Karthikayani. K, Sadhana S, L. C, Suman A. Patil, Anandbabu Gopatoti, Shanta Phani
{"title":"Prediction of Skin Cancer using Convolutional Neural Network","authors":"Karthikayani. K, Sadhana S, L. C, Suman A. Patil, Anandbabu Gopatoti, Shanta Phani","doi":"10.1109/ICAISS55157.2022.10010936","DOIUrl":null,"url":null,"abstract":"Skin damage is one of the most fatal illnesses. Unassisted dissection and management at the beginning will result in it contacting other areas of the body. Due to the rapid progression of skin cells, it occurs when exposed to sunlight An automated system for skin sore recognition is expected to reduce effort, time, and human life for early detection. A technique for preventing skin cancer is based on both images and significant learning. An enhanced system is proposed in the paper for representing skin infections. In this study, nine types of skin illnesses were collected. It contains nine clinically significant skin cancers, such as actinic keratosis, basal cell carcinoma, innocuous keratosis, dermatofibromas, melanomas, nevus, seborrheic keratosis, and squamous cell carcinoma. Convolutional Neural Networks are used to classify skin diseases into various classes as well as diagnose the severity of them. In the diagnosis system, pictures are taken into consideration as well as significant learning is utilized. More pictures have also been added by using different methodologies. Finally, the deep learning approach also helps to ensure the task's precision. By using the proposed CNN procedure, an average accuracy of 96.12 percent is obtained.","PeriodicalId":243784,"journal":{"name":"2022 International Conference on Augmented Intelligence and Sustainable Systems (ICAISS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 International Conference on Augmented Intelligence and Sustainable Systems (ICAISS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICAISS55157.2022.10010936","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
Skin damage is one of the most fatal illnesses. Unassisted dissection and management at the beginning will result in it contacting other areas of the body. Due to the rapid progression of skin cells, it occurs when exposed to sunlight An automated system for skin sore recognition is expected to reduce effort, time, and human life for early detection. A technique for preventing skin cancer is based on both images and significant learning. An enhanced system is proposed in the paper for representing skin infections. In this study, nine types of skin illnesses were collected. It contains nine clinically significant skin cancers, such as actinic keratosis, basal cell carcinoma, innocuous keratosis, dermatofibromas, melanomas, nevus, seborrheic keratosis, and squamous cell carcinoma. Convolutional Neural Networks are used to classify skin diseases into various classes as well as diagnose the severity of them. In the diagnosis system, pictures are taken into consideration as well as significant learning is utilized. More pictures have also been added by using different methodologies. Finally, the deep learning approach also helps to ensure the task's precision. By using the proposed CNN procedure, an average accuracy of 96.12 percent is obtained.