A deep learning approach to permanent tooth germ detection on pediatric panoramic radiographs

Kaya Emine,Gunec Huseyin Gurkan,Aydin Kader Cesur,Urkmez Elif Seyda,Duranay Recep,Ates Hasan Fehmi 대한영상치의학회 2022 Imaging Science in Dentistry Vol.52 No.3

Purpose: The aim of this study was to assess the performance of a deep learning system for permanent tooth germ detection on pediatric panoramic radiographs. Materials and Methods: In total, 4518 anonymized panoramic radiographs of children between 5 and 13 years of age were collected. YOLOv4, a convolutional neural network (CNN)-based object detection model, was used to automatically detect permanent tooth germs. Panoramic images of children processed in LabelImg were trained and tested in the YOLOv4 algorithm. True-positive, false-positive, and false-negative rates were calculated. A confusion matrix was used to evaluate the performance of the model. Results: The YOLOv4 model, which detected permanent tooth germs on pediatric panoramic radiographs, provided an average precision value of 94.16% and an F1 value of 0.90, indicating a high level of significance. The average YOLOv4 inference time was 90 ms. Conclusion: The detection of permanent tooth germs on pediatric panoramic X-rays using a deep learning-based approach may facilitate the early diagnosis of tooth deficiency or supernumerary teeth and help dental practitioners find more accurate treatment options while saving time and effort.

A deep learning approach to permanent tooth germ detection on pediatric panoramic radiographs

Kaya, Emine,Gunec, Huseyin Gurkan,Aydin, Kader Cesur,Urkmez, Elif Seyda,Duranay, Recep,Ates, Hasan Fehmi Korean Academy of Oral and Maxillofacial Radiology 2022 Imaging Science in Dentistry Vol.52 No.-

Purpose: The aim of this study was to assess the performance of a deep learning system for permanent tooth germ detection on pediatric panoramic radiographs. Materials and Methods: In total, 4518 anonymized panoramic radiographs of children between 5 and 13 years of age were collected. YOLOv4, a convolutional neural network (CNN)-based object detection model, was used to automatically detect permanent tooth germs. Panoramic images of children processed in LabelImg were trained and tested in the YOLOv4 algorithm. True-positive, false-positive, and false-negative rates were calculated. A confusion matrix was used to evaluate the performance of the model. Results: The YOLOv4 model, which detected permanent tooth germs on pediatric panoramic radiographs, provided an average precision value of 94.16% and an F1 value of 0.90, indicating a high level of significance. The average YOLOv4 inference time was 90 ms. Conclusion: The detection of permanent tooth germs on pediatric panoramic X-rays using a deep learning-based approach may facilitate the early diagnosis of tooth deficiency or supernumerary teeth and help dental practitioners find more accurate treatment options while saving time and effort

Portal Hypertension in Children: A Tertiary Center Experience in Turkey

Emine Nur Sunar Yayla,Sinan Sarı,Neslihan Gürcan Kaya,Ödül Eğrİtaş Gürkan,Hakan Sözen,İbrahim Onur Özen,Aydın Dalgıç,Buket Dalgıç 대한소아소화기영양학회 2023 Pediatric gastroenterology, hepatology & nutrition Vol.26 No.6

Purpose: Portal hypertension (PH) and its complications have a significant impact on morbidity and mortality. This study aimed to evaluate the etiology; clinical, laboratory, and endoscopic findings; treatment approaches; long-term outcomes; and prognosis of pediatric PH. Methods: This retrospective study included 222 pediatric patients diagnosed with PH between 1998 and 2016, and data encompassing clinical, laboratory, and radiological features; treatments; and complications were analyzed. Results: The most common causes of PH were portal vein thrombosis (20.3%), progressive familial intrahepatic cholestasis (18.9%), and biliary atresia (12.2%). Among the enrolled patients, 131 (59.0%) were included in the cirrhotic group and 91 (41.0%) in the noncirrhotic group. Hepatomegaly and increased transaminase levels were more frequent in the cirrhotic group than in the non-cirrhotic group. Additionally, portal gastropathy, esophageal varices, and variceal bleeding were more frequent in the non-cirrhotic group, whereas ascites, hepatopulmonary syndrome and hepatic encephalopathy were more common in the cirrhotic group. The incidence of hepatomegaly was higher in the presinusoidal group than in the prehepatic group (p<0.001). Hyperbilirubinemia was more frequent in the prehepatic group (p=0.046). The frequency of esophageal varices was similar between the prehepatic and presinusoidal groups; however, variceal bleeding was more frequent in the prehepatic group (p=0.002). Conclusion: Extrahepatic portal vein obstruction, genetic-metabolic diseases, and biliary atresia were the most prevalent causes of PH in our country. In patients with PH, hepatomegaly, increased transaminase levels, and synthesis dysfunction were suggestive of cirrhotic PH. Notably, PH in patients without cirrhosis might be more severe than that in those with cirrhosis.

