Search

Background: Every year, lung cancer contributes to a high percentage deaths in the world. Early detection of lung cancer is important for its effective treatment, and non-invasive rapid methods are usually used for diagnosis. Introduction: In this study, we aimed to detect lung cancer using deep learning methods and determine the contribution of deep learning to the classification of lung carcinoma using a convolutional neural network (CNN). Methods: A total of 301 patients diagnosed with lung carcinoma pathologies in our hospital were included in the study. In the thorax, Computed Tomography (CT) was performed for diagnostic purposes prior to the treatment. After tagging the section images, tumor detection, small and non-small cell lung carcinoma differentiation, adenocarcinoma-squamous cell lung carcinoma differentiation, and adenocarcinoma-squamous cell-small cell lung carcinoma differentiation were sequentially performed using deep CNN methods. Result: In total, 301 lung carcinoma images were used to detect tumors, and the model obtained with the deep CNN system exhibited 0.93 sensitivity, 0.82 precision, and 0.87 F1 score in detecting lung carcinoma. In the differentiation of small cell-non-small cell lung carcinoma, the sensitivity, precision and F1 score of the CNN model at the test stage were 0.92, 0.65, and 0.76, respectively. In the adenocarcinoma-squamous cancer differentiation, the sensitivity, precision, and F1 score were 0.95, 0.80, and 0.86, respectively. The patients were finally grouped as small cell lung carcinoma, adenocarcinoma, and squamous cell lung carcinoma, and the CNN model was used to determine whether it could differentiate these groups. The sensitivity, specificity, and F1 score of this model were 0.90, 0.44, and 0.59, respectively, in this differentiation. Conclusion.: In this study, we successfully detected tumors and differentiated between adenocarcinoma- squamous cell carcinoma groups with the deep learning method using the CNN model. Due to their non-invasive nature and the success of the deep learning methods, they should be integrated into radiology to diagnose lung carcinoma.

Background Pulmonary embolism is a type of thromboembolism seen in the main pulmonary artery and its branches. This study aimed to diagnose acute pulmonary embolism using the deep learning method in computed tomographic pulmonary angiography (CTPA) and perform the segmentation of pulmonary embolism data. Methods The CTPA images of patients diagnosed with pulmonary embolism who underwent scheduled imaging were retrospectively evaluated. After data collection, the areas that were diagnosed as embolism in the axial section images were segmented. The dataset was divided into three parts as training, validation, and testing. The results were calculated by selecting 50% as the cut-off value for the intersection over union. Results Images were obtained from 1,550 patients. The mean age of the patients was 64.23 ± 15.45 years. A total of 2,339 axial computed tomography images obtained from the 1,550 patients were used. There were a total of 5,992 labels, with 1,879 images. PyTorch U-Net was used to train 400 epochs, and the best model, epoch 178, was recorded. In the testing group, the number of true positives was determined as 471 and false positives as 35, while 27 were not detected. The sensitivity of CTPA segmentation was 0.95, the precision value was 0.93, the F1 score value was 0.94, and the learning rate was 0.0001. The area under the curve value obtained in the receiver operating characteristic analysis was calculated as 0.88. Conclusions In this study, the segmentation of acute pulmonary embolism in CTPA performed using the deep learning method provided successful results.

