Search Results (293)

Background: Pathological complete response (pCR) serves as a prognostic surrogate endpoint for long-term clinical outcomes in breast cancer patients receiving neoadjuvant systemic therapy (NAST). This study aims to develop and evaluate machine learning-based biomarkers for predicting pCR and recurrence-free survival (RFS). Methods: This retrospective monocentric study included 235 women (mean age 46 ± 11 years) with non-metastatic breast cancer treated with NAST. We developed various machine learning models using clinical features (age, genetic mutations, TNM stage, hormonal receptor expression, HER2 status, and histological grade), along with morphological features (size, T2 signal, and surrounding edema) and radiomics data extracted from pre-treatment MRI. Patients were divided into training and test groups with different MRI models. A customized machine learning pipeline was implemented to handle these diverse data types, consisting of feature selection and classification components. Results: The models demonstrated superior prediction ability using radiomics features, with the best model achieving an AUC of 0.72. Subgroup analysis revealed optimal performance in triple-negative breast cancer (AUC of 0.80) and HER2-positive subgroups (AUC of 0.65). Conclusion: Machine learning models incorporating clinical, qualitative, and radiomics data from pre-treatment MRI can effectively predict pCR in breast cancer patients receiving NAST, particularly among triple-negative and HER2-positive breast cancer subgroups. Full article

Accurate detection of fractures in X-ray images is important to initiate appropriate medical treatment in time—in this study, an advanced combined attention CNN model with multiple attention mechanisms was developed to improve fracture detection by deeply representing features. Specifically, our model incorporates squeeze blocks and convolutional block attention module (CBAM) blocks to improve the model’s ability to focus on relevant features in X-ray images. Using computed tomography X-ray images, this study assesses the diagnostic efficacy of the artificial intelligence (AI) model before and after optimization and compares its performance in detecting fractures or not. The training and evaluation dataset consists of fractured and non-fractured X-rays from various anatomical locations, including the hips, knees, lumbar region, lower limb, and upper limb. This gives an extremely high training accuracy of 99.98 and a validation accuracy 96.72. The attention-based CNN thus showcases its role in medical image analysis. This aspect further complements a point we highlighted through our research to establish the role of attention in CNN architecture-based models to achieve the desired score for fracture in a medical image, allowing the model to generalize. This study represents the first steps to improve fracture detection automatically. It also brings solid support to doctors addressing the continued time to examination, which also increases accuracy in diagnosing fractures, improving patients’ outcomes significantly. Full article

Background: Colorectal cancer (CRC) is a major contributor to cancer mortality on a global scale, with polyps being critical precursors. The accurate classification of colorectal polyps (CRPs) from colonoscopy images is essential for the timely diagnosis and treatment of CRC. Method: This research proposes a novel hybrid model, CRP-ViT, integrating ResNet50 with Vision Transformers (ViTs) to enhance feature extraction and improve classification performance. This study conducted a comprehensive comparison of the CRP-ViT model against traditional convolutional neural networks (CNNs) and emerging quantum neural networks (QNNs). Experiments were conducted for binary classification to predict the presence of polyps and multi-classification to predict specific polyp types (hyperplastic, adenomatous, and serrated). Results: The results demonstrate that CRP_QNN-ViT achieved superior classification performance while maintaining computational efficiency. CRP_QNN-ViT achieved an accuracy of 98.18% for training and 97.73% for validation on binary classification and 98.13% during training and 97.92% for validation on multi-classification tasks. In addition to the key metrics, computational parameters were compared, where CRP_QNN-ViT excelled in computational time. Conclusions: This comparative analysis reveals the potential of integrating quantum computing into medical image analysis and underscores the effectiveness of transformer-based architectures for CRP classification. Full article

Sweet sensing is a fundamental sensory experience that plays a critical role not only in food preference, reward and dietary behaviour but also in glucose metabolism. Sweet taste receptors (STRs), composed of a heterodimer of taste receptor type 1 member 2 (T1R2) and member 3 (T1R3), are now recognised as being widely distributed throughout the body, including the gastrointestinal tract. Preclinical studies suggest these receptors are central to nutrient and glucose sensing, detecting energy availability and triggering metabolic and behavioural responses to maintain energy balance. Both internal and external factors tightly regulate their signalling pathways, and dysfunction within these systems may contribute to the development of metabolic disorders such as obesity and type 2 diabetes (T2D). Functional magnetic resonance imaging (fMRI) has provided valuable insights into the neural mechanisms underlying sweet sensing by mapping brain responses to both lingual/oral and gastrointestinal sweet stimuli. This review highlights key findings from fMRI studies and explores how these neural responses are modulated by metabolic state and individual characteristics such as body mass index, habitual intake and metabolic health. By integrating current evidence, this review advances our understanding of the complex interplay between sweet sensing, brain responses, and health and identifies key gaps and directions for future research in nutritional neuroscience. Full article