Evaluating Focal 18F-FDG Uptake in Thyroid Gland with Radiomics

Aksu Ayşegül,Karahan Şen Nazlı Pınar,Acar Emine,Çapa Kaya Gamze 대한핵의학회 2020 핵의학 분자영상 Vol.54 No.5

Purpose The aim of this study was to evaluate the ability of 18F-FDG PET/CT texture analysis to predict the exact pathological outcome of thyroid incidentalomas. Methods 18F-FDG PET/CT images between March 2010 and September 2018 were retrospectively reviewed in patients with focal 18F-FDG uptake in the thyroid gland and who underwent fine needle aspiration biopsy from this area. The focal uptake in the thyroid gland was drawn in 3D with 40% SUVmax threshold. Features were extracted from volume of interest (VOI) using the LIFEx package. The features obtained were compared in benign and malignant groups, and statistically significant variables were evaluated by receiver operating curve (ROC) analysis. The correlation between the variables with area under curve (AUC) value over 0.7 was examined; variables with correlation coefficient less than 0.6 were evaluated with machine learning algorithms. Results Sixty patients (70% train set, 30% test set) were included in the study. In univariate analysis, a statistically significant difference was observed in 6 conventional parameters, 5 first-, and 16 second-order features between benign and malignant groups in train set (p < 0.05). The feature with the highest benign-malignant discriminating power was GLRLMRLNU (AUC:0.827). AUC value of SUVmax was calculated as 0.758. GLRLMRLNU and SUVmax were evaluated to build a model to predict the exact pathology outcome. Random forest algorithm showed the best accuracy and AUC (78.6% and 0.849, respectively). Conclusion In the differentiation of benign-malignant thyroid incidentalomas, GLRLMRLNU and SUVmax combination may be more useful than SUVmax to predict the outcome.

Serum Chitotriosidase Activity in Pulmonary Tuberculosis: Response to Treatment and Correlations with Clinical Parameters

Gulhan Cakır,Seyfettin Gumus,Ergun Ucar,Hatice Kaya,Ergun Tozkoparan,Emin Ozgur Akgul,Bulent Karaman,Omer Deniz,Ismail Kurt,Metin Ozkan,Hayati Bilgic 대한진단검사의학회 2012 Annals of Laboratory Medicine Vol.32 No.3

Background: Chitotriosidase is an accepted marker of macrophage activation. In this study, we investigated serum chitotriosidase levels in pulmonary tuberculosis (PTB). Methods: Forth-two patients with PTB and 30 healthy subjects were enrolled in the study. The radiological extent of PTB, radiological sequela after treatment, and the degree of smear positivity were assessed. Chitotriosidase levels were measured by a fluorometric method. Results: The serum chitotriosidase levels of the PTB patients were significantly higher than those of the control subjects (39.73±24.97 vs. 9.63±4.55 nmol/mL/h, P<0.001). After completion of the standard 6-month antituberculous treatment, chitotriosidase levels in PTB patients significantly decreased (10.47±4.54 nmol/mL/h, P<0.001). Chitotriosidase levels correlated significantly with the radiological extent of PTB, degree of smear positivity, and post-treatment radiological sequela score (r=0.439, r=0.449, and r=0.337, respectively). Conclusions: This study demonstrated that serum chitotriosidase levels increase in PTB; therefore, chitotriosidase can be used as a marker of disease activity, severity, and response to treatment. Background: Chitotriosidase is an accepted marker of macrophage activation. In this study, we investigated serum chitotriosidase levels in pulmonary tuberculosis (PTB). Methods: Forth-two patients with PTB and 30 healthy subjects were enrolled in the study. The radiological extent of PTB, radiological sequela after treatment, and the degree of smear positivity were assessed. Chitotriosidase levels were measured by a fluorometric method. Results: The serum chitotriosidase levels of the PTB patients were significantly higher than those of the control subjects (39.73±24.97 vs. 9.63±4.55 nmol/mL/h, P<0.001). After completion of the standard 6-month antituberculous treatment, chitotriosidase levels in PTB patients significantly decreased (10.47±4.54 nmol/mL/h, P<0.001). Chitotriosidase levels correlated significantly with the radiological extent of PTB, degree of smear positivity, and post-treatment radiological sequela score (r=0.439, r=0.449, and r=0.337, respectively). Conclusions: This study demonstrated that serum chitotriosidase levels increase in PTB; therefore, chitotriosidase can be used as a marker of disease activity, severity, and response to treatment.

Interfacial Energy of Solid Bismuth in Equilibrium with Bi-In Eutectic Liquid at 109.5℃ Equilibrating Temperature

Yavuz Ocak,Sezen Akbulut,Necmettin Marasli,Kazlm Keslioglu,Ugur Boyuk,Hasan Kaya,Emin Cadirli 대한금속ᆞ재료학회 2008 METALS AND MATERIALS International Vol.14 No.2

Research Paper : Quantification of momilactone B in rice hulls and the phytotoxic potential of rice extracts on the seed germination of Alisma plantago-aquatica

( Husrev Mennan ),( Mathieu Ngouajio ),( Mevlut Sahin ),( Dogan Isik ),( Emine Kaya Altop ) 한국잡초학회 2012 Weed Biology and Management Vol.12 No.1

The occurrence of herbicide-resistant weeds has boosted interest in the use of crop allelopathy as a potential alternative to herbicides for weed control in rice (Oryza sativa). The phytotoxic compounds that are released by rice could help to enhance its competitive ability and improve weed management.This study aimed to screen rice genotypes for phytotoxic activity, quantify the amount of momilactone B in various rice tissues, and identify the potential parental lines for quantitative trait locus analysis. Therefore, a total of 41 cultivars from germplasm collections was evaluated for their effects. Significant differences were found among the rice cultivars in their ability to reduce the germination, root growth, and root dry weight accumulation ofAlisma plantago-aquatica.The leaf extract was the most inhibitory to germination. Out of the five cultivars that were tested, momilactone B was detected in four of them: Marateli, Kizilirmak, Karadeniz, and Kiziltan. Karadeniz and Kiziltan were identified as the rice cultivars with a high momilactone B content in the tissues and therefore they could be used in breeding programs to enhance the phytotoxic potential of rice.The development of a rice cultivar with proven allelopathic characteristics could provide an environmentally friendly and low-cost approach for the control of A. plantago-aquatica.