Examination of bone fractures in women exposed to domestic violence (Tokat-Turkey).

BACKGROUND: Fractures are an important symptom of physical violence that will negatively affect the woman's quality of life in the coming years. However, there is limited information in the literature about fractures in women exposed to domestic violence (DV). The aim of this study was to compare fracture development rates and age distributions in women exposed to DV and intimate partner violence (IPV), a component of DV, and women exposed to other physical violence (OV), to determine the incidence of DV cases with and without fractures, and to determine fracture locations in DV cases and to identify diagnostic lesions accompanying fractures. METHODS: A retrospective review was made of patients injured as a result of IPV, other domestic violence (ODV) and OV. The data of cases with fracture were analyzed in terms of age groups of the victims and according to location and types of fractures. RESULTS: Of the 854 female patients aged >18 years who were admitted to the hospital due to violence, 55.2% were exposed to DV. Most DV victims (87.9%) were assaulted by intimate partners. The incidence of fractures in IPV cases (7.2%), was nearly twice that of ODV and OV cases. The mean age of IPV cases with fractures (42.1 ± 12.1 years) was significantly higher than that of IPV cases without fractures (33.1 ± 11.8 years) (p < 0.05). Most IPV cases (61.8%) were aged <35 years. Most DV cases with fractures (75%) were aged <50 years. Facial/neck injuries (41.5%) and facial fractures (52.6%) were prominent in DV cases. CONCLUSION: The results of this study of the presence of facial fractures, especially in women aged <50 years, is an important finding that can alert doctors to potential cases of domestic violence.

Domain Generalization with Correlated Style Uncertainty.

Domain generalization (DG) approaches intend to extract domain invariant features that can lead to a more robust deep learning model. In this regard, style augmentation is a strong DG method taking advantage of instance-specific feature statistics containing informative style characteristics to synthetic novel domains. While it is one of the state-of-the-art methods, prior works on style augmentation have either disregarded the interdependence amongst distinct feature channels or have solely constrained style augmentation to linear interpolation. To address these research gaps, in this work, we introduce a novel augmentation approach, named Correlated Style Uncertainty (CSU), surpassing the limitations of linear interpolation in style statistic space and simultaneously preserving vital correlation information. Our method's efficacy is established through extensive experimentation on diverse cross-domain computer vision and medical imaging classification tasks: PACS, Office-Home, and Camelyon17 datasets, and the Duke-Market1501 instance retrieval task. The results showcase a remarkable improvement margin over existing state-of-the-art techniques. The source code is available https://github.com/freshman97/CSU.

An investigation of the effect of the COVID-19 (SARS-CoV-2) pandemic on occupational accidents (Tokat-Turkey).

The aims of this study were to compare the incidence of occupational accidents during one-year periods of the COVID-19 Pandemic and before the COVID-19 Pandemic, and to determine in which sectors occupational accidents occurred and what types of injuries were sustained in the population of Tokat, Turkey. A retrospective review was made of the records of Tokat State Hospital of patients injured in occupational accidents between 12.03.2019 and 11.03.2021. The patients injured in occupational accidents were classified according to age, gender, sector, accident type, trauma localization and type, time of the accident, and outcome of the injuries. Of 608 patients injured in occupational accidents, 384 (63.2%) were injured in the period before the pandemic and 224 (36.8%) were injured in the period during the pandemic (p < 0.001). Most work-related injuries occurred in the industry sector (n = 287; 47.2%; p < 0.001). Occupational accidents increased in the service sector (p < 0.001), but decreased in other sectors. The increase in occupational accidents in the health sector (p < 0.001) and transportation sector (p < 0.05) within the service sector caused a general increase despite the decrease in other service sectors (p > 0.05). In current study, the increase in the number of injuries in the transportation sector due to the increase of motor courier accidents, in health sector, and in pandemic quarantines were remarkable. It was evaluated that this narrow-scoped study pioneered comprehensive studies on the measures that can be taken to prevent occupational accidents in such pandemics in the future.

Radiomics Boosts Deep Learning Model for IPMN Classification.