Pineal bez metastazları oldukça nadirdir. Çalışmamızın amacı, pineal bez metastazlarının manyetik rezonans görüntüleme bulgularını değerlendirmektir. Bu çalışmada Eylül 2010 ile Aralık 2019 tarihleri arasında hastane/ radyoloji arşivindeki beyin manyetik rezonans görüntülemelerinin raporları retrospektif olarak tarandı. Olgular belirlendikten sonra, hastaların cinsiyet, yaş, tanı, sağkalım süresi gibi özellikleri ve boyut (en büyük kesit çap), T1 ağırlıklı, T2 ağırlıklı sinyaller, kontrast tutulumu, ek beyin metastatik tutulum alanları gibi özellikler değerlendirildi. Araştırmamızda pineal metastazlı 7 hasta tespit edildi. Altta yatan maligniteler akciğer (N 2), meme (N 2), prostat kanseri (N 1), nöroblastom (N 1), non-Hodgkin lenfoma (N 1) idi. Pineal metastaz saptandıktan sonra ortalama yaşam süresi 3.14 aydı. Lezyonların boyutları 0.8 ile 1.8 cm arasında değişiyordu. Altı tümör, hem T1 ağırlıklı hem de T2 ağırlıklı olarak gri cevhere göre izointens idi. Biri T1 ağırlıklı ve T2 ağırlıklı görüntülerde heterojen sinyal intensitesi gösterdi. 7 tümörden 6'sı homojen solid kontrastlanma gösterirken, bir tümör nekroza bağlı heterojen kontrastlanma gösterdi. İki hastada leptomeningeal, bir hastada hipofiz sapı, bir hastada parankim, bir hastada kalvaryum-dural metastaz vardı. Kalan 3 hastada ise beyinde eşlik eden metastaz izlenmedi. Bilinen malignitesi olan hastalarda pineal lezyonların varlığı metastatik tutulum şüphesini artırmalıdır., The pineal gland metastatic disease is relatively uncommon. Our research’s objective was to assess pineal gland metastasis findings from magnetic resonance imaging (MRI). We queried the radiology reports of brain MRI examinations performed between September 2010 and December 2019. After identifying cases, patient characteristics including sex, age, diagnosis, survival time, and MRI features including size (largest cross-sectional diameter), T1- Weighted Image (WI) signal, T2-WI signal, contrast enhancement, and additional brain metastatic involvement area were evaluated. Our investigation identified 7 patients with pineal gland metastasis. Underlying malignancies were lung (N 2), breast (N 2), prostate cancer (N 1), neuroblastoma (N 1), and non-Hodgkin lymphoma (N 1). The average survival period after the detection of the pineal gland metastasis is 3.14 ± 3.93 months. The lesions ranged in size from 0.8 to 1.8 cm (mean 1.18±0.38 cm). Six tumors were isointense to gray matter both on T1-WI and T2-WI. One showed heterogeneous signal intensities on T1-WI and T2-WI. 6 out of 7 tumors showed homogenous solid enhancement while one tumor showed heterogeneous enhancement due to necrosis. Two patients had leptomeningeal, one patient had pituitary stalk, one patient had parenchyma, and one patient had calvarium-dural metastases. In the remaining 3 patients, no accompanying metastases were observed in brain. The presence of pineal gland lesions in patients with known malignancy should increase suspicion of metastatic involvement.

Koroner bilgisayarlı tomografik anjiografide (BTA) koroner damarların opasifikasyonuna etki eden faktörlerin gözden geçirilmesi ve bunların çekim pratiğine yansımalarını değerlendirmeyi amaçladık. Retrospektif olarak koroner BTA çekimleri değerlendirilmiş olup sol ana koroner arter (LMCA) santral kesiminden yapılan ölçümlere göre 300-400 Hounsfield Unit aralığında yapılan ölçümler optimum kabul edilip, bunun dışındakiler optimum olmayan grup olarak kabul edildi. İki grup kilo, kalp atımı, tüp akımı, kontrast miktarı, region of interest (ROI), end diastolik fazda midventriküler hatta sol ventrikül kısa aks çapı, Field of View (FOV), kontrast+ serum fizyolojik (SF) verilme süresi kıyaslandı. İstatistiksel anlamlılık sınırı olarak p, We aimed to review factors affecting the opacification of the coronary arteries in coronary computed tomography angiography (CTA) and evaluate their reflections on imaging practices. Coronary CTA images were retrospectively evaluated. The measurements performed from the central part of the left main coronary artery (LMCA) were divided into two groups optimal CTA (in the range of 300-400 Hounsfield units) and non-optimal CTA. Weight, heart rate, tube current, amount of contrast agent, region of interest (ROI), the short axis diameter of the left ventricle at the midventricular line in the end-diastolic phase, the field of view (FOV), and contrast + saline injection time were compared between the two groups. P

