Retinal disorders, such as diabetic retinopathy, glaucoma, macular edema, and vein occlusions, are significant contributors to global vision impairment. These conditions frequently remain symptomless until patients suffer severe vision deterioration, underscoring the critical importance of early diagnosis. Fundus images serve as a valuable resource for identifying the initial indicators of these ailments, particularly by examining various characteristics of retinal blood vessels, such as their length, width, tortuosity, and branching patterns. Traditionally, healthcare practitioners often rely on manual retinal vessel segmentation, a process that is both time-consuming and intricate, demanding specialized expertise. However, this approach poses a notable challenge since its precision and consistency heavily rely on the availability of highly skilled professionals. To surmount these challenges, there is an urgent demand for an automatic and efficient method for retinal vessel segmentation and classification employing computer vision techniques, which form the foundation of biomedical imaging. Numerous researchers have put forth techniques for blood vessel segmentation, broadly categorized into machine learning, filtering-based, and model-based methods. Machine learning methods categorize pixels as either vessels or non-vessels, employing classifiers trained on hand-annotated images. Subsequently, these techniques extract features using 7D feature vectors and apply neural network classification. Additional post-processing steps are used to bridge gaps and eliminate isolated pixels. On the other hand, filtering-based approaches employ morphological operators within morphological image processing, capitalizing on predefined shapes to filter out objects from the background. However, this technique often treats larger blood vessels as cohesive structures. Model-based methods leverage vessel models to identify retinal blood vessels, but they are sensitive to parameter selection, necessitating careful choices to simultaneously detect thin and large vessels effectively. Our proposed research endeavors to conduct a thorough and empirical evaluation of the effectiveness of automated segmentation and classification techniques for identifying eye-related diseases, particularly diabetic retinopathy and glaucoma. This evaluation will involve various retinal image datasets, including DRIVE, REVIEW, STARE, HRF, and DRION. The methodologies under consideration encompass machine learning, filtering-based, and model-based approaches, with performance assessment based on a range of metrics, including true positive rate (TPR), true negative rate (TNR), positive predictive value (PPV), negative predictive value (NPV), false discovery rate (FDR), Matthews's correlation coefficient (MCC), and accuracy (ACC). The primary objective of this research is to scrutinize, assess, and compare the design and performance of different segmentation and classification techniques, encompassing both supervised and unsupervised learning methods. To attain this objective, we will refine existing techniques and develop new ones, ensuring a more streamlined and computationally efficient approach.

Objective: Standardizing image acquisition protocols and image quality across cameras is an important need in imaging, in particular in multi-center clinical trials and the use of image analysis and machine learning algorithms. The objective of this study was to examine the effect of ordered subset expectation maximization (OSEM) reconstruction parameters on the quantitative image quality of cardiac perfusion SPECT images in different typical SPECT cameras and therefore assess the need to change the parameter values across cameras. Methods: The analysis was carried out by comparing the defect contrast-to-noise ratio (CNR) at 12 OSEM subset-iteration combinations. Eight frames were reconstructed using the SIMIND Monte Carlo Simulation package. An activity of 370 MBq (10mCi) and projection acquisition interval of 20 seconds per projection were used. Attenuation (AC) and scatter corrections (SC) were performed in this study for all images. Results: The 16-2 subset-iteration combination yielded the highest CNR and defect contrast values for both cameras. The difference between CNR values for two cameras was found to be close to 5%. Conclusions: Monte Carlo simulations can be useful to investigate how quantitative image quality behaves with respect to reconstruction parameters and correction algorithms in a controlled environment. In this study, the use of different camera brands did not seem to significantly affect the lesion detectability. Further simulations with more extended range of parameters and camera brands may be conducted in the future to quantify further the variability between different brands of cameras.

Osteoid osteoma (OO) is a benign osteoblastic tumor of bone that usually affects children and young adults. They are usually located on metaphysis or diaphysis of long bones. Their clinical, anamnesis and radiological findings are typical. Intra-articular OO however has different properties due to its placement within joints. Sclerosis around the lesion is either minimal or non-existent, but synovitis can be seen in the joint. For this reason, they are usually diagnosed later. In this case series, we diagnosed three cases (2 ankles and 1 hip joint) that were diagnosed with osteochondral lesions previously and had in chronic pain which did not respond to several treatments in different centers with intra-articular OO and treated them with radiofrequency ablation using computerized tomography. Knowing the radiological properties of intra-articular OO and being aware of this condition during differential diagnosis of joint pain cases will be useful to diagnose this rare pathology.