Intraductal Papillary Mucinous Neoplasm (IPMN) cysts are pre-malignant pancreas lesions, and they can progress into pancreatic cancer. Therefore, detecting and stratifying their risk level is of ultimate importance for effective treatment planning and disease control. However, this is a highly challenging task because of the diverse and irregular shape, texture, and size of the IPMN cysts as well as the pancreas. In this study, we propose a novel computer-aided diagnosis pipeline for IPMN risk classification from multi-contrast MRI scans. Our proposed analysis framework includes an efficient volumetric self-adapting segmentation strategy for pancreas delineation, followed by a newly designed deep learning-based classification scheme with a radiomics-based predictive approach. We test our proposed decision-fusion model in multi-center data sets of 246 multi-contrast MRI scans and obtain superior performance to the state of the art (SOTA) in this field. Our ablation studies demonstrate the significance of both radiomics and deep learning modules for achieving the new SOTA performance compared to international guidelines and published studies (81.9% vs 61.3% in accuracy). Our findings have important implications for clinical decision-making. In a series of rigorous experiments on multi-center data sets (246 MRI scans from five centers), we achieved unprecedented performance (81.9% accuracy). The code is available upon publication.

Suicides in Turkey: 25-year trend (1995-2019).

The assessment of national suicide risks is considered critical in many countries for the establishment of suicide prevention initiatives aimed at considerably lowering suicide rates. The aim of this study is to identify at-risk suicide populations by reviewing the suicides in Turkey over a 25-year period. The Turkish Statistical Institute's suicide statistics for 1995-2019 in Turkey was retrospectively reviewed in current article. The data collected in the study was statistically analyzed using the MINITAB vn 14 software. Between 1995 and 2019, the total number of suicides in Turkey was 66,819, and suicide rates, especially in males, showed an increasing trend in this period. Males comprised 68.3% of the total cases, and most (27.2%) were aged 15-24 years. Suicides mostly occurred between May and July (27.7%), of individuals with a primary school level of education (51.7%) and who were married (6.0 per 100,000). Illness was most important risk factor for suicide (36.8%) and hanging (47.5%) was the leading suicide method in all age groups and in both genders. Despite the fact that Turkey's suicide rate is lower than many other countries, the growth in male suicide rates is concerning. Suicides are likely to become a severe problem in Turkey in the near future unless measures like education, psychiatric evaluations, the reactivation of psychological counseling service phone lines, and the establishment of youth counseling centers, as described in this paper, are taken.

Sex estimation from the clavicle using 3D reconstruction, discriminant analyses, and neural networks in an Eastern Turkish population.

Sex estimation of skeletal remains is an important aspect of forensic anthropology. The clavicle is a bone with relatively high accuracy in sex determination. In this study, 7 clavicular parameters were obtained using the CT images and 3D reconstruction of 360 cases equally distributed as 180 males and 180 females. Sex determination was made using univariate, linear, and stepwise discriminant analyses, and multilayer perceptron neural networks. Maximum sex determination accuracy of 85.3% was achieved with univariate analysis, 89.4% with linear discriminant analysis, 90.0% with stepwise discriminant analysis, and 91.4% with multilayer perceptron neural networks. Significant changes were observed in the MLC, APMD-R and CDC parameters according to age, and these were determined to affect the accuracy of sex determination in different age groups. In forensic anthropological studies, more reliable results can be obtained by considering the confounding factors during sampling. Although high accuracy rates can be achieved with neural networks, the results should be approached with caution.

Sex estimation using foramen magnum measurements, discriminant analyses and artificial neural networks on an eastern Turkish population sample.

