Yazar "Kaya, Ismail" seçeneğine göre listele

Listeleniyor 1 - 5 / 5
  • Küçük Resim Yok
    Öğe
    A revolutionary acute subdural hematoma detection based on two-tiered artificial intelligence model
    (Turkish Assoc Trauma Emergency Surgery, 2023) Kaya, Ismail; Gencturk, Tugrul Hakan; Gulagiz, Fidan Kaya
    BACKGROUND: The article was planned to make the first evaluation in terms of acute subdural hemorrhages, thinking that it can help in appropriate pathologies by tomography interpretation with the artificial intelligence (AI) method, at least in a way to quickly warn the responsible doctor.METHODS: A two-level AI-based hybrid method was developed. The proposed model uses the mask-region convolutional neural network (Mask R-CNN) technique, which is a deep learning model, in the hemorrhagic region's mask generation stage, and a problem -specific, optimized support vector machines (SVM) technique which is a machine learning model in the binary classification stage. Furthermore, the bee colony algorithm was used for the optimization of SVM algorithms' parameters.RESULTS: In the first stage, the mean average precision (mAP) value was obtained as 0.754 when the intercept over union (IOU) value was taken as 0.5 with the Mask R-CNN architecture used. At the same time, when a 5-fold cross-validation was applied, the mAP value was obtained 0.736. With the hyperparameter optimization for both Mask R-CNN and the SVM algorithm, the accuracy of the two-level classification process was obtained as 96.36%. Furthermore, final false-negative rate and false-positive rate values were obtained as 6.20%, and 2.57%, respectively.CONCLUSION: With the proposed model, both the detection of hemorrhage and the presentation of the suspicious area to the physician were performed more successfully on two dimensional (2D) images with low cost and high accuracy compared to similar studies and today's interpretations with telemedicine techniques.
  • Küçük Resim Yok
    Öğe
    Detection and Segmentation of Subdural Hemorrhage on Head CT Images
    (IEEE-Inst Electrical Electronics Engineers Inc, 2024) Gencturk, Tugrul Hakan; Kaya Gulagiz, Fidan; Kaya, Ismail
    In today's world, there has been a significant increase in the diversity of data sources and the volume of data. This situation especially necessitates the use of technologies such as deep learning in data processing. This study thoroughly examines the processing of computed tomography (CT) images with deep learning models and their role in the diagnosis of brain hemorrhages, proposing an innovative deep learning-based model for accurately detecting and segmenting brain hemorrhages. This model combines the architectures of Mask Scoring R-CNN and EfficientNet-B2, offering an effective approach for the detection and classification of brain hemorrhages. MS R-CNN is used to detect potential hemorrhage areas in CT images, while the EfficientNet-B2 architecture serves a classification function to determine whether these areas indeed contain hemorrhages. Thus, the model offers a two-stage verification process that enhances accuracy and precision. The performance of the model has been evaluated under patient-based and random partitioning techniques using by employing two distinct datasets: an open-access and a private. In patient-based evaluation, the proposed model has an accuracy of %91.59 on open dataset and an accuracy of %90.46 on private dataset for SDH hemorrhages. In the random partitioning method, the model's accuracy rate has risen to %94.30 on open dataset and %97.33 on private dataset. Compared with similar studies in the literature, these results demonstrate that the model has a high level of accuracy and reliability. This study highlights the potential and importance of AI-supported methods in the detection of brain hemorrhages and provides a solid foundation for future work in this area. Additionally, the results obtained from an open dataset by the proposed model offer a realistic and comparable reference for future work in this field. The results obtained from a second data set also clearly demonstrate the validity of the model.
