUC: 0.639, sensitivity: 0.733, specificity: 0.491), which significantly improved to an accuracy of 0.706 (Cohen’s kappa: 0.282, F1-score: 0.474, AUC: 0.667, sensitivity: 0.6, specificity: 0.736) when dynamic-based standardization of the images was performed prior to the radiomics. Model explainability using local interpretable model-agnostic explanations (LIME) and Shapley additive explanations (SHAP) revealed potential intuitive correlations between the IDH–wildtype increased heterogeneity and the texture complexity. These results strengthened our hypothesis that DSC–MRI radiogenomics in gliomas hold the potential to provide increased predictive performance from models that generalize well and provide understandable patterns between IDH mutation status and the extracted features toward enabling the clinical translation of radiogenomics in neuro-oncology.

In this study a four-wheel independent steering (4WIS) system for an electric vehicle (EV) steered by stepper motors is presented as a revolutionary real-time control technique employing neural networks in combination with fuzzy logic, where the use of the neural network greatly simplifies the computational process of fuzzy logic. The control of the four wheels is based on a variation of a Hopfield Neural Network (VHNN) method, in which the input is the error of each steering motor and the output is processed by a hyperbolic tangent function (HTF) feeding the fuzzy logic controller (FLC), which ultimately drives the stepper motor. The whole system consists of the four aforementioned blocks which work in sync and are inseparable from each other with the common goal of driving all the steering stepper motors at the same time. The novelty of this system is that each wheel monitors the condition of the others, so even in the case of the failure of one wheel, the vehicle does not veer off course. The results of the simulation show that the suggested control system is very resilient and workable at all angles and speeds.

The European Organisation for Research and Treatment of Cancer (EORTC) Quality of Life Questionnaire-Lung Cancer 13 (QLQ-LC13) assesses quality of life (QOL) in patients with lung cancer and was the first EORTC module developed for use in international clinical trials. Since its publication in 1994, major treatment advances with possible effects on QOL have occurred. These changes called for an update of the module and its international psychometric validation. We aimed to investigate the scale structure and psychometric properties of the updated lung cancer module, QLQ-LC29, in patients with lung cancer. This international, observational field study was done in 19 hospitals across 12 countries. Patients aged older than 18 years with a confirmed diagnosis of lung cancer and no other previous primary tumour, and who were mentally fit with sufficient language skills to understand and complete the questionnaire were included. Patients were asked during a hospital visit to fill in the paper versions of the core questionnaire EORTC QLQ-C30 plus QLQ-LC29, and investigators selected half of these patients to complete the questionnaire again 2–4 weeks later. Our primary aim was to assess the scale structure and psychometric properties of EORTC QLQ-LC29. We analysed scale structure using confirmatory factor analysis; reliability using Cronbach's α value (internal consistency) and intra-class coefficient (test–retest reliability); sensitivity using independent t tests stratified by Karnofsky performance status; and responsiveness to change over time by ANOVA. This study is registered with ClinicalTrials.gov, NCT02745691. Between April 12, 2016, and Sept 26, 2018, 523 patients with a confirmed diagnosis of either non-small-cell lung cancer (n=442) or small-cell lung cancer (n=81) were recruited. Confirmatory factor analysis provided a solution composed of five multi-item scales (coughing, shortness of breath, fear of progression, hair problems, and surgery-related symptoms) plus 15 single symptom or side-effect items: χ2=370·233, root mean square error of approximation=0·075, and comparative-fit index=0·901. Cronbach's α for internal consistencies of all multi-item scales were above the threshold of 0·70. Intra-class coefficients for test–retest reliabilities ranged between 0·82 and 0·97. Three (shortness of breath, fear of progression, and hair problems) of the five multi-item scales showed responsiveness to change over time (p values <0·05), as did nine of 15 single symptom items. Four (coughing, shortness of breath, fear of progression, and surgery-related symptoms) of the five multi-item scales and ten of the 15 single symptom items were sensitive to known group differences (ie, lower vs higher Karnofsky performance status). Results determined the psychometric properties of the updated lung cancer module, which is ready for use in international clinical studies. EORTC Quality of Life Group.

This study aimed to investigate which of the two frequently adopted perfusion models better describes the contrast enhanced ultrasound (CEUS) perfusion signal in order to produce meaningful imaging markers with the goal of developing a machine-learning model that can classify perfusion curves as benign or malignant in breast cancer data. Twenty-five patients with high suspicion of breast cancer were analyzed with exponentially modified Gaussian (EMG) and gamma variate functions (GVF). The adjusted R2 metric was the criterion for assessing model performance. Various classifiers were trained on the quantified perfusion curves in order to classify the curves as benign or malignant on a voxel basis. Sensitivity, specificity, geometric mean, and AUROC were the validation metrics. The best quantification model was EMG with an adjusted R2 of 0.60 ± 0.26 compared to 0.56 ± 0.25 for GVF. Logistic regression was the classifier with the highest performance (sensitivity, specificity, Gmean, and AUROC = 89.2 ± 10.7, 70.0 ± 18.5, 77.1 ± 8.6, and 91.0 ± 6.6, respectively). This classification method obtained similar results that are consistent with the current literature. Breast cancer patients can benefit from early detection and characterization prior to biopsy.

This study aims to develop an explainable radiomics-based model for the automatic assessment of image quality in breast cancer Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) data. A cohort of 280 images obtained from a public database was annotated by two clinical experts, resulting in 110 high-quality and 110 low-quality images. The proposed methodology involved the extraction of 819 radiomic features and 2 No-Reference image quality metrics per patient, using both the whole image and the background as regions of interest. Feature extraction was performed under two scenarios: (i) from a sample of 12 slices per patient, and (ii) from the middle slice of each patient. Following model training, a range of machine learning classifiers were applied with explainability assessed through SHapley Additive Explanations (SHAP). The best performance was achieved in the second scenario, where combining features from the whole image and background with a support vector machine classifier yielded sensitivity, specificity, accuracy, and AUC values of 85.51%, 80.01%, 82.76%, and 89.37%, respectively. This proposed model demonstrates potential for integration into clinical practice and may also serve as a valuable resource for large-scale repositories and subgroup analyses aimed at ensuring fairness and explainability.

Chronic hypokalemia is the main finding in patients with Gitelman's syndrome (GS). GS, a variant of Bartter's syndrome, is an autosomal recessive renal disorder characterized by hypokalemia, hypomagnesemia, metabolic alkalosis, and hypocalciuria. GS is caused by inactivating mutations in the thiazide-sensitive sodium-chloride cotransporter gene. It is also called the \"milder\" form of Bartter's syndrome, as patients with GS are usually diagnosed in adulthood during routine investigation. Our objective is to highlight the impact of correct distinction between the causes of hypokalemia on management and the need of long-term follow- up after the restoration of normokalemic status. Herein, we report an asymptomatic 40-year-old male, whose persistent hypokalemia was due to GS. The diagnosis was first established by laboratory tests, and he was treated with low-dose aldosterone antagonists (spironolactone), angiotensin-converting enzyme inhibitors, and potassium and magnesium supplements. Genetic testing confirmed the diagnosis of GS and revealed a rare mutation. We conclude that GS is a rare and real diagnostic and therapeutic challenge, for which a close collaboration between endocrinologists and nephrologists is mandatory, as also the thorough genetic investigation of the mutations associated with this syndrome.