BACKGROUND: Although many studies have been conducted using the foramen magnum for sex estimation, recent findings have indicated that the discriminant and regression models obtained from the foramen magnum may not be reliable. Artificial Neural Networks, was used as a classification technique in sex estimation studies on some other bones, did not used in sex estimation studies on the foramen magnum until now. The aim of this study was sex estimation on an Eastern Turkish population sample using foramen magnum measurements, discriminant analyses and Artificial Neural Networks. METHODOLOGY: The study was performed on the CT images of a total of 720 cases, comprising 360 males and 360 females. For sex estimation, discriminant analysis and Artificial Neural Networks were used. RESULTS: The accuracy rate was 86.7% with discriminant analysis and when sex estimation accuracy was determined according to cases with posterior probabilities above 95%, the accuracy ranged from 0% to 33.3%. With the use of the discriminant formulas of 2 other studies, obtained from different Turkish samples, sex could be determined at a rate of 84.6%. Some formulas were found to be unsuccessful in sex estimation. Sex estimation accuracy of 88.2% was achieved with Artificial Neural Networks. CONCLUSION: In this study, it was found that sex could be determined to some extent with discriminant formulas from other samples from the same population, although some formulas were unsuccessful. With the use of image processing techniques and machine learning algorithms, better results can be obtained in sex estimation.

Transformer based Generative Adversarial Network for Liver Segmentation.

Automated liver segmentation from radiology scans (CT, MRI) can improve surgery and therapy planning and follow-up assessment in addition to conventional use for diagnosis and prognosis. Although convolutional neural networks (CNNs) have became the standard image segmentation tasks, more recently this has started to change towards Transformers based architectures because Transformers are taking advantage of capturing long range dependence modeling capability in signals, so called attention mechanism. In this study, we propose a new segmentation approach using a hybrid approach combining the Transformer(s) with the Generative Adversarial Network (GAN) approach. The premise behind this choice is that the self-attention mechanism of the Transformers allows the network to aggregate the high dimensional feature and provide global information modeling. This mechanism provides better segmentation performance compared with traditional methods. Furthermore, we encode this generator into the GAN based architecture so that the discriminator network in the GAN can classify the credibility of the generated segmentation masks compared with the real masks coming from human (expert) annotations. This allows us to extract the high dimensional topology information in the mask for biomedical image segmentation and provide more reliable segmentation results. Our model achieved a high dice coefficient of 0.9433, recall of 0.9515, and precision of 0.9376 and outperformed other Transformer based approaches. The implementation details of the proposed architecture can be found at https://github.com/UgurDemir/tranformer_liver_segmentation.

Neuropathic pain in knee osteoarthritis.

BACKGROUND: This study aimed to investigate the relationship between the neuropathic pain in knee osteoarthritis with the body composition, anthropometric and postural features, physical function, and quality of life. METHODS: Patients with primary knee osteoarthritis, 50-70 years of age, were included in the study and divided into Group 1 with neuropathic pain and Group 2 with no neuropathic pain according to Douleur Neuropathique-4. The groups were compared in terms of demographic, clinical, radiological, laboratory findings and anthropometric measurements, body composition, physical function tests, osteoarthritis severity, quality of life, and posturography. RESULTS: 200 patients were included in the study. 98 (82.6% female) were in Group 1 and 102 (74.5% female) in Group 2. Age was higher in Group 1 compared to Group 2 [61 (50-70) and 57.5 (50-70), respectively, p = 0.03]. Symptom duration was also longer in Group 1 (5.21 ± 4.76 and 3.38 ± 3.58, p = 0.002). Body mass indices were 31.9 ± 5.6 and 30.1 ± 4.8 (p = 0.015). Kellgren-Lawrence class, Western Ontario and McMaster Osteoarthritis Index and Short Form-36 scores were more unfavorable in Group 1. Although fall risk was similar, stability and Fourier harmony indices were impaired in Group 1 compared to Group 2 especially when the visual and proprioceptive input was blocked. CONCLUSIONS: Almost half of the patients with knee osteoarthritis had neuropathic pain which was associated with longer symptom duration and higher age, lower education, higher body mass index, more severe radilogical findings, worse pain perception, lower physical function and quality of life, and lower stability.

Information Bottleneck Attribution for Visual Explanations of Diagnosis and Prognosis.

