Yalçın, TolgaGürsel, Amira Tandirovic2025-01-062025-01-0620212757-9255https://search.trdizin.gov.tr/tr/yayin/detay/509317https://hdl.handle.net/20.500.14669/1274The practice of detecting skin cancer is based primarily on a visual examination by a dermatologist,\rfollowed by a series of tests for a more accurate diagnosis. The concept “the earlier cancer is detected in\rits natural history, the more effective the treatment is likely to be\" is also valid for skin cancer. Hence,\rany delayed or missed diagnosis can lead to a more severe clinical stage or, what's worse, death. On the\rother hand, the lack of biomarkers in clinical use brings about overdiagnosis and unnecessary biopsies.\rDL-CAD system seems to be an excellent candidate for improving diagnostic accuracy and reducing\runnecessary treatments. However, the vast majority of conventional CADs manipulate dermoscopic\rimages, which require not only costly equipment but also time-consuming processing. Despite the\rdifficulties with precision, state-of-the-art DL-CAD systems provide an interpretation using digital\rimages, requiring no expertise in cost-effective dermoscopic image capture and interpretation. Preprocessing\rmethods play a crucial role in solving this problem. This study presents results with regard to\rpre-processing steps to improve the images to be used in the diagnosis of the 5 most common skin cancer\rtypes for the proposed CNN based ResNet50 deep learning model. To the best of our knowledge it is the\rfirst time that ResNet50 deep-learning model has been utilized in diagnosis of skin cancer.trinfo:eu-repo/semantics/openAccessArticle11104109950931736