Search

AIM During daily practice of neurosurgery, especially in sub-specializations such as radiosurgery, tumor segmentation is essential and time consuming. Artificial intelligence methods are getting widely used for such purposes. In this study we propose a deep convolutional generative adversarial networks (DCGAN) model which learns normal brain MRI from normal subjects than finds distortions such as a glioma from a test subject while performing a segmentation at the same time. MATERIAL AND METHODS MRIs of 300 healthy subjects were employed as training set. Additionally, test data were consisting anonymized T2-weigted MRIs of 27 healthy subjects and 27 HGG patients. Consecutive axial T2-weigted MRI slices of every subject were extracted and resized to 364x448 pixel resolution. The generative model produced random normal synthetic images and used these images for calculating residual loss to measure visual similarity between input MRIs and generated MRIs. RESULTS The model correctly detected anomalies on 24 of 27 HGG patients' MRIs and marked them as abnormal. Besides, 25 of 27 healthy subjects' MRIs in the test dataset detected correctly as healthy MRI. The accuracy, precision, recall, and AUC were 0.907, 0.892, 0.923, and 0.907, respectively. CONCLUSION Our proposed model demonstrates acceptable results can be achieved only by training with normal subject MRIs via using DCGAN model. This model is unique because it learns only from normal MRIs and it is able to find any abnormality which is different than the normal pattern.

Aim To propose a convolutional neural network (CNN) for the automatic detection of high-grade gliomas (HGGs) on T2-weighted magnetic resonance imaging (MRI) scans. Material and methods A total of 3580 images obtained from 179 individuals were used for training and validation. After random rotation and vertical flip, training data was augmented by factor of 10 in each iteration. In order to increase data processing time, every single image converted into a Jpeg image which has a resolution of 320x320. Accuracy, precision and recall rates were calculated after training of the algorithm. Results Following training, CNN achieved acceptable performance ratios of 0.854 to 0.944 for accuracy, 0.812 to 0.980 for precision and 0.738 to 0.907 for recall. Also, CNN was able to detect HGG cases even though there is no apparent mass lesion in the given image. Conclusion Our preliminary findings demonstrate; currently proposed CNN model achieves acceptable performance results for the automatic detection of HGGs on T2-weighted images.

OBJECTIVEThe aim of this study was to investigate the relationship between lumbar spondylolysis and payload weight between different combat units of Turkish land forces (TLF).METHODThe authors reviewed clinical and radiological data of the military personnel with low-back pain (LBP) admitted to their clinic between July 2017 and July 2018. Age, BMI, average payload weight, and military service unit were recorded. CT scans were evaluated for pars interarticularis fractures and spondylolisthesis, whereas MRI studies were evaluated for spondylolisthesis, Modic-type endplate changes, or signal loss on T2-weighted images compatible with disc degeneration.RESULTFollowing exclusion, a total of 642 all-male military personnel were included. Of these personnel, 122 were commandos, 435 were infantry, and 85 were serving in the artillery units. Bilateral pars interarticularis fracture was noted in 42 commandos (34.42%) and 2 infantrymen (0.45%). There was no spondylolysis in the artillery units. There was no multiple-level spondylolysis and the most common level of spondylolysis was L5. Commandos had a significantly higher incidence of spondylolysis and more average payload weight (p < 0.001). Twelve patients (27.2%) with spondylolysis had accompanying MRI pathologies at the same level, whereas 32 patients (72.7%) had no accompanying MRI pathologies.CONCLUSIONSIncreased payload weight in military personnel is associated with spondylolysis, and commandos in the TLF have significantly heavier payloads, which causes an increased rate of spondylolysis compared to other units. Additionally, spondylolysis without adjacent-level changes on MRI could be undiagnosed. LBP in active military personnel who have a history of carrying heavy payloads should be evaluated extensively with both MRI and CT scans.

The inferior fronto-occipital fasciculus (IFOF) and uncinate fasciculus (UF) are major fronto-capsular white matter pathways. IFOF connects frontal areas of the brain to parieto-occipital areas. UF connects ventral frontal areas to anterior temporal areas. Both fascicles are thought to subserve higher language and emotion roles. Controversy pertaining to their connectivity and subdivision persists in the literature, however. High-definition fiber tractography (HDFT) is a non-tensor tractographic method using diffusion spectrum imaging data. Its major advantage over tensor-based tractography is its ability to trace crossing fiber pathways. We used HDFT to investigate subdivisions and cortical connectivity of IFOF and UF in 30 single subjects and in an atlas comprising averaged data from 842 individuals. A per-subject aligned, atlas-based approach was employed to seed fiber tracts and to study cortical terminations. For IFOF, we observed a tripartite arrangement corresponding to ventrolateral, ventromedial, and dorsomedial frontal origins. IFOF volume was not significantly lateralized to either hemisphere. UF fibers arose from ventromedial and ventrolateral frontal areas on the left and from ventromedial frontal areas on the right. UF volume was significantly lateralized to the left hemisphere. The data from the averaged atlas was largely in concordance with subject-specific findings. IFOF connected to parietal, occipital, but not temporal, areas. UF connected predominantly to temporal poles. Both IFOF and UF possess subdivided arrangements according to their frontal origin. Our connectivity results indicate the multifunctional involvement of IFOF and UF in language tasks. We discuss our findings in context of the tractographic literature.

The synovium is a specialized tissue lining the synovial joints, bursae, and tendon sheaths of the body. It is affected by various localized or systemic disorders. Synovial diseases can be classified as inflammatory, infectious, degenerative, traumatic, hemorrhagic, and neoplastic. Damage in other intraarticular structures, particularly cartilages, generally occurs as a part of pathologic processes involving the synovium, leading to irreversible joint destruction. Imaging has an essential role in the early detection of synovial diseases prior to irreversible joint damage. Obtaining and understanding characteristic imaging findings of synovial diseases enables a proper diagnosis for early treatment. This article focuses on the recent literature that is related with the role of imaging in synovial disease.

Background: Extracranial carotid artery pseudoaneurysms are rare cases resulting from trauma, mycotic infection, head and neck carcinomas or complications related to their treatment. Trauma is the most common cause of carotid artery pseudoaneurysms. They can also present after surgery, most commonly following endarterectomy, which is a rare cause with an estimated incidence of 0.3-0.6%. Case Report: A 26-year-old male patient was admitted with swelling in his left neck after left carotid endarterectomy. Angiography confirmed pseudoaneursym in the left carotid bulb and it was treated successfully with two heparin-bonded covered stent grafts. Conclusions: Endovascular treatment of carotid pseudoaneurysms with covered stent-grafts is a safe and efficient method providing definitive arterial reconstruction. But series with longer follow-up periods are needed to evaluate patient compatibility to lifelong antiplatelet theraphy.

Summary Background Pelvic vascular lesions such as pseudoaneurysms and arteriovenous fistulas associated with the internal pudendal artery are uncommon. The most common cause is traumas including those of iatrogenic origin. Surgical treatment is complicated due to location of the lesions and endovascular approach is usually the first choice among the treatment options. Case Report A 79-year-old patient was admitted with massive hematuria following transurethral resection of prostate for benign prostatic hyperplasia. Doppler US and angiography revealed a pseudoaneurysm and arteriovenous fistula originating from the right internal pudendal artery. It was successfully treated with coil embolization. Conclusions Arteriovenous fistulas and pseudoaneurysms concerning internal pudendal artery may occur as complications of prostate operations. Minimally invasive endovascular methods provide safe and efficient treatment and today should be considered as the first line of choice.