COVID was initially detected in Wuhan City, Hubei Province, People's Republic of China, in late 2019, as reported by researchers. Subsequently, it rapidly disseminated to numerous nations at the beginning of 2020, ultimately manifested as a pandemic with worldwide prevalence. Regarded as one of the most severe pandemics in documented human history, this outbreak resulted in deaths and infection over a quite millions of individuals globally. Due to its airborne nature, the coronavirus can be transmitted through actions such as coughing, sneezing, talking, and similar activities. Enclosed spaces lacking sufficient airflow are more likely to facilitate the spread of air borne diseases. Wearing a face mask that can provide protection against airborne pollutants, considered as Standard Operation Procedures (SOPS) for COVID-19. It is crucial to monitor the implementation of preventive measures both within and outside the building or workplace in order to prevent the transmission of COVID-19. The main objective of this project is to develop a face mask and social distance detector. You Only Learn One Representation (YOLOR) was implemented as a most advanced end-to-end target identification approach to develop the proposed system. An online available facemask dataset was utilized. The developed system can track individuals wearing masks in real time and can also identify and highlight persons with a rectangular box if their social distance is violated. This proposed interactive framework enables constant monitoring both internally and externally, thereby enhancing the capacity to identify offenders and ensure the safety of all individuals involved.

Inflammation of the lungs, called pneumonia, is a disease characterized by inflammation of the air sacs that interfere with the exchange of oxygen and carbon dioxide. It is caused by a variety of infectious organisms, including viruses, bacteria, fungus, and parasites. Pneumonia is more common in people who have pre-existing lung diseases or compromised immune systems, and it primarily affects small children and the elderly. Diagnosis of pneumonia can be difficult, especially when relying on medical imaging, because symptoms may not be immediately apparent. Convolutional neural networks (CNNs) have recently shown potential in medical imaging applications. A CNN-based deep learning model is being built as part of ongoing research to aid in the detection of pneumonia using chest X-ray images. The dataset used for training and evaluation includes images of people with normal lung conditions as well as photos of people with pneumonia. Various preprocessing procedures, such as data augmentation, normalization, and scaling, were used to improve the accuracy of pneumonia diagnosis and extract significant features. In this study, a framework for deep learning with four pre-trained CNN models—InceptionNet, ResNet, VGG16, and DenseNet—was used. To take use of its key advantages, transfer learning utilizing DenseNet was used. During training, the loss function was minimized using the Adam optimizer. The suggested approach seeks to improve early diagnosis and enable fast intervention for pneumonia cases by leveraging the advantages of several CNN models. The outcomes show that CNN-based deep learning models may successfully diagnose pneumonia in chest X-ray pictures.

This research underscores the importance of enhancing the early detection of diabetic retinopathy and glaucoma, two prominent culprits behind vision loss. Typically, retinal diseases lurk without symptoms until they inflict severe vision impairment, underscoring the critical need for early identification. The research is centered on the potential of leveraging fundus images, which offer invaluable insights by analyzing various attributes of retinal blood vessels, such as their length, width, tortuosity, and branching patterns. The conventional practice of manually segmenting retinal vessels by medical professionals is both intricate and time-consuming, demanding specialized expertise. This approach, reliant on pathologists, grapples with limitations related to scalability and accessibility. To surmount these challenges, the research introduces an automated solution employing computer vision. It conducts an evaluation of diverse retinal vessel segmentation and classification methods, including machine learning, filtering-based, and model-based techniques. Robust performance assessments, involving metrics like the true positive rate, true negative rate, and accuracy, facilitate a comprehensive comparison of these methodologies. The ultimate goal of this research is to create more efficient and accessible diagnostic tools, consequently enhancing the early detection of eye diseases through automated retinal vessel segmentation and classification. This endeavor combines the capabilities of computer vision and deep learning to pioneer new benchmarks in the realm of biomedical imaging, thereby addressing the pressing issues surrounding eye disease diagnosis.