Purpose: Magnetic resonance imaging (MRI) has a special place in the evaluation of orbital and periorbital lesions. Segmentation is one of the deep learning methods. In this study, we aimed to perform segmentation in orbital and periorbital lesions. Material and methods: Contrast-enhanced orbital MRIs performed between 2010 and 2019 were retrospectively screened, and 302 cross-sections of contrast-enhanced, fat-suppressed, T1-weighted, axial MRI images of 95 patients obtained using 3 T and 1.5 T devices were included in the study. The dataset was divided into 3: training, test, and validation. The number of training and validation data was increased 4 times by applying data augmentation (horizontal, vertical, and both). Pytorch UNet was used for training, with 100 epochs. The intersection over union (IOU) statistic (the Jaccard index) was selected as 50%, and the results were calculated. Results: The 77th epoch model provided the best results: true positives, 23; false positives, 4; and false negatives, 8. The precision, sensitivity, and F1 score were determined as 0.85, 0.74, and 0.79, respectively. Conclusions: Our study proved to be successful in segmentation by deep learning method. It is one of the pioneering studies on this subject and will shed light on further segmentation studies to be performed in orbital MR images.

Purpose The purpose of this study was to prospectively assess the Eustachian tube (ET) cartilage using 3 Tesla (3T) magnetic resonance imaging (MRI) and compare the results between healthy ears and those with a middle ear disease. Material and methods The study included 56 ears with a middle ear disease as the patient group and 100 ears without a middle ear disease as the control group. The patients' age ranged from 18 to 65 years. The axial three-dimensional (3D) multiple echo recombined gradient echo (MERGE) sequence and oblique parasagittal planes were obtained. Visualisation of the ET cartilage was assessed on the MR images using a three-point numerical rating score. In the axial plane, the ET lumen's diameter was measured from the mid-portion of the cartilage. Results There was no significant difference between the patient group and the control group according to patients' age and gender, and the medial laminal thickness of the ET cartilage. In the patient group, the diameter of the ET cartilage was significantly smaller than in the control group. The ET lumen diameter was significantly lower according to each of the three scoring systems. Conclusions 3T MRI provides an evaluation of the ET cartilage and isthmus level, which are small but important anatomical localisations and surgical landmarks. MR imaging has the potential to provide essential information on ET prior to new surgical treatments, such as balloon dilation for middle ear diseases.

Background: The typical findings of COVID-19 pneumonia include multilobar groundglass opacities and consolidation areas observed predominantly in the basal and peripheral parts of both lungs in computed tomography. Objective: The current study aimed to correlate indeterminate lesions of COVID-19 pneumonia detected on computed tomography with the results of the reverse transcription-polymerase chain reaction (RT-PCR) test. Methods: Patients with high-resolution computed tomography images that were reported to contain indeterminate lesions in terms of COVID-19 pneumonia were included retrospectively in the study. The lesions were categorized and the patterns were classified. The RT-PCR-positive and the RTPCR- negative patients were compared. P Results: The RT-PCR-positive patients exhibited a higher rate of peripheral lesions. Limited consolidation areas were not detected in the RT-PCR-positive patients. In the RT-PCR-negative patients, the rates of acinar nodules and the tree-in-bud pattern were significantly higher. The RTPCR- negative patients had higher nodular contour features and lesion coalescence. In the subgroup consisting of lesions with ground-glass opacities and/or ground-glass opacity around the nodule, the rate of nodular contour positivity was significantly higher in the RT-PCR- positive patients. Conclusion: COVID-19 pneumonia should be suspected when peripheral indeterminate lesions are detected. When indeterminate lesions, such as tree-in-bud pattern, acinar nodules and limited consolidation area are detected, alternative diagnoses should be considered first, even if there are ground glass opacities accompanying these lesions.