Visual explanation methods have an important role in the prognosis of the patients where the annotated data is limited or unavailable. There have been several attempts to use gradient-based attribution methods to localize pathology from medical scans without using segmentation labels. This research direction has been impeded by the lack of robustness and reliability. These methods are highly sensitive to the network parameters. In this study, we introduce a robust visual explanation method to address this problem for medical applications. We provide an innovative visual explanation algorithm for general purpose and as an example application we demonstrate its effectiveness for quantifying lesions in the lungs caused by the Covid-19 with high accuracy and robustness without using dense segmentation labels. This approach overcomes the drawbacks of commonly used Grad-CAM and its extended versions. The premise behind our proposed strategy is that the information flow is minimized while ensuring the classifier prediction stays similar. Our findings indicate that the bottleneck condition provides a more stable severity estimation than the similar attribution methods. The source code will be publicly available upon publication.

Feasibility of Distal Mechanical Thrombectomy in M3, A3 and P3 Segments via a 0.013-inch Delivery System: Preliminary Experience.

AIM: To assess the safety and efficacy of distal thrombectomy (DT) using a Catch View mini (CVm) device via a microcatheter with a 0.013-inch inner diameter. MATERIAL AND METHODS: Nine of 246 acute ischemic stroke patients who underwent mechanical thrombectomy developed distal emboli and were included in the study. In all nine subjects (mean age, 64.5 ± 11.6; range, 39?77 years), a combination of CVm and a 0.013-inch microcatheter was used in distal mechanical thrombectomy. Modified Thrombolysis in Cerebral Ischemia scores of 2c and 3 were considered to indicate successful recanalization, and patients with a Modified Rankin Score of ? 2 on the 90th day were considered to have good clinical outcomes. RESULTS: Eleven DT maneuvers were performed using the same stent retriever and microcatheter. The mean National Institutes of Health Stroke Scale score was 13 ± 3.4. Thrombectomy was performed from M3 in six patients, A3 in four, and P3 in one. Successful recanalization was achieved in all of the procedures. The rate of good clinical outcome was 55.5%. CONCLUSION: Advances in technology in the endovascular field enable access to more distal vessels in acute ischemic stroke. As the profile of the instruments used during access decreases, the risk of complications may decrease. The CVm stent retriever could become a useful tool in DT based on its compatibility with a 0.013-inch lumen delivery system.

Assessment of Axial Behavior of Circular HPFRCC Members Externally Confined with FRP Sheets.

The aim of this paper is to identify the axial behavior characteristics of FRP (fiber reinforced polymer) confined circular HPFRCC (high performance fiber reinforced cementitious composite) members under compression. The test program comprised of 24 circular specimens with an average compressive strength of 102.7 MPa, including 21 carbon FRP (CFRP) confined (2, 4, 6, 8 and 10 layers) and three unconfined specimens. Transverse confinement generated by external FRP sheets resulted with a remarkable enhancement in axial strength and deformability, which is extremely important to resist seismic actions. The higher was the thickness of FRP confinement, the larger was the ultimate strain (εcu) and peak compressive strength (f'cc) of externally confined HPFRCC. When compared to FRP confined conventional concrete, different axial and lateral deformation characteristics were seen in FRP jacketed HPFRCC members. Higher strength and steel fiber presence in HPFRCC limited the lateral deformations which resulted with reduced strain efficiency with respect to conventional concrete. After presenting the experimental work, performance and accuracy of several available models proposed for predicting the axial behavior of FRP jacketed concrete were evaluated in a comparative manner.

A prospective study of paranasal sinus osteomas in 1,889 cases: changing patterns of localization.

OBJECTIVES/HYPOTHESIS: We developed the largest paranasal sinus computed tomography (CT) scan study so far by including 1,889 cases to investigate the prevalence, localization, age distribution, and the secondary complications of paranasal sinus osteomas. STUDY DESIGN: Prospective study. METHODS: A prospective study was performed on 1,889 consecutive adult individuals who underwent paranasal sinus CT examinations with suspected sinus disease. RESULTS: The prevalence of paranasal sinus osteomas was determined to be 3%. Osteomas were located most frequently in the ethmoid sinuses. The size of the osteomas varied from approximately from 2 to 30 mm. Of the osteomas found, 37%were accompanied by pathological sinonasal findings. CONCLUSIONS: The prevalence of sinonasal osteoma in the paranasal sinus region detected by CT scan is supporting the literature, whereas the localization pattern challenges it.