Rahime Ceylan

Lymphoma is a type of cancer classified under blood cancer, emerging because of cell degradation. It is visualized using computed tomography (CT) and positron emission tomography (PET). Segmentation refers to the process of separating the desired object from the background and other elements in an image. In this study, CT images obtained from lymphoma patients were segmented using U-Net, a deep learning-based segmentation model. The test results achieved were a 0.83 Dice Similarity Coefficient (DSC), 0.73 Jaccard Index (JI), an average Hausdorff Distance (HD) of 15.81 mm for neck axial CT images, and a 0.75 DSC, 0.64 JI, and an average HD of 30.18 mm for neck coronal CT images. The detailed statistical and visual analyses demonstrated that the lymphoma lesion segmentation was successfully performed on neck coronal and axial CT images using U-Net.

Adrenal lesions refer to abnormalities or growths that occur in the adrenal glands, which are located on top of each kidney. These lesions can be benign or malignant and can affect the function of the adrenal glands. This paper presents a study on adrenal tumor segmentation using a modified U-Net model with various parameter selection strategies. The study investigates the effect of fine-tuning parameters, including k-fold values and batch sizes, on segmentation performance. Additionally, the study evaluates the effectiveness of different preprocessing techniques, such as Discrete Wavelet Transform (DWT), Contrast Limited Adaptive Histogram Equalization (CLAHE), and Image Fusion, in enhancing segmentation accuracy. The results show that the proposed model outperforms the original U-Net model, achieving the highest scores for Dice, Jaccard, sensitivity, and specificity scores of 0.631, 0.533, 0.579, and 0.998, respectively, on the T1-weighted dataset with DWT applied. These results highlight the importance of parameter selection and preprocessing techniques in improving the accuracy of adrenal tumor segmentation using deep learning.