Calismamizda mediasten lenf nodlarinin BT incelemelerde dogru anlasilmasi ve akilda tutulmasi ozellikle tip ogrencileri icin zor bir surec olup bu sureci kolaylastirmak adina 3D yazici ile basimi yapilmis mediasten modelini besinci sinif ogrencilerinin egitiminde kullanarak ogrenmedeki etkisini olcmeyi hedefledik. Bu calisma ESOGU Tip Fakultesi’nde 15.02.2018-15.05.2019 tarihleri arasinda prospektif olarak besinci sinif ogrencilerinin Radyoloji staji icerisinde anlatilan Toraks Anatomisi dersi kapsaminda iki dongu halinde yapildi. besinci sinif ogrencilerine once teorik ders anlatilip, IASLC (International Association for the Study of Lung Cancer) lenf nodu haritasina gore 1-14 araligindaki lenf nodu istasyonlari ve zonlari kesitsel iki boyutlu gorsellerle desteklenerek anlatildi. Daha sonra dersin pratik saatinin sonunda yazili onami alinmis ogrenciler iki gruba ayrildi, bir gruba lenf nodu istasyonlari ve zonlari power point ders materyalleriyle anlatildi. Diger gruba Ultimaker 3 Extended uc boyutlu (3D) yazici ile katman birikimli modelleme yontemi ile yapilan mediasten modelinden faydalanilarak anlatim yapildi. Sonuclar SPSS’de bagimli orneklem t testi ile analiz edilip sonuclar tablo haline getirildi. Bagimli orneklem t testine gore 3D yazici ile basimi yapilan mediasten modeli ile anlatilan ogrenci grubu, power point ile anlatilan ogrenci grubuna gore daha fazla soru sayisi ortalamasina sahip olup anlamli farklilik saptandi (t: 3.07, p:0.05).3D yazici tip egitiminde anatomik yapilari gostermede, pratik yaptirmada onemli bir yere gelmistir. Mediastinal lenf nodlari gibi zor, kafa karistiran anatomik lokalizasyonlarda 3D yazici ile ders anlatimini desteklemek ogrenciler icin olumlu sonuclar verecektir.

Background & Objectives: Hypothermia, described as temperature < 35°C, is a frequent condition encountered in patients operated under general anesthesia. It is associated with significant morbidity and mortality. We aimed to estimate its incidence and to investigate the conditions associated with hypothermia in pediatric patients. Methods: This prospective clinical study was carried out in the operating theatre of a tertiary care center between August 2015 and September 2015. A total of 108 pediatric patients who underwent various surgical procedures that lasted for more than 30 minutes were enrolled. Baseline demographic data, types of surgical procedures, duration of operations, preoperative and perioperative body temperatures were recorded. The incidence of hypothermia and its possible correlates were sought. Results: Our series consisted of 108 children (77 males, 71.3%; 31 females, 28.7%) with an average age of 6.08±5.09 years were included in the study. There was no case diagnosed with hypothermia in the preoperative, perioperative and postoperative periods. Patients in American Society of Anesthesiologists classification (ASA) three group had significantly higher preoperative body temperatures compared to those in ASA-1 and ASA-2 groups (p = 0.027). The postoperative body temperature in patients receiving intravenous fluid replacement was significantly lower (p=0.017). Conclusion: For pediatric patients scheduled for surgical interventions, we recommend close monitorization and follow-up of body temperature, implementation of preventive measures to avoid hypothermia and routine perioperative heating. Avoidance of hypothermia may prevent hazardous consequences of postoperative hypothermia. doi: https://doi.org/10.12669/pjms.36.4.456 How to cite this:Esen O, Yilmaz G, Aydin N. Perioperative hypothermia in pediatric patients operated in a tertiary care center: Incidence and correlates. Pak J Med Sci. 2020;36(4):793-798. doi: https://doi.org/10.12669/pjms.36.4.456 This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Oz: Toplumda ciddi saglik problemleri arasinda bulunan spinal travmalar, gecmis yillarda destekleyici yontemlerle tedavi edilirken gunumuzde implant ozelliklerinin gelismesiyle, yerini radyolojik goruntulemelerin de destegiyle planlamanin daha iyi yapildigi cerrahi tedaviye birakmistir. Gunumuzun populer yeniliklerinden olan 3 boyutlu yazicilar hayatin her alaninda oldugu gibi tip alaninda da her gecen gun daha fazla kullanilmaktadir. Bu calismanin amaci BT uzerinden bilgisayar destekli modelleme kullanilarak 3 boyutlu yazici yardimi ile birebir hastanin omurga modelleri uretilerek; cerraha ameliyat oncesi simulasyon imkani saglamaktir. Calismamizda spinal travma oykusu olan hastalarin direk grafi, bilgisayarli tomografi; 3 boyutlu bilgisayarli tomografi ile bilgisayar destekli omurga modelleri olusturularak ve 3 boyutlu yazicilarda uretilerek farkli cerrahlar tarafindan cerrahi plan yapmalari saglanacaktir.

