Biyomedikal Mühendisliği
Bu koleksiyon için kalıcı URI
Güncel Gönderiler
Öğe Biomedical image segmentation with modified U-Net(International Information and Engineering Technology Association, 2023) Tatlı, Umut; Budak, CaferImage segmentation is an important field in image processing and computer vision, particularly in the development of methods to assist experts in the biomedical and medical fields. It plays a vital role in saving time and costs. One of the mostsuccessful and significant methods in image segmentation using deep learning is the U-Net model. In this paper, we propose U-Net11, a novel variant of U-Net that uses 11 convolutional layers and introduces some modifications to improve the segmentation performance. The classical U-Net model was developed and tested on three different datasets, outperforming the traditional U-Net approach. The U-Net11 model was evaluated for breast cancer segmentation, lung segmentation from CT images, and the nuclei segmentation dataset from the Data Science Bowl 2018 competition. These datasets are valuable due to their varying image quantities and the varying difficulty levels in segmentation tasks. The modified U-Net model has achieved Dice Similarity Coefficient scores of 69.09% on the breast cancer dataset, 95.02% on the lung segmentation dataset and 81.10% on the nuclei segmentation dataset, exceeding the performance of the classical U-Net model by 5%, 2% and 4% respectively. This difference in success rates is particularly significant for critical segmentation datasets.Öğe Detection of ring cell cancer in histopathological images with region of interest determined by SLIC superpixels method(Springer, 2022) Budak, Cafer; Mençik, VasfiyeGastric cancer is the sixth most common cancer and the fourth leading cause of cancer deaths worldwide. Gastric cancer presents with a more insidious onset and is most frequently discovered at an advanced stage. Early diagnosis is critical since the stage of the disease is determinant in the severity, treatment, and survival rate of cancer. In the study, the Region of Interest (RoI) was determined in histopathological images using image preprocessing techniques and signet ring cell carcinoma (SRCC) was detected with popular deep learning models VGG16, VGG19, and InceptionV3. The fine-tuning strategy was applied by customizing the last five layers of deep network models based on the target data. The parameters of accuracy, precision, recall, and F1-score were used to evaluate the model performance. Signet ring cell dataset taken from the competition "Digestive System Pathological Detection, and Segmentation Challenge 2019" was employed. When compared to results of the DigestPath2019 Grand challenge ring cell gastric cancer competition, higher accuracy rates were obtained using deep learning models with the accurate defined RoI images. VGG16 model exhibited a higher performance with accuracy of 95% and a F1-score of 95% among the models. The results obtained by the algorithm were analyzed and confirmed by the experienced pathologist.Öğe Automatic cell nuclei segmentation using superpixel and clustering methods in histopathological images(Balkan Yayın, 2021) Mendi, Gamze; Budak, CaferIt is seen that there is an increase in cancer and cancer-related deaths day by day. Early diagnosis is vital for the early treatment of the cancerous area. Computer-aided programs allow for the early diagnosis of unhealthy cells that specialist pathologists diagnose due to efforts. In this study, clustering and superpixel segmentation techniques were used to detect cell nuclei in high-resolution histopathology images automatically. As a result of the study, the successful performances of the segmentation algorithms were analyzed and evaluated. It is seen that better success is obtained in the Watershed and FCM algorithms in highresolution histopathological images used. Quickshift and SLIC methods gave better results in terms of precision. It is seen that there are k-Means and FCM algorithms that provide the best performance in F measure (F-M), and the correct negative rate (TNR) is more successful in Quickshift, kMeans, and SLIC methods.
