Yazar "Simsek, Mehmet Ali" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    Automatic Meniscus Segmentation Using YOLO-Based Deep Learning Models with Ensemble Methods in Knee MRI Images
    (Mdpi, 2025) Simsek, Mehmet Ali; Sertbas, Ahmet; Sasani, Hadi; Dincel, Yasar Mahsut
    The meniscus is a C-shaped connective tissue with a cartilage-like structure in the knee joint. This study proposes an innovative method based on You Only Look Once (YOLO) series models and ensemble methods for meniscus segmentation from knee magnetic resonance imaging (MRI) images to improve segmentation performance and evaluate generalization capability. In this study, five different segmentation models were trained, and masks were created from the YOLO series. These masks are combined with pixel-based voting, weighted multiple voting, and dynamic weighted multiple voting optimized by grid search. Tests were conducted on internal and external sets and various metrics. The dynamic weighted multiple voting method optimized with grid search performed the best on both the test set (DSC: 0.8976 +/- 0.0071, PPV: 0.8561 +/- 0.0121, Sensitivity: 0.9467 +/- 0.0077) and the external set (DSC: 0.9004 +/- 0.0064, PPV: 0.8876 +/- 0.0134, Sensitivity: 0.9200 +/- 0.0119). The proposed ensemble methods offer high accuracy, reliability, and generalization capability for meniscus segmentation.
  • Küçük Resim Yok
    Öğe
    Impact of Thermosonication Treatment on Parsley Juice: Particle Swarm Algorithm (PSO), Multiple Linear Regression (MLR), and Response Surface Methodology (RSM)
    (Amer Chemical Soc, 2024) Altiner, Dilek Dulger; Yikmis, Seydi; Simsek, Mehmet Ali; Turkol, Melikenur; Demirok, Nazan Tokatli; Celik, Guler
    Thermosonication (TS), also known as ultrasonic-assisted heat treatment, is gaining attention in liquid product processing due to its ability to improve quality parameters and can serve as an alternative to thermal treatments. The parsley juice (TS-PJ) was subjected to thermosonication treatment (frequency: 26 kHz; power: 200 W; amplitude 60, 70, 80, 90, and 100%; temperature: 40, 45, 50, 55, and 60 degrees C; time: 4, 6, 8, 10, and 12 min) and was compared with untreated control parsley juice (C-PJ) and pasteurized treated (P-PJ) (85 degrees C/2 min) parsley juice samples. The objectives of the research work were to determine the effect of thermosonication on the quality attributes such as total chlorophyll and ascorbic acid of parsley juice using particle swarm algorithm (PSO), multiple linear regression (MLR), and response surface methodology (RSM). Thermosonication enhanced the bioactive compounds of parsley juice. The results showed that 15 phenolic compounds were detected in the samples. There was a significant (p < 0.05) increase in gallic acid contents in ultrasound-treated TS-PJ. There was no significant difference in total chlorophyll and ascorbic acid content between C-PJ and TS-PJ samples. Na and K from macro minerals and Fe and Zn from micro minerals were high in PJ samples. While K contents were increased, P contents were lower in the TS-PJ sample. RSM modeling provided superior prediction compared to MLR. PSO, on the other hand, made good predictions intuitively. Thermosonication enriched parsley juice's bioactive components and had positive health effects.
  • Küçük Resim Yok
    Öğe
    Morphometric analysis and tortuosity typing of the large intestine segments on computed tomography colonography with artificial intelligence.
    (Corporacion Editora Medica Valle, 2024) Sasani, Hadi; Ozkan, Mazhar; Simsek, Mehmet Ali; Sasani, Mahmut
    Background: Morphological properties such as length and tortuosity of the large intestine segments play important roles, especially in interventional procedures like colonoscopy. Objective: Using computed tomography (CT) colonoscopy images, this study aimed to examine the morphological features of the colon's anatomical sections and investigate the relationship of these sections with each other or with age groups. The shapes of the transverse colon were analyzed using artificial intelligence. Methods: The study was conducted as a two- and three-dimensional examination of CT colonography images of people between 40 and 80 years old, which were obtained retrospectively. An artificial intelligence algorithm (YOLOv8) was used for shape detection on 3D colon images. Results: 160 people with a mean age of 89 men and 71 women included in the study were 57.79 +/- 8.55 and 56.55 +/- 6.60, respectively, and there was no statistically significant difference (p= 0.24). The total colon length was 166.11 +/- 25.07 cm for men and 158.73 +/- 21.92 cm for women, with no significant difference between groups (p=0.12). As a result of the training of the model Precision, Recall, and mAP were found to be 0.8578, 0.7940, and 0.9142, respectively. Conclusions: The study highlights the importance of understanding the type and morphology of the large intestine for accurate interpretation of CT colonography results and effective clinical management of patients with suspected large intestine abnormalities. Furthermore, this study showed that 88.57% of the images in the test data set were detected correctly and that AI can play an important role in colon typing.