Mehmet Gül

Mehmet Gül


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 February 2025 in IEEE Access
Verified
Journal Article
Open access
MGMehmet Gül
Mehmet Gül
Breast cancer, which is among the most common types of cancer in women, is a serious disease that requires attention due to its high risk of death. In this respect, every effort made to help early diagnosis is remarkable. This article proposed two methods, one CNN-based and the other local binary pattern (LBP)-based, to perform the preliminary diagnosis process on breast cancer histopathology images with high performance. Within the scope of the study, the high performance of the two proposed methods was applied to two separate comprehensive datasets most preferred in breast cancer studies. The proposed CNN model has 20 layers and is called quad star LBP (QS-LBP) due to its star-like structure based on the proposed LBP. The histopathology images improved with the QS-LBP method were then analyzed with the most commonly used Random Forest and Optimized Forest algorithms among machine learning algorithms. The BreaKHis dataset contains images with 40X, 100X, 200X, and 400X magnification resolutions and contains approximately 7924 images. The other comprehensive dataset containing analyzed histopathology images contains approximately 278 thousand images. Both datasets examined are extremely important in terms of the significant number of breast cancer histopathology images they contain. The results obtained with the QS-LBP method developed within the scope of the study are 94.58% accuracy, 92.3% F1 score, and 97.9% AUC/ROC, respectively. The results obtained with the proposed CNN model are 98.27% accuracy, 98% F1 score, and 97% AUC/ROC, respectively. The QS-LBP method and CNN model developed within the scope of the study outperform many existing methodologies in classifying breast cancer histopathology images as benign and malignant. In addition to all these, the accuracy of both methods proposed within the scope of the article can be compared with some state-of-the-art methods.

22 February 2024 in Neural Computing and Applications
Verified
Journal Article
Open access
PDF file
MGMehmet Gül
Mehmet Gül
YKYılmaz Kaya
Yılmaz Kaya
A brain tumor is one of the most lethal diseases that can affect human health and cause death. Invasive biopsy techniques are one of the most common methods of identifying brain tumor disease. As a result of this procedure, bleeding may occur during the procedure, which could harm some brain functions. Consequently, this invasive biopsy process may be extremely dangerous. To overcome such a dangerous process, medical imaging techniques, which can be used by experts in the field, can be used to conduct a thorough examination and obtain detailed information about the type and stage of the disease. Within the scope of the study, the dataset was examined, and this dataset consisted of brain images with tumors and brain images of normal patients. Numerous studies on medical images were conducted and obtained with high accuracy within the hybrid model algorithms. The dataset's images were enhanced using three distinct local binary patterns (LBP) algorithms in the developed model within the scope of the study: the LBP, step-LBP (nLBP), and angle-LBP (αLBP) algorithms. In the second stage, classification algorithms were used to evaluate the results from the LBP, nLBP and αLBP algorithms. Among the 11 classification algorithms used, four different classification algorithms were chosen as a consequence of the experimental process since they produced the best results. The classification algorithms with the best outcomes are random forest (RF), optimized forest (OF), rotation forest (RF), and instance-based learner (IBk) algorithms, respectively. With the developed model, an extremely high success rate of 99.12% was achieved within the IBk algorithm. Consequently, the clinical service can use the developed method to diagnose tumor-based medical images.

29 September 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
MGMehmet Gül
Mehmet Gül
Global cancer statistics indicate colon cancer caused nearly 1 million deaths, with lung cancer accounting for approximately 2 million fatalities1. Accurate tumor identification is a critical diagnostic challenge, where histopathological examination serves as the gold standard. While current pathological localization techniques are reliable, they possess procedural limitations. This study focuses on nuclear detection and classification via pathological imaging to determine tumor presence and characterize behavior. We introduce Cross-Over LBP (CO-LBP), an innovative Local Binary Pattern variant for colon cancer diagnosis, and conduct a comparative analysis with the established step-LBP (n-LBP) method. Our evaluation framework incorporates machine learning algorithms and transfer learning techniques applied to histopathological images from the LC25000 dataset. Results demonstrate CO-LBP’s clinically competitive performance (94.57% accuracy, 90.91% kappa), while n-LBP yields superior diagnostic outcomes (96.87% accuracy, 93.74% kappa), highlighting their complementary strengths in texture-based feature extraction. The experimental protocol first evaluated both LBP variants with machine learning classifiers, then with transfer learning models. The LC25000 dataset, comprising colon tissue histopathological images, served as the benchmark. Quantitative analysis revealed the following performance for n-LBP: accuracy (96.87%), kappa (93.74%), precision (96.9%), recall (96.9%), F1 score (96.9%), and ROC (99.4%). CO-LBP achieved comparable. Results accuracy (94.57%), kappa (90.91%), precision (94.9%), recall (94.9%), F1 score (94.9%), and ROC (98.8%). These findings substantiate the diagnostic potential of both methods, illustrating their distinct performance characteristics.

