Yazar "Tulu, Cagatay Neftali" seçeneğine göre listele

Listeleniyor 1 - 7 / 7
  • [ X ]
    Öğe
    A comparative study of machine learning models for predicting neoadjuvant chemoradiotheraphy response in rectal cancer patients using radiomics and clinical features
    (Lippincott Williams & Wilkins, 2025) Ozdemir, Gorkem; Tulu, Cagatay Neftali; Isik, Omer; Olmez, Tolga; Sozutek, Alper; Seker, Ahmet
    Neoadjuvant chemoradiotherapy (nCRT) followed by total mesorectal excision is the standard treatment for locally advanced rectal cancer. However, the response to nCRT varies significantly among patients, making it crucial to identify those unlikely to benefit to avoid unnecessary toxicities. Radiomics, a technique for extracting quantitative features from medical images like computed tomography (CT), offers a promising noninvasive approach to analyze disease characteristics and potentially improve treatment decision-making. This retrospective cohort study aimed to compare the performance of various machine learning models in predicting the response to nCRT in rectal cancer based on medical data, including radiomic features extracted from CT, and to investigate the contribution of radiomics to these models. Participants who had completed a long course of nCRT before undergoing surgery were retrospectively enrolled. The patients were categorized into 2 groups: nonresponders and responders based on pathological assessment using the Ryan tumor regression grade. Pretreatment contrast-enhanced CT scans were used to extract 101 radiomic features using the PyRadiomics library. Clinical data, including age, gender, tumor grade, presence of colostomy, carcinoembryonic antigen level, constipation status, albumin, and hemoglobin levels, were also collected. Fifteen machine learning models were trained and evaluated using 10-fold cross-validation on a training set (n = 112 patients). The performance of the trained models was then assessed on an internal test set (n = 35 patients) and an external test set (n = 40 patients) using accuracy, area under the ROC curve (AUC), recall, precision, and F1-score. Among the models, the gradient boosting classifier showed the best training performance (accuracy: 0.92, AUC: 0.95, recall: 0.96, precision: 0.93, F1-score: 0.94). On the internal test set, the extra trees classifier (ETC) achieved an accuracy of 0.84, AUC of 0.90, recall of 0.92, precision of 0.87, and F1-score of 0.90. In the external validation, the ETC model yielded an accuracy of 0.75, AUC of 0.79, recall of 0.91, precision of 0.76, and F1-score of 0.83. Patient-specific biomarkers were more influential than radiomic features in the ETC model. The ETC consistently showed strong performance in predicting nCRT response. Clinical biomarkers, particularly tumor grade, were more influential than radiomic features. The model's external validation performance suggests potential for generalization.
  • [ X ]
    Öğe
    A novel embedding approach to learn word vectors by weighting semantic relations: SemSpace
    (Pergamon-Elsevier Science Ltd, 2021) Orhan, Umut; Tulu, Cagatay Neftali
    In this study, we propose a novel embedding approach, called as SemSpace, to determine word vectors of synsets and to find the best weights for semantic relations. First, SemSpace finds the optimum weights to the semantic relations in WordNet by aligning them to values produced by human intelligence, and then, determines word vectors of synsets by adjusting euclidean distances among them. Proposed approach requires two inputs; first, a lexical-semantic network such as WordNet, second, a word-level similarity dataset generated by people. In the experiments, we used WordNet 3.0 data for the lexical-semantic network, and three (RG65, WS353, and MEN3K) benchmark testsets to align semantic weights. Using the aligned semantic weights and the determined word vectors, the obtained resultsresults on the benchmark testsets are compared with literature studies. According to the obtained results, it might be concluded that SemSpace is not only successful to find word level semantic similarity values and semantic weights, but also to discover new semantic relations with their semantic levels.
  • [ X ]
    Öğe
    Automatic Short Answer Grading With SemSpace Sense Vectors and MaLSTM
    (IEEE-Inst Electrical Electronics Engineers Inc, 2021) Tulu, Cagatay Neftali; Ozkaya, Ozge; Orhan, Umut
    Automatic assessment of exams is widely preferred by educators than multiple-choice exams because of its efficiency in measuring student performance, lack of subjectivity when evaluating student response, and faster evaluation time than the time consuming manual evaluation. In this study, a new approach for the Automatic Short Answer Grading (ASAG) is proposed using MaLSTM and the sense vectors obtained by SemSpace, a synset based sense embedding method built leveraging WordNet. Synset representations of the Student's answers and reference answers are given as input into parallel LSTM architecture, they are transformed into sentence representations in the hidden layer and the vectorial similarity of these two representation vectors are computed with Manhattan Similarity in the output layer. The proposed approach has been tested using the Mohler ASAG dataset and successful results are obtained in terms of Pearson (r) correlation and RMSE. Also, the proposed approach has been tested as a case study using a specific dataset (CU-NLP) created from the exam of the Natural Language Processing course in the Computer Engineering Department of Cukurova University. And it has achieved a successful correlation. The results obtained in the experiments show that the proposed system can be used efficiently and effectively in context-dependent ASAG tasks.