Prostate cancer is one of the most prevalent malignancies in men, posing a significant public health challenge due to its high incidence and long-term treatment-related toxicities. Long-lived patients often experience prolonged side effects that can severely diminish their quality of life. Despite advancements in radiotherapy techniques like IMRT and VMAT, some patients still experience acute and late side effects. Current treatment protocols do not account for individual variability in normal-tissue radiosensitivity, highlighting the need for predictive tools and a personalised treatment approach. Genetic factors and molecular regulators like microRNAs (miRNAs) contribute to these variations by influencing DNA repair, inflammation, and apoptosis. This review explores potential biomarkers of radiotoxicity, focusing on immune-related factors such as IL-6 and TGF-β1, SNPs influencing radiosensitivity, miRNAs involved in radiation responses, and functional assays including the radiation-induced lymphocyte apoptosis (RILA) test. These approaches offer promising tools for identifying radiosensitive patients and enabling risk-adapted radiotherapy. Full article

The aim of our study was to test the application of a new vision training device, the EYE ROLL, for home-based eye movement training in athletes. Sixty-seven participants were randomly divided into three groups: a control group (no training); an eye movement training group with no device; and a group using the new EYE ROLL device. The results of 51 participants were used for statistical analyses after a 4-week period. Before and after the 4-week period, participants underwent the same assessment procedures: a comprehensive vision examination and saccadic eye movement recording. Before training, for both 10° and 5° stimuli, all subjects showed statistically significantly larger and faster rightward saccades compared to leftward saccades. After four weeks, the control group showed increased horizontal saccadic asymmetry and a decrease in leftward saccade amplitude. However, both velocities showed asymmetry in both visits. There were larger changes in saccadic parameters for leftward saccades, but no clear changes in saccadic response asymmetry after training. There were no consistent differences between the training groups. The EYE ROLL is a novel device that may serve as a substitute training tool for saccadic enhancement and may improve the symmetry of horizontal saccadic movements after four weeks of home-based training. Full article

Backgrounds: Approximately 18 million individuals were diagnosed with cancer in 2018. The rate is predicted to exceed 22 million by 2030. Radiotherapy is an essential part of cancer therapy, with well documented local and systemic side effects, including oxidative stress and apoptosis. Kidney tissues are also exposed to the deleterious effects of radiotherapy, resulting in acute or chronic kidney function impairment. This study compared the effects of the potent selective α2-adrenoreceptor agonist dexmedetomidine and amifostine on oxidative stress and apoptosis in kidney damage induced by x-irradiation in rats. Methods: Forty Sprague Dawley rats were assigned into five groups: control, x-irradiation, x-irradiation + amifostine, x-irradiation + dexmedetomidine 100 µg/kg, and X-ray irradiation + dexmedetomidine 200 µg/kg. Results: Necrotic tubules and degenerative Bowman’s capsules were present in the x-irradiation group. An increase was determined in malondialdehyde (MDA), Cleaved Caspase-3, and 8-OHdG levels compared to the control group (p ≤ 0.05). In contrast, there was a decrease in necrotic tubules, degenerative Bowman’s capsules, and the levels of MDA, Cleaved Caspase-3, and 8-OHdG in the amifostine and dexmedetomidine 100 µg/kg and 200 µg/kg treatment groups (p ≤ 0.05). Conclusions: Alpha 2 adrenergic receptor agonists exhibit protective effects against kidney injury induced in association with x-irradiation by reducing oxidative stress and apoptosis. Full article