Pulmonary vein (PV) stenosis is a rare but serious complication of PV isolation. It usually develops 3-6 months after the procedure, but may rarely develop in the acute phase. We present a case of symptomatic PV stenosis within 48 hours after antral PV isolation. Following the initiation of medical treatment including a glucocorticoid, acute changes in the PV wall regressed and the patient's complaint of dyspnea at rest improved rapidly. In addition, long-term renin-angiotensin-aldosterone system (RAAS) blockers were given. The complaint did not recur during follow-up and PV stenosis was mild at 6 months.

Objective: The present study aimed to compare the upper airway dimensions as well as hemodynamic and anesthetic features of propofol, ketamine, and ketofol in children undergoing magnetic resonance imaging (MRI) scanning. Material and Methods: This retrospective study was carried out on data derived from a total of 89 patients aged between 1-160 months who were allocated in 3 groups concerning the anesthetic agents administered during sedation for MRI. Group I received ketamine and propofol (ketofol), whereas Group II had propofol and, and Group III received ketamine in this procedure. Results: The cross-sectional area of the upper airway at the levels of the base of tongue, soft palate and epiglottis were higher in patients receiving ketofol, compared to those receiving propofol or ketamin (p

Cranioplasty is a reconstruction operation made to protect intracranial structures. It is applied for the closure of bone defects occurring due to causes such as trauma, tumor, infection, and infarct. Many different products changing from autologous bone grafts to synthetic materials are used for cranioplasty. Three-dimensional printers that are among the popular innovations of today are used gradually more in medical area as in every field of life and they make the surgical operation easier. When customizable materials are combined with technology, the authors come across successful results and less complications. The aim of the authors' study was to show a 3-dimensional modeling method in 2 patients the authors applied cranioplasty and the advantages provided by this method for the surgeon and the patient. © 2019 by Mutaz B. Habal, MD

WOS: 000471902200032, PubMed: 31121999, Background/aim: Application fields of bone tissue engineering studies continue to expand. New biocompatible materials aimed to improve bone repairment and regeneration of implants are being discovered everyday by scientists, engineers, and surgeons. Our objective in this study is to combine polylactic acid which is a polymer with hydroxyapatite in the repairment of bone defects considering the increased need by medical application fields. Materials and methods: After 750 g of PLA with a diameter of 2.85 mm was granulated into minimum particles, these particles were homogenously mixed with hydroxyapatite prepared in laboratory environment. Using this mixture, HA-PLA filament with a diameter of 2.85 mm was prepared in the extrusion device in Kutahya Medical Sciences University Innovative Technology Laboratory. The temperature was 250 degrees C and the gearmotor speed was 9 rpm during extrusion. X-ray diffraction (XRD) analysis was made for crystal phase analyses of the produced hydroxyapatite powder, to determine the produced main phase and examine whether a minor phase occurred. Vickers microhardness test was applied on both samples to measure the endurance levels of the samples prepared with HA-PLA filament. A loading force of 10 kg was applied on the samples for 10 s. Results: Hydroxyapatite peaks in XRD spectrum of the sample presented in figures are concordant with Joint Committee on Powder Diffraction Standards, JCPDS - File Card No. 01-075-9526 and no significant minor phase was observed. For both samples, hardness value was observed to increase between 3 and 5 mm. Conclusion: Surfacing hydroxyapatite on metallic materials is possible. By similar logic, to increase durability with low cost, characteristics of biomaterials can be improved with combinations such as hydroxyapatite PLA. Thus, we found that while these materials have usage limitations due to present disadvantages when used alone, it is possible to increase their efficiency and availability through different combinations.

