Search Results (2)

Skin lesion segmentation has a critical role in the early and accurate diagnosis of skin cancer by computerized systems. However, automatic segmentation of skin lesions in dermoscopic images is a challenging task owing to difficulties including artifacts (hairs, gel bubbles, ruler markers), indistinct boundaries, low contrast and varying sizes and shapes of the lesion images. This paper proposes a novel and effective pipeline for skin lesion segmentation in dermoscopic images combining a deep convolutional neural network named as You Only Look Once (YOLO) and the GrabCut algorithm. This method performs lesion segmentation using a dermoscopic image in four steps: 1. Removal of hairs on the lesion, 2. Detection of the lesion location, 3. Segmentation of the lesion area from the background, 4. Post-processing with morphological operators. The method was evaluated on two publicly well-known datasets, that is the PH2 and the ISBI 2017 (Skin Lesion Analysis Towards Melanoma Detection Challenge Dataset). The proposed pipeline model has achieved a 90% sensitivity rate on the ISBI 2017 dataset, outperforming other deep learning-based methods. The method also obtained close results according to the results obtained from other methods in the literature in terms of metrics of accuracy, specificity, Dice coefficient, and Jaccard index. Full article

Background and Objective. A tick bite has been an emergency of increased importance in recent years since it can cause a progressive, fatal disease such as Crimean-Congo hemorrhagic fever (CCHF). This issue should be considered by physicians working not only in endemic areas but also in the entire world, taking into account immigration, overseas trips, etc. In our study, we aimed to increase the awareness of the issue by evaluating the emergency department admissions of tick bite complaints in an endemic area.
Material and Methods. In total, 251 patients who had been admitted to the emergency department with a complaint of a tick bite within 10 months were included into the study. The data were obtained by collecting main complaints, demographic characteristics, cell counts on admission, and biochemical tests as well as CCHF findings in the RT-PCR test. The patients were divided into 2 groups according to the results of real-time polymerase chain reaction (PCR+ and PCR–).
Results. All the patients complained of tick bites. As for the additional complaints, 46% of the overall study population had fatigue and 36% experienced fever. Fever was the most common complaint in the PCR+ group (39%). The platelet and white blood cell counts were significantly lower and the AST level was significantly higher in the PCR+ group than the PCR– group (P<0.01).
Conclusions. In CCHF, where an early diagnosis is very important in reducing mortality, and the symptoms such as a tick bite, fever, and fatigue should be taken seriously by emergency medicine physicians. Leukopenia and thrombocytopenia and higher levels of enzymes in the liver function tests should be taken into account. Full article