Monkeypox Detection Using CNN with Transfer Learning.

Monkeypox disease is caused by a virus that causes lesions on the skin and has been observed on the African continent in the past years. The fatal consequences caused by virus infections after the COVID pandemic have caused fear and panic among the public. As a result of COVID reaching the pandemic dimension, the development and implementation of rapid detection methods have become important. In this context, our study aims to detect monkeypox disease in case of a possible pandemic through skin lesions with deep-learning methods in a fast and safe way. Deep-learning methods were supported with transfer learning tools and hyperparameter optimization was provided. In the CNN structure, a hybrid function learning model was developed by customizing the transfer learning model together with hyperparameters. Implemented on the custom model MobileNetV3-s, EfficientNetV2, ResNET50, Vgg19, DenseNet121, and Xception models. In our study, AUC, accuracy, recall, loss, and F1-score metrics were used for evaluation and comparison. The optimized hybrid MobileNetV3-s model achieved the best score, with an average F1-score of 0.98, AUC of 0.99, accuracy of 0.96, and recall of 0.97. In this study, convolutional neural networks were used in conjunction with optimization of hyperparameters and a customized hybrid function transfer learning model to achieve striking results when a custom CNN model was developed. The custom CNN model design we have proposed is proof of how successfully and quickly the deep learning methods can achieve results in classification and discrimination.

Multiple Brain Tumor Classification with Dense CNN Architecture Using Brain MRI Images.

Brain MR images are the most suitable method for detecting chronic nerve diseases such as brain tumors, strokes, dementia, and multiple sclerosis. They are also used as the most sensitive method in evaluating diseases of the pituitary gland, brain vessels, eye, and inner ear organs. Many medical image analysis methods based on deep learning techniques have been proposed for health monitoring and diagnosis from brain MRI images. CNNs (Convolutional Neural Networks) are a sub-branch of deep learning and are often used to analyze visual information. Common uses include image and video recognition, suggestive systems, image classification, medical image analysis, and natural language processing. In this study, a new modular deep learning model was created to retain the existing advantages of known transfer learning methods (DenseNet, VGG16, and basic CNN architectures) in the classification process of MR images and eliminate their disadvantages. Open-source brain tumor images taken from the Kaggle database were used. For the training of the model, two types of splitting were utilized. First, 80% of the MRI image dataset was used in the training phase and 20% in the testing phase. Secondly, 10-fold cross-validation was used. When the proposed deep learning model and other known transfer learning methods were tested on the same MRI dataset, an improvement in classification performance was obtained, but an increase in processing time was observed.

Evaluation of the Nexus X-ray rules in blunt thorax trauma.

BACKGROUND: There is still no agreed radiographic rule for the evaluation of blunt thoracic trauma. Emergency physicians want radiography according to their experience and examination findings. Various studies have been carried out on this subject and some of these studies have reached findings that can support the initial steps of the rules of radiography. One of them is the rule of Nexus thorax radiography rules. In this study, we aim to determine the accuracy of nexus thorax radiography rules. METHODS: Our study was a prospective cohort study performed in the emergency department of our University Hospital. In this study, 690 patients were evaluated. RESULTS: As a result of our study, we observed that patients were asked for more thoracic trauma because of chest pain, palpation tenderness in the thorax and sudden deceleration mechanism and pathology was found in approximately 25% of all imaging. The most common pathology we observed was rib fracture. Approximately 45% of the patients underwent thorax CT, and thorax CT was the most frequently requested for the detailed examination. When we evaluate the patients according to nexus thorax radiography rules, it was seen that the mechanism of sudden deceleration, intoxication and the disturbing, painful injury was more important than other parameters. The overall sensitivity and specificity of Nexus thorax radiographs were found to be 98% and 38%, respectively. CONCLUSION: In the evaluation of blunt thoracic trauma, the rules of nexus thorax radiography are considered useful concerning pathological detection.

Evaluation of an Image-based Automated Detection System in Detecting Ki67 Proliferation Index and Correlation with the Traditional Eye-Ball Method in Gastroenteropancreatic Neuroendocrine Tumors.

OBJECTIVE: To design an application which can calculate Ki67 and compare its results with the traditional method in gastroenteropancreatic (GEP)-neuroendocrine tumors (NETs). STUDY DESIGN: Descriptive analytical study. PLACE AND DURATION OF STUDY: Faculties of Medicine and Technology of Mugla Sitki Kocman University between January 2015 to January 2016. METHODOLOGY: A new analyser for detecting the exact percentage of positive cells in images captured from different slides retrospectively selected from hospital records was designed and the concordance with results given by an expert pathologist was compared. Demonstrative slides from randomly selected 50 patients diagnosed as GEP-NETs were stained with Ki67 antibody; and images were captured from the hotspots. The images were then uploaded to the application of the analyser designed for detecting the percentage of Ki67-stained cells. RESULTS: Twenty-seven male (54%) and 23 (46%) female patients with a mean age of 52.3 ±8.80 years were included. According to the pathologist with eye-ball method, 17 cases were grade 1 (34%), 21 cases were grade 2 (42%) and 12 (24%) cases were grade 3. By software, 8 cases were grade 1 (16%), 36 cases were grade 2 (72%) and 6 cases were grade 3 (12%). Statistical evaluation revealed a kappa value of 0.447 indicating moderate aggreement between the pathologist and the software. CONCLUSION: The total count of the cells both by the analyser and the pathologist were similar. However, improvements are needed to raise the precision for the detection of positive and negative tumoral cells.