Browsing by Author "Gur A."

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Production, optimization and characterization of polylactic acid microparticles using electrospray with porous structure
    (MDPI AG, 2021) Tasci M.E.; Dede B.; Tabak E.; Gur A.; Sulutas R.B.; Cesur S.; Ilhan E.; Lin C.-C.; Paik P.; Ficai D.; Ficai A.; Gunduz O.
    Polymeric microparticles with controlled morphologies and sizes are being studied by researchers in many applications, such as for drug release, healthcare and cosmetics. Herein, spherical and porous polymeric microparticles of different sizes and morphologies by electrospray technique have been developed as a viable alternative. In this work, polylactic acid (PLA) microparticles with a spherical shape and porous morphology were successfully produced via an electrospray technique in a single step. Molecular interactions between the components and the effect of parameters, such as varying solvent compositions, flow rates and voltage on microparticle morphology, were investigated over the particle formation. It was observed that the type of solvents used is the most effective parameter in terms of particle morphology, size and distribution. When the optical microscopy and SEM images of the microparticles were examined, 3 wt.% PLA in dichloromethane (DCM) solution concentration with an applied voltage of 18 kV and a flow rate of 20 µL/min was found to be the optimum parameter combination to achieve the desired spherical and porous micron-size particles. The average diameter of the particles achieved was 3.01 ± 0.58 µm. DCM was found to be a more suitable solvent for obtaining microparticles compared to the other solvents used. Finally, particles that are obtained by electrospraying of PLA–DCM solution are porous and monodisperse. They might have excellent potential as a carrier of drugs to the targeted sides and can be used in different biomedical applications. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.
  • No Thumbnail Available
    Item
    Effects of Data Augmentation Techniques on Classification Performance in Knee MRIs
    (Institute of Electrical and Electronics Engineers Inc., 2023) Kucuk E.N.; Gur A.
    The role of the amount of data used in increasing the effectiveness of deep learning models is very important. Due to the insufficient publicly available data in some sub-fields of health, data augmentation is vital. This study proposes an approach to improve the experimental work process in deep learning-based injury detection using data augmentation techniques on knee Magnetic Resonance (MR) images. The study is also one of the few in the body of literature to examine the impact of data augmentation in hard tissues. The effect of data augmentation on classification performance is tested using various transfer learning models, and the highest success rates in this study are determined for three classes. Forecasting achievements: the accuracy is 89.98% in the abnormal, 80.35% in the anterior cruciate ligament, and 76.66% in the meniscus classes. As a result of the experiments, it has been seen that the AutoAugment architecture works faster and generally gives more successful results than other augmentation methods. © 2023 IEEE.