Current Issue : July-September Volume : 2025 Issue Number : 3 Articles : 5 Articles
Cancer, in general, and skin cancer, in particular, is a genetic disease caused by cell division malfunction. It represents a major public health problem due to the large number of deaths caused by it. This is because it is often detected at very advanced stages. Traditional detection methods often involve visual examination by dermatologists. However, these methods are generally onesided and inaccurate in some cases. Hence, there is an urgent need to develop effective and intelligent methods for early diagnosis to improve skin cancer treatment. This paper presents a solution based on Deep Learning methods, more specifically, on a pre-trained convolutional neural network (CNN) EfficientNet- B0, which we refined by performing an unfreezing technique so that the model could capture the specific features of our skin cancer detection dataset. As an optimizer for our model, we used stochastic gradient descent with momentum with a learning rate of 0.001. This method was implemented in the publicly available ISIC-2019 dermoscopic image database, in which we performed image resizing and cropping, morphological closure, and Gaussian filter application preprocessing. We then proceeded to rebalance the results, followed by augmentation of data. We obtained a classification accuracy of 88%....
Introduction: Stroke is defined as the rapid development of localized or global clinical signs of cerebral dysfunction with symptoms lasting more than 24 hours that can lead to death without any apparent causes other than a vascular origin. The ischemic or hemorrhagic nature of a stroke (stroke) can only be determined by computed tomography (CT) and/or magnetic resonance imaging. The aim of our work was to study the CT aspects of strokes in the radiology and medical imaging department of Fousseyni DAOU Hospital in Kayes. Methodology: This was a descriptive study with prospective collection in the Radiology and Medical Imaging Department of Fousseyni Daou Hospital in Kayes over a period of 12 months concerning 159 cases of strokes confirmed by CT scan. The variables analyzed were sociodemographic, clinical, and CT data. Results: We collected 159 cases out of 628 patients referred to the radiology and medical imaging department for a brain CT scan during the study period, representing a frequency of 25.32% of cases. In our series, men were predominant in 61.63% of cases, with a sex ratio of 1.61. The average age was 65.19 years in 34.59% of cases, with extremes of 31 and 87 years. Arteriopulmonary hypertension was the main risk factor, with 57.23%. Right hemiplegia represented 40.88% of physical deficits. Headaches were the main functional sign, representing 39.62% of cases. We noted the predominance of ischemic lesions, which represented 73.33% of patients. Conclusion: Strokes are a major public health problem. Cranioencephalic CT scans have highlighted the different types of strokes, with a predominance of ischemic strokes and the different locations. Cerebral CT scans remain the first-line examination for making the diagnosis and determining the nature of the stroke and the associated signs of severity. They improve therapeutic management....
Super-resolution (SR) techniques have gained traction in biomedical imaging for their ability to enhance image quality. However, it remains unclear whether these improvements translate into better performance in clinical tasks. In this study, we provide a comprehensive evaluation of state-of-the-art SR models—including CNN- and Transformer-based architectures—by assessing not only visual quality metrics (PSNR and SSIM) but also their downstream impact on segmentation and classification performance for lung CT scans. Using U-Net and ResNet architectures, we quantify how SR influences diagnostic tasks across different datasets, and we evaluate model generalization in cross-domain settings. Our findings show that advanced SR models such as SwinIR preserve diagnostic features effectively and, when appropriately applied, can enhance or maintain clinical performance even in low-resolution contexts. This work bridges the gap between image quality enhancement and practical clinical utility, providing actionable insights for integrating SR into real-world biomedical imaging workflows....
Background: Non-small cell lung cancer (NSCLC) has been the most common cancer globally in the recent decade. CT is the most common imaging modality for the initial diagnosis of NSCLC. The gold standard for definitive diagnosis is the histological evaluation of a biopsy or surgical sample, which usually requires a long processing time for the confirmation of diagnosis. This study aims to develop artificial intelligence models to predict overall staging based on patient demographics and radiomics retrieved from the initial CT images, so as to prioritize later-stage patients for histology evaluation to facilitate cancer diagnosis. Method: Two cohorts of NSCLC patient datasets were utilized for this study. The NSCLC-radiomics dataset from The Cancer Imaging Archive (TCIA) was divided into 70% for the training group and 30% for the internal testing group. Another cohort from a local hospital was collected for the an external testing group. Patient demographics and 107 radiomic features were retrieved from the gross tumor volume delineated by clinical oncologists on CT images. Artificial neural networks were used to build models for NSCLC overall staging (stage I, II, or III) prediction. Four traditional classifiers were also adopted to build models for comparison. Result: The proposed feedforward neural network (FFNN) model showed good performance in predicting overall staging with an accuracy of 88.84%, 76.67%, and 74.52% in overall accuracies in validation, internal cohort testing, and external cohort testing, respectively. The sensitivity and specificity are balanced in all the stages, with average precision and F1 score in each of the stages. Conclusion: The FFNN demonstrated good performance in overall staging prediction for NSCLC patients. It has the benefit of predicting multiple overall stages in a single model. The software required and the proposed model are simple. It can be operated on a general-purpose computer in the radiology department. The application will eventually be used as a prediction tool to prioritize the biopsy or surgery sample for histological analysis and molecular investigation, thus shortening the time for diagnosis by pathologists, which supports the triage of patients for further testing....
Background: Quantifying bone mineral density (BMD) is important to monitor and evaluate bone health status. When applied to chest and abdomen CT images, the BMD values of thoracic and lumbar spines can be determined. Objective: This study aims to analyze the distribution of lumbar BMD across different age groups and races, investigate the correlation between lumbar BMD and thoracic BMD, evaluate the feasibility of using chest CT scans for BMD assessment, and analyze numerical data to establish CT-based thresholds for diagnosing osteopenia and osteoporosis. Methodology: CT imaging data from 400 female subjects aged 20 - 80 years, acquired from 2010 to 2022, was studied retrospectively. We examined variations in lumbar BMD among females across different ages and races. The thoracic BMD values were measured relative to aortic blood and subcutaneous adipose tissue on chest CT images, while the lumbar BMD values were measured relative to psoas muscle and subcutaneous adipose tissue on abdominal CT images. Then, the correlation coefficient of BMD values between thoracic and lumbar was calculated. The receiver operating characteristic (ROC) of thoracic spine BMD values was studied with the lumbar spine BMD values considered the gold standard for osteoporosis diagnosis. Results: Thoracic BMD ranged from 60 - 350 mg/cm3, while lumbar BMD ranged from 60 - 350 mg/cm3 in most subjects. Between thoracic and lumbar BMD, a strong positive correlation (r = 0.95) was determined and the area under the ROC curve was 0.969. Lumbar BMD demonstrates age-related decline and has a strong positive correlation with thoracic BMD. Among the four major racial groups—White, Black, Hispanic, and Asian—Hispanics exhibited the highest lumbar BMD, while Whites showed the lowest. Conclusions: Lumbar BMD demonstrates age-related decline and strongly correlates with thoracic BMD. These findings support the use of CT as a valuable tool in screening for osteoporosis....
Loading....