Yazar "Kaya, İsmail" seçeneğine göre listele
Listeleniyor 1 - 3 / 3
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A Comparative Study on Subdural Brain Hemorrhage Segmentation(Springer Science and Business Media Deutschland GmbH, 2023) Gençtürk, Tuğrul Hakan; Kaya, İsmail; Gülağız, Fidan KayaBrain hemorrhages are one of the most dangerous disease groups. If not detected early, it can lead to death or severe disability. The most common method used to detect bleeding is the evaluation of computed tomography (CT) images belonging to the bleeding area by specialist physicians. Considering the difficulty of access to neurosurgery specialists and the lack of expertise of other doctors in emergency intervention on the subject, there is a need for decision support mechanisms to assist physicians in the diagnosis and treatment process. Artificial intelligence-based systems to be used for this purpose can accelerate the diagnosis and treatment process while reducing the burden on physicians. In this study, the suitability of Mask Region-Based Convolutional Neural Network (Mask R-CNN), Cascade Region-Based Convolutional Neural Network (Cascade R-CNN), Mask Scoring Region-Based Convolutional Neural Network (MS R-CNN), Hybrid Task Cascade (HTC), You Only Look At Coefficients (YOLACT), Instances as Queries (QueryInst), and Sample Consistency Network (SCNet) methods, investigated for the problem of detection and segmentation of subdural brain hemorrhages. The performance of the methods was determined over the images in the CQ500 dataset. This is one of the few studies that perform segmentation of subdural cerebral hemorrhages using CT images from an open dataset. The results were evaluated according to Intersection Over Union (IoU) and Mean Average Precision (mAP) metrics. Experimental results showed that two methods could detect and segment subdural hemorrhages more accurately than the others. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.Öğe Evaluation of biopsy results in vertebra compression fractures treated by kyphoplasty(2020) Uzunoğlu, İnan; Gürkan, Gökhan; Cingöz, İlker Deniz; Atar, Murat; Kaya, İsmail; Hancıoğlu, Sert; Istan, Gündüz KadirAim: In the treatment of vertebral compression fractures, kyphoplasty stands out as an effective treatment method that has beenperformed more frequently in recent years. The etiology of compression fractures varies from patient to patient. Biopsy results takenfrom the patients during the procedure reflect these differences. We wanted to emphasize the importance of the biopsy procedureperformed during kyphoplasty by evaluating the biopsy results.Materials and Methods: The patient files, radiological images and biopsy results of the patients, who were treated with kyphoplastydue to vertebral compression fracture and who had a biopsy performed during this procedure between 2017 and 2019.Results: The total number of operated patients was found to be 201, and the number of vertebrae biopsies was 269. Eighty-three ofour patients were male and 118 were female. Of the 269 biopsy results in total, 18 (6.7%) had pathological findings; 3 of them werecompatible with osteomyelitis, while the remaining 15 were malignant.Conclusion: Since the biopsy procedure performed during the treatment of vertebral compression fractures with kyphoplasty couldbe performed safely and provides an opportunity for early diagnosis and treatment, a biopsy requirement for the benefit of patientswould be inevitable in all kyphoplasty procedures.Öğe Importance of paravertebral muscle quality in the etiology of degenerative lumbar spinal stenosis(2023) Kaya, İsmailObjectives: Degenerative lumbar spinal stenosis (DLSS) is the leading cause of pain, disability, and loss of independence in older adults. In this study, the relationship between DLSS and paravertebral muscle thickness and density was investigated using computed tomography (CT) and magnetic resonance imaging (MRI) methods. Thus, the importance of muscles has been examined to take precautions in the name of preventive medicine. Methods: This study was planned as a cross-sectional study. The patient group (n = 77) who had surgery for DLSS and the control group (n = 77) were examined. A total of 154 participants (55 females and 22 males in each group) were evaluated retrospectively in terms of cross-sectional area (CSA) and density in the psoas, erector spina and multifidus muscles. In both groups age, gender and body mass index values equalized. Measurements was averaged from the mid-lumbar 3 level from both sides and multi-points. Results: There was no significant difference between muscle thicknesses (p > 0.05). When evaluated in terms of muscle densities, a significant difference was found between the patient and the control group in terms of psoas muscle (p < 0.05). Likewise, there is the same relationship between erector spinae muscle density and multifidus muscle density (p < 0.05). Conclusions: Roughly no difference was found between the patient and control groups in terms of CSA of the psoas, erector spinae and multifidus muscles, but it was observed that the muscle density, especially in the multifidus, decreased significantly in the patients. Our results suggest that paravertebral muscle density assessment is an important criterion in disease prediction and can inform preventive treatment.