Background: In addition to behavioral and biochemical abnormalities, a parafunction associated with temporomandibular joint disorders (TMDs) resulted in stress-induced depression in rats. Exploring how chronic stress influences molar wear in rodents provides insights into the understanding of depression, TMD, and oral health. This study aimed to conduct a three-dimensional (3D) analysis of first molar wear in an animal model of depression by comparing molar attrition and cusp variation between stressed male rats and control groups. Methods: After obtaining a validated model of depression in male rats, we obtained 3D scans of lower molars to analyze wear patterns. The 3D analysis was applied to quantify cusps’ volume and the difference in first molar cusp morphological structure. The data were then compared to identify significant morphological differences between groups side by side. Results: The analysis revealed the reduction of cusps’ volume in the depression groups. Rats exposed to depression exhibited significantly greater occlusal table wear than their control counterparts (p < 0.05). Conclusions: As dentistry moves towards greater digital imaging, understanding the impact of psychological factors on TMD becomes increasingly necessary. This study shows that stress-induced depression in rats can result in significant tooth wear, as investigated using a 3D dental scanner. Full article

Nuclear medicine (NM) procedures are performed using unsealed radioactive sources that are administered to patients, resulting in both internal and external exposure for patients and staff alike. Optimization is mainly concerned with ensuring the use of the lowest sufficient level of radiation to perform a procedure while maintaining adequate image quality. Diagnostic reference levels (DRLs) have been proven effective in aiding optimization in clinical practice. This dose review aims to establish an inclusive DRL system for the common adult NM procedures performed at Dubai Health. Our defined DRLs will focus on both the administered radiopharmaceuticals and the radiation dose metrics derived from hybrid computed tomography (CT). Dose surveys for 1439 adult nuclear medicine procedures performed over twelve months were collected and retrospectively analyzed. DRLs were obtained for a total of eight scintigraphy procedures, four hybrid positron emission tomography procedures with CT (denoted PET/CT), and five target sites for CT hybrid single-photon emission tomography with CT (denoted as SPECT/CT). Our derived DRLs for the scintigraphy, hybrid SPECT/CT and PET/CT procedures are within the reported national DRLs, except for the CT dose of the hybrid SPECT/CT for the neck, abdomen and chest/abdomen sites and the ¹⁸F PSMA administered activity. A fixed activity dose was administered for a scintigraphy procedure that is weight dependent. This patient dose review serves as a foundational effort aiming to optimize radiation safety and standardize diagnostic practices in NM. Further research is needed to enhance adherence to safety benchmarks. Full article

Meningiomas arise from the meningeal layers covering the central nervous system structures. Although most are benign, meningiomas can still cause neurological morbidity due to the mass effect and compression of the surrounding parenchyma. The prognosis also depends on several factors such as growth pattern or location. Morphological imaging approaches, such as MRI and CT, that emphasize intracranial calcifications, vascular patterns, or invasion of major vessels act as the basis of the diagnosis; PET/CT imaging is a valuable diagnostic tool for assessing somatostatin receptor activity in tumors. It enables the visualization and quantification of somatostatin receptor expression, providing insights into tumor biology, receptor status, and potential therapeutic targets. Aside from radiosurgery and neurosurgical intervention, peptide receptor radionuclide therapy (PRRT) has also shown promising results. Somatostatin receptors 1 and 2 are nearly universally expressed in meningioma tissue. This characteristic is increasingly exploited to identify patients eligible for adjuvant therapy using DOTA-conjugated somatostatin receptor-targeting peptides PET. In the treatment of relapsed/refractory meningiomas, PRRT is increasingly considered a safe and effective therapeutic option. It is often supported by artificial intelligence strategies for dose optimization and side-effect monitoring. The objective of this study is to evaluate the safety and benefits of these strategies based on the latest findings. Full article

Functional endoscopic sinus Surgery (FESS) is a form of safe and effective management for chronic rhinosinusitis. Nevertheless, although FESS is minimally invasive, it poses a risk of rare orbital complications. This study aims to investigate the variations in the medial maxillary wall relative to the medial orbital wall, as depicted on computed tomography (CT) scans. We retrospectively included CT scans of the sinuses between November 2022 and April 2023. To maintain consistency, we used the coronal image that delineated the anterior ethmoidal foramen. The attachment site of the inferior turbinate to the medial maxillary wall was categorized into three classes according to its position relative to the inferomedial orbital strut. Class I indicates that the site of attachment is located within 2 mm, either medially or laterally. Class II indicates that it has been medially displaced by more than 2 mm, whereas Class III indicates that it has been laterally displaced by more than 2 mm. We enrolled 183 patients, yielding a total of 363 sides. Classes I, II, and III account for 55.4%, 41.3%, and 3.3% of the cases, respectively. A significant correlation exists between the classification and the dimensions and volume of the maxillary sinus (p < 0.001). The logistic regression model indicates a significant negative correlation between the width of the maxillary sinus and risk classification (p < 0.001), implying a protective effect with increasing width. Knowledge of the variations in the medial wall of the maxillary sinus relative to the medial orbital wall is essential for guidance toward the optimal endoscopic approach, and it demonstrates relevance to risk stratification. Full article