  • Küçük Resim Yok
    Öğe
    Low-Cost 3-D-Printer-Assisted Personalized Cranioplasty Treatment: A Case Series of 14 Consecutive Patients
    (Elsevier Science Inc, 2023) Kaya, Ismail; Yakar, Huseyin; Kesen, Enes
    OBJECTIVE: The current study used polylactic acid molds [developed locally using three-dimensional printers and our software] and polymethyl methacrylate (PMMA) to perform cranioplasty of bone defects in technically demanding areas of the skull while ensuring ideal cosmetic results and functional recovery. The overall aim was to identify the ideal method for standard cranioplasty procedures -METHODS: Polylactic acid duplicates of the skull defects were created for eligible patients, after which a two-part negative mold composed of plaster and silicone was used to form artificial bone with PMMA. Thereafter, cranioplasty was performed and the treat-ment success was assessed by evaluating the per-centage of similarity objectively and the body image scale subjectively. -RESULTS: No surgical complications were seen to occur in the 14 patients included in the current study. Further-more, the subjective and objective evaluation revealed a significant improvement in outcomes (p < 0.05). No post-operative complications were observed over a follow-up period of 6 months, except in 1 patient who exhibited late infection.CONCLUSIONS: Cranioplasty operations were per-formed at an economical price of approximately US$50 dollars, suggesting that this method can be applied widely. Furthermore, preoperative preparation of the PMMA models can help reduce the duration of anesthesia and surgery which, in turn, will minimize the risk of surgical complications. Based on current knowledge in the field, we believe that this method represents the ideal technique.
  • Küçük Resim Yok
    Öğe
    Shunt Fractures Associated with Intermittent Hydrocephalus: Case Reviews and New Solutions
    (Elsevier Science Inc, 2022) Yakar, Huseyin; Kaya, Ismail
    OBJECTIVE: Although ventriculoperitoneal shunt surgery is the most common method for hydrocephalus treatment, it may lead to serious complications and require surgical interventions. Peritoneal catheter fracture is one of the common complications that may cause intermittent hydrocephalus. If patients with peritoneal catheter fracture have symptoms of hydrocephalus and ventricular dilatation, the treatment algorithm is clear. However, the diagnosis and treatment protocol remains unclear otherwise. In this article, the possible mechanisms of hydrocephalic symptoms, the diagnosis, as well as treatment algorithms are examined. METHODS: Eight patients with a ventriculoperitoneal shunt who had intermittent hydrocephalic symptoms due to peritoneal catheter fracture but without any radiologically significant ventricular dilatation at Nigde Omer Halisdemir University from 2018 to 2021 were collected. A new diagnostic algorithm was created. Patient follow-up was performed in each patient as a procedure. RESULTS: The method that we determined was successful in all our patients. No complications were observed. We have followed the patients with a normal clinic for at least 6 months. CONCLUSIONS: The provocation test we have formulated always revealed the true cause of the clinic. Thus, on the one hand, with a positive provocation test we recommend revision surgery without waiting for the ventricular dilatation or hydrocephalic symptoms in patients with a fractured peritoneal catheter, considering the results of asymptomatic shunt revision surgery have been reported to be better than those with symptomatic shunt dysfunction; on the other hand, patients with negative provocation tests are saved from unnecessary surgical intervention as well as benefit from true etiologic fast treatment.
  • Küçük Resim Yok
    Öğe
    The relationship between sphenoidal sinus and sella turcica morphometry in the Turkish population: a retrospective study
    (Springer France, 2024) Keles, Haci; Yakar, Huseyin; Kaya, Ismail; Cicek, Fatih; Ceranoglu, Faruk Gazi; Ciftci, Ali Turker; Karadag, Huseyin
    Purpose The anatomical position of the sphenoidal sinus (SS) is very important for neurosurgeons because of the trans-sphenoidal approach to the pituitary gland. Therefore, the aim of this study was to determine the volume and shape of the SS and its relationship with the morphometry of the sella turcica. Methods This study included CT images of 282 males and 258 females with a mean age of 50.52 years (range 18-75) who underwent head CT. The morphometric values of the sella turcica and the volume of the SS were measured on the included radiologic images. Measurements were made on the sagittal slice closest to the midline in T1 sequence. Morphometric measurements were made with Micro Dicom Viewers software program and volume measurements were made with ITK SNAP software program. Results In this study, 4 types of SS shapes were obtained in the whole population: amorphous, pentagonal, triangular and quadrilateral. The mean SS volume was 7055.88 mm3 in males and 5694.48 mm3 in females and a statistically significant difference was observed (p < 0.001). In addition, a statistically significant difference was found between the sexes in the width and surface area parameters of the sella turcica (p < 0.05). Conclusion In this study, the morphometric relationship between the shape of the sinus sphenoidale and sella turcica was demonstrated between men and women. In particular, the shape of the sinus sphenoidale was found to be anthropometrically different between men and women in the Turkish population. It is hypothesised that the data obtained in our study will guide surgeons performing transsphenoidal approach.