  • [ X ]
    Öğe
    Convolutional Fourier Analysis Network (CONV-FAN-POX): A novel Time-Frequency approach for medical image analysis
    (Elsevier Sci Ltd, 2026) Tulu, Cagatay Neftali; Kaya, Yasin
    The recent monkeypox outbreak underscores the urgent need for improved diagnostic tools to enable swift, accurate disease detection. This study introduces CONV-FAN-POX, a novel neural architecture that integrates Fourier Analysis Network (FAN) principles into a deep learning pipeline for medical image classification. Unlike traditional models that rely solely on spatial-domain features, FAN leverages the Fourier series to enable robust modeling of quasi-periodic patterns and to capture global frequency-domain characteristics essential for accurate diagnosis. The proposed model, utilizing an EfficientNetV2 backbone, was evaluated on the MSLD2.0 dataset, achieving an average accuracy of 0.9881 and an F1-score of 0.9856 across five-fold cross-validation in a six-class setting. To validate the model's robustness and the specific contributions of the frequency-domain approach, extensive ablation studies were conducted, including a direct comparison of FAN and Dense-layer architectures, training and evaluation on the MSID dataset, and cross-dataset transfer testing. Furthermore, Explainable AI (XAI) was applied using Grad-CAM, which provides visual evidence that the FAN layer effectively prioritizes lesion-relevant features over background noise. Achieving superior performance while utilizing significantly fewer trainable parameters than conventional architectures, these results highlight CONV-FAN-POX as an efficient, interpretable, and generalizable alternative for medical image analysis, particularly in time-frequency-rich diagnostic contexts.
  • [ X ]
    Öğe
    Experimental Comparison of Pre-Trained Word Embedding Vectors of Word2Vec, Glove, FastText for Word Level Semantic Text Similarity Measurement in Turkish
    (Lublin Univ Technology, Poland, 2022) Tulu, Cagatay Neftali
    This study aims to evaluate experimentally the word vectors produced by three widely used embedding methods for the word-level semantic text similarity in Turkish. Three benchmark datasets SimTurk, AnlamVer, and RG65_Turkce are used in this study to evaluate the word embedding vectors produced by three different methods namely Word2Vec, Glove, and FastText. As a result of the comparative analysis, Turkish word vectors produced with Glove and FastText gained better correlation in the word level semantic similarity. It is also found that The Turkish word coverage of FastText is ahead of the other two methods because the limited number of Out of Vocabulary (OOV) words have been observed in the experiments conducted for FastText. Another observation is that FastText and Glove vectors showed great success in terms of Spearman correlation value in the SimTurk and AnlamVer datasets both of which are purely prepared and evaluated by local Turkish individuals. This is another indicator showing that these aforementioned datasets are better representing the Turkish language in terms of morphology and inflections.
  • [ X ]
    Öğe
    The potential of radiomics features in the detection of hepatocellular carcinoma (HCC) in 2D liver MRI images by using machine learning methods
    (Springer London Ltd, 2025) Tulu, Cagatay Neftali; Ibrikci, Turgay
    Hepatocellular carcinoma (HCC) is the sixth most prevalent cancer globally and the fourth leading cause of cancer-related mortality. Early detection of tumors through non-invasive methods, such as MRI (Magnetic Resounance Imaging), is critical for diagnosis and treatment planning. This study proposes a machine learning-based approach to predict the presence of HCC tumors in two-dimensional liver MR images by employing radiomics features extracted from the images. The publicly available Atlas dataset was used to extract radiomics features from MRI slices taken from 60 patients, those features were then employed to train machine learning models. The results demonstrate that radiomics features are highly effective for detecting HCC tumors. The LightGBM machine learning classifier achieved an AUC score of 0.95 and an Accuracy score of 0.87, indicating strong predictive accuracy and efficiency in identifying tumor-containing images. Highlighting the Center of Mass Index and Gray Level Size Zone Matrix (GLSZM) features are highly effective radiomics features in the model decisions. The performance of the trained models confirms that extracting radiomics features from MRI images is an effective and reliable approach for automatically detecting HCC tumors. The obtained results indicate promising outcomes, suggesting that the diagnostic process using radiomics features can be successfully applied to medical images in various clinical fields.
  • [ X ]
    Öğe
    TurkSentGraphExp: an inherent graph aware explainability framework from pre-trained LLM for Turkish sentiment analysis
    (PeerJ Inc, 2025) Kilic, Yasir; Tulu, Cagatay Neftali
    Sentiment classification is a widely studied problem in natural language processing (NLP) that focuses on identifying the sentiment expressed in text and categorizing it into predefined classes, such as positive, negative, or neutral. As sentiment classification solutions are increasingly integrated into real-world applications, such as analyzing customer feedback in business reviews (e.g., hotel reviews) or monitoring public sentiment on social media, the importance of both their accuracy and explainability has become widely acknowledged. In the Turkish language, this problem becomes more challenging due to the complex agglutinative structure of the language. Many solutions have been proposed in the literature to solve this problem. However, it is observed that the solutions are generally based on black-box models. Therefore the explainability requirement of such artificial intelligence (AI) models has become as important as the accuracy of the model. This has further increased the importance of studies based on the explainability of the AI model's decision. Although most existing studies prefer to explain the model decision in terms of the importance of a single feature/token, this does not provide full explainability due to the complex lexical and semantic relations in the texts. To fill these gaps in the Turkish NLP literature, in this article, we propose a graph-aware explainability solution for Turkish sentiment analysis named TurkSentGraphExp. The solution provides both classification and explainability for sentiment classification of Turkish texts by considering the semantic structure of suffixes, accommodating the agglutinative nature of Turkish, and capturing complex relationships through graph representations. Unlike traditional black-box learning models, this framework leverages an inherent graph representation learning (GRL) model to introduce rational phrase-level explainability. We conduct several experiments to quantify the effectiveness of this framework. The experimental results indicate that the proposed model achieves a 10 to 40% improvement in explainability compared to state-of-the-art methods across varying sparsity levels, further highlighting its effectiveness and robustness. Moreover, the experimental results, supported by a case study, reveal that the semantic relationships arising from affixes in Turkish texts can be identified as part of the model's decision-making process, demonstrating the proposed solution's ability to effectively capture the agglutinative structure of Turkish.