شماره ركورد كنفرانس :
5498
عنوان مقاله :
Fusion of Dermoscopic Datasets: A Method to Promote Performance of Deep Learning in Melanoma Detection
عنوان به زبان ديگر :
Fusion of Dermoscopic Datasets: A Method to Promote Performance of Deep Learning in Melanoma Detection
پديدآورندگان :
Taghilooniya Samira s.taghiloonia@student.alzahra.ac.ir Data mining laboratory, Alzahra University, Tehran, Iran , Keyvanpour Mohammad Reza keyvanpour@alzahra.ac.ir Department of Computer Engineering, Faculty of Engineering, Alzahra University, Tehran, Iran , Shojaedini Seyed Vahab Department of Biomedical Engineering, Iranian Research Organization for Science and Technology, Tehran, Iran
كليدواژه :
Skin cancer , Melanoma , Deep learning , Classification , Dataset fusion
عنوان كنفرانس :
اولين كنفرانس بين المللي و چهارمين كنفرانس ملي تجهيزات و فناوري هاي آزمايشگاهي
چكيده فارسي :
Skin cancer is one of the diseases that has spread a lot in recent years. The abnormal growth of skin cells causes this cancer. If this disease is diagnosed in the early stages, it can be easily treated and prevent the possible death of the patient. Therefore, artificial intelligence experts have made great efforts to identify and diagnose this disease with the help of computer-aided detection (CAD) systems. Based on this, machine learning-based approaches have become an efficient way to classify skin lesions. This paper presents a CAD system for classifying melanoma and nevus. We used the combination of two ISIC 2019 and ISIC 2020 datasets to overcome the data imbalance. A pre-trained model with extra layers is used to feature extraction and classify skin lesions. The proposed method achieves 94% sensitivity, 97% specificity, and 95% accuracy on test data.