30 December 2020 in Celal Bayar Üniversitesi Fen Bilimleri Dergisi
Verified
Journal Article
Closed access
MGMehmet Gül
Mehmet Gül
Today, the epidemic diseases such as COVID-19 spreads very fast in the globalizing world and lethal effects on human health have had a noticeable effect on the health sector. For this situations, various disciplines have had different studies to minimize the effects of the epidemic. In such cases, it is a separate requirement that the use of the opportunities brought by technology. In this study, the kinematic analysis of the open-source robot arm was especially examined in terms of reducing the workload of individuals working in the healthcare sector. The open-source robot arm is articulated and has 5 degrees of freedom. The kinematic analysis is very important for determination of the working space of the robotic systems. The inverse kinematic analysis was done with Python programming language and the control module was developed to check the analysis. The control module shows the angle values depending on the joints of the robot arm. It is also shown the Px, Py, and Pz positions obtained depending on the position of the end effector in 3D space. On the other hand, Euler angle values are also specified, which are based on the position of the last position taken by the joints of the robot arm in the 3D space. In the study, the geometric approach method was used that is still popular in the inverse kinematic analysis. It is hoped that this study will inspire the development and use of professional and industrial kinds of the open-source robot arm.

30 November 2021 in Kocaeli Journal of Science and Engineering
Verified
Journal Article
Closed access
PDF file
MGMehmet Gül
Mehmet Gül
The widespread use of robotic systems is an example of increasing technological developments in daily life. The robotic systems that are accustomed to widespread use in the industry show huge impact in education, health, and many other areas nowadays. Robotic systems are no longer expensive and are not difficult to access systems that can be drawn and designed with design software like CAD programs. Within the scope of the study, major changes are made in the reference design, and Python software is used to send data to the Arduino control card that is used for control of the robotic system and to provide movement. The humanoid robotic arm developed in the study is printed with the 3D printer, sign languages that can be realized by one-handed letters among sign languages were investigated. All 26 alphabetical letters of English in American Sign Language can be demonstrated with the right hand alone. It has nearly the same principle that represents the demonstration of sign language expressions with a robotic hand, and the American Sign Language is the most widely known sign language. If experience is gained with this study, it can be used for the other sign language. In this study, audio and text messages sent over Python were performed on the humanoid robotic arm.

30 June 2025 in Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi
Verified
Journal Article
Open access
PDF file
ASAynur Sevinc
Aynur Sevinc
BKBuket Kaya
Buket Kaya
MGMehmet Gül
Mehmet Gül
In conventional methods, the detection of tumour disease from brain images using magnetic resonance imaging is a difficult and human error-prone field of study that requires an expert medical doctor. Incomplete or inaccurate detection of brain tumours can have significant undesirable consequences such as shortening of human life. In order to overcome these difficulties, many researchers are working on autonomous disease detection supported by artificial intelligence. The aim of this study is to utilise brain magnetic resonance images with deep learning architectures for fast and reliable autonomous cancer detection. In this study, brain images are classified using two different datasets and a convolutional neural network infrastructure, which are widely used in the publicly available literature. The results obtained as a result of experiments with similar parameters in training, validation and testing processes are compared in detail with other studies in the literature and the differences between them are presented. The new convolutional neural network-based model proposed in the study achieved 99.76% classification result in the accuracy evaluation metric. The results obtained showed that the model proposed in the study can be used with high accuracy in brain tumour detection and can shed light on other fields of study.