Background: Down syndrome (DS) is one of the most prevalent chromosomal abnormalities affecting global healthcare. Recent advances in artificial intelligence (AI) and machine learning (ML) have enhanced DS diagnostic accuracy. However, there is a lack of thorough evaluations analyzing the overall impact and effectiveness of AI-based DS diagnostic approaches. Objectives: This review intends to identify methodologies and technologies used in AI-driven DS diagnostics. It evaluates the performance of AI models in terms of standard evaluation metrics, highlighting their strengths and limitations. Methodology: In order to ensure transparency and rigor, the authors followed the preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines. They extracted 1175 articles from major academic databases. By leveraging inclusion and exclusion criteria, a final set of 25 articles was selected. Outcomes: The findings revealed significant advancements in AI-powered DS diagnostics across diverse data modalities. The modalities, including facial images, ultrasound scans, and genetic data, demonstrated strong potential for early DS diagnosis. Despite these advancements, this review outlined the limitations of AI approaches. Small and imbalanced datasets reduce the generalizability of the AI models. The authors present actionable strategies to enhance the clinical adoptions of these models. Full article

Brain tumor diagnosis is a complex task due to the intricate anatomy of the brain and the heterogeneity of tumors. While magnetic resonance imaging (MRI) is commonly used for brain imaging, accurately detecting brain tumors remains challenging. This study aims to enhance brain tumor classification via deep transfer learning architectures using fine-tuned transfer learning, an advanced approach within artificial intelligence. Deep learning methods facilitate the analysis of high-dimensional MRI data, automating the feature extraction process crucial for precise diagnoses. In this research, several transfer learning models, including InceptionResNetV2, VGG19, Xception, and MobileNetV2, were employed to improve the accuracy of tumor detection. The dataset, sourced from Kaggle, contains tumor and non-tumor images. To mitigate class imbalance, image augmentation techniques were applied. The models were pre-trained on extensive datasets and fine-tuned to recognize specific features in MRI brain images, allowing for improved classification of tumor versus non-tumor images. The experimental results show that the Xception model outperformed other architectures, achieving an accuracy of 96.11%. This result underscores its capability in high-precision brain tumor detection. The study concludes that fine-tuned deep transfer learning architectures, particularly Xception, significantly improve the accuracy and efficiency of brain tumor diagnosis. These findings demonstrate the potential of using advanced AI models to support clinical decision making, leading to more reliable diagnoses and improved patient outcomes. Full article

This research investigated the unstudied impact, in 416 cases of stone-induced hydronephrosis detected radiographically in 369 patients, of stone size on the stone’s location in the urinary tract and on the hydronephrosis grade. Most (62.5%) of the hydronephrosis cases were Grade 2; 17.1%, Grade 3; 10.6%, Grade 4; and 9.9%, Grade 1. The mean size of the stones reported in the renal pelvis, pelviureteric junction (PUJ), upper ureter (UU), midureter (MU), lower ureter (LU), and vesicoureteral junction (VUJ) that caused hydronephrosis were 23.03 ± 8.97 mm, 15.56 ± 6.59 mm, 12.91 ± 6.02 mm, 11.05 ± 4.27 mm, 10.41 ± 4.80 mm, and 6.73 ± 3.28 mm, respectively. The mean size of Grade 1-causing stones was 16.63 mm; Grade 2, 11.49 mm; Grade 3, 15.69 mm; and Grade 4, 21.23 mm. The mean stone size significantly decreased from the renal pelvis, through the PUJ, UU, MU, and LU, and down to the VUJ and increased as the hydronephrosis grade increased from Grade 2 to Grade 4. In conclusion, large-size stones were predominantly located in the renal pelvis and PUJ, with few located in the lower ureter, and no large stones reached the VUJ. Small-size stones were mostly located in the VUJ, with only one stone in the PUJ, and no small-size stones were present in the renal pelvis. Large-size stones caused severe hydronephrosis, and small-size stones caused grade 2 hydronephrosis. Increases in stone size decreased its passage rate in the ureter and increased the chance of causing high-grade hydronephrosis. These results alert urologists to adopt faster therapeutic procedures for larger stone sizes to reduce renal damage caused by obstructive uropathy. Full article