Objectives: In the present study, we aimed to compare the postoperative compliance and complications between ERAS and conventional postoperative care in patients undergoing abdominal hysterectomies. Material and methods: This is the prospective, randomized, controlled trial, which involved 62 patients, who underwent abdominal hysterectomy between December 2016 to February 2017. A total of 30 patients formed the ERAS group. A total of 32 patients who received conventional perioperative care and matched for age, body mass index (BMI) and American Society of Anesthesiologists score were assigned as a control group. Groups were compared in terms of patient characteristics [age, body mass index, ASA Score, parity, diagnosis, type of surgery, and perioperative intravenous fluids], postoperative compliance (postoperative intravenous fluids, time to first flatus, first defecation, ambulation, eating solid food, and postoperative hospital stay), and postoperative complications. Results: Peri- and post-operative administrated intravenous fluids were significantly lower in the ERAS group (p < 0.001 for both). Time to first flatus (p = 0.001), time to first defecation (p < 0.001), and time to eating solid food (p < 0.001) were all significantly shorter in the ERAS group. Post-operative early mobilization on the first postoperative day was achieved in eight (26.7%) patients in the ERAS group. There were no significant differences in complications. One (3.3%) patient in the ERAS Group and 11 (34.4%) patients in the Conventional Group required hospital readmission after discharge (p = 0.002). Conclusion: The ERAS protocol seems to be a simple tool for reducing the incidence of postoperative complications and shortening hospitalization.

Inventory routing problem can be defined as forming the routes to serve to the retailers from the manufacturer, deciding on the quantity of the shipment to the retailers and deciding on the timing of the replenishments. The difference of inventory routing problems from vehicle routing problems is the consideration of the inventory positions of retailers and supplier, and making the decision accordingly. Inventory routing problems are complex in nature and they can be solved either theoretically or using a heuristics method. Metaheuristics is an emerging class of heuristics that can be applied to combinatorial optimization problems. In this paper, we provide the relationship between vendor-managed inventory and inventory routing problem. The proposed genetic for solving vehicle routing problem is described in detail.

The clustering allows dividing the geographical region to be covered into small zones in which each zone can be handled with a powerful node called clusterhead. The clusterheads have direct communication link with each of its members whereas the member nodes of a cluster must go through the clusterhead to communicate with each other. Since choosing clusterheads optimally is an NP-hard problem, existing solutions to this problem are based on heuristic (mostly greedy) approaches. In this paper, we present three well-known heuristic clustering algorithms: the Lowest-ID, the Highest-Degree, and the Node-Weight.

Aim: To manufacture personal hand and finger splint with three dimensional printer, applying in emergency service patients and comparing with traditional splint applications.Material and Methods: Personal hand-finger splints were manufactured using three dimensional printer and applied to 25 patients referring to Kutahya Medical Sciences University, Faculty of Medicine, Emergency Medicine Department with upper extremity trauma and requiring hand-finger splints and these were compared with splints in the market which are medical products manufactured with traditional methods for cost, patient comfort and treatment efficiency.Results: 11 (44%) traffic accidents, 8 work accidents (32%) and 6 (24%) simple home accidents were detected in trauma etiology distribution. Based on the pathologies of the cases, 9 (36%) soft tissue pathologies, 5 (20%) proximal phalangeal, 4 (16%) distal phalangeal, 2 middle phalangeal, 3 (12%) metacarpal bone and 2 (8%) thumb fractures were found. In the controls made for all patients in the third week, it was observed that their complaints were over, they didn’t need splints anymore and there was recovery in fusion and soft tissue traumas in control x-rays. In the follow-ups of these cases, it was detected that they easily returned to their daily activities.Conclusion: In our study, personal hand-finger splints were manufactured and applied to 25 patients using 3 dimensional printer. For all cases, complete recovery was detected in the controls of all cases and fusion was provided based on control x-rays and they easily returned to their daily activities.Keywords: Finger splint; trauma; 3D printer.

Cerebral vasospasm, especially delayed cerebral ischemia following subarachnoid hemorrhage (SAH) is the most important complication that effects mortality and morbidity of patients with intracranial aneurysms. The presence of cerebral vasospasm has been correlated with an increase in mortality in the first 2 weeks after SAH. Despite clinical studies and research, the etiopathogenesis of cerebral vasospasm is not understood exactly and there is not yet an effective therapy. The aim of our study was to investigate the effect of application of lumber drainage on vasospasm and delayed cerebral infarction following SAH and to examine the incidence of complications. Patient groups were determined by retrospective screening of 70 patients who underwent a surgical operation at the Osmangazi University Medical Faculty Department of Neurosurgery between 2009 and 2013 after a diagnosis of ruptured aneurysmal SAH. After the application of lumbar drainage, the complications and mortality after aneurysm surgery was significantly decreased and correlated with the amount of hemorrhagic cerebrospinal fluid drainage.