International Journal of Education and Management Engineering (IJEME)
IJEME Vol. 12, No. 5, 8 Oct. 2022
Cover page and Table of Contents: PDF (size: 667KB)
Diagnosis of Skin Cancer Using Machine Learning and Image Processing Techniques
Full Text (PDF, 667KB), PP.38-44
Views: 0 Downloads: 0
Author(s)
Prashant Kaler
1,*
Shilpa Kodli
1
Sudhir Anakal
1
Index Terms
Dermoscopic Images, Machine Learning, Convolutional Neural Networks, Skin Lesion, ResNet-50.
Abstract
Skin Lesion is a part of the skin that can be caused by abnormal growth in the epithelium layer on the skin. There are nine types of skin lesion like Actinic Keratoses (AK), Basal Cell Carcinoma (BCC), Dermatofibroma (DF), Melanoma (MEL), Melanocytic Nevi (MV), Benign Keratosis (BK), Vascular Lesions (VASC), Squamous Cell Carcinoma (SCC), and Pigmented Benign Keratosis (PBK). The aim of this study is to spotlight on the problem of skin lesion classification based on early detection of the disease using deep learning techniques. This approach is used to work out the problem of classifying a dermoscopic image. The dermoscopic is a digital device; in this case Smartphone is attached to a lens and collects the images through the device. The proposed spotlight is built in the region of using Convolutional neural network architecture and ResNet-50 module is used to predict Skin-Lesion classification. The dataset used in this research was taken from kaggle repository. The proposed work uses ResNet-50 CNN model which has yielded 93% of accuracy for detecting Skin Cancer, previous work was carried out using Visual Geometry Group model which yielded 73% accuracy. In the proposed work we have considered 25,000 images of skin lesion. Hence we are able to attain this accuracy with more reliable Machine Learning algorithms compared to the previous work.
Cite This Paper
Prashant Kaler, Shilpa Kodli, Sudhir Anakal, "Diagnosis of Skin Cancer Using Machine Learning and Image Processing Techniques", International Journal of Education and Management Engineering (IJEME), Vol.12, No.5, pp. 38-44, 2022. DOI:10.5815/ijeme.2022.05.05
Reference
[1]Adria Romero Lopez, Xavier Giro-i-Nieto Universitat Politecnica de Catalunya Barcelona, Catalunya, Spain, “Skin Lesion Classification from Dermoscopic Images Using Deep Learning Techniques”.
[2]Ranpreet Kaur, Hamid Gholam Hosseini, Roopak Sinha and Maria Linden, “Melanoma Classification Using a Novel Deep Convolutional Neural Network with Dermoscopic Images”.
[3]Manu Goyal, Amanda Oakley, Priyanka Bansal, Darren Dancey and Moi Hoon Yap, “Skin Lesion Segmentation in Dermoscopic Images With Ensemble Deep Learning Methods”.
[4]Julie Ann A. Salido and Conrado Ruiz Jr, “Using Deep Learning to Detect Melanoma in Dermoscopy Images”.
[5]Haseeb younis, Muhammad Hamza Bhatti, Muhammad Azeem, “Classification Of Skin Cancer Dermoscopic Images Using Transfer Learning”.
[6]Dr. Ahlam Fadhil Mahmood, Hameed Abdulaziz Mahmood, “Appending global to local features for skin lesion classification on dermoscopic images”.
[7]Neema M, Arya S Nair, Annette Joy, Amal Pradeep Menon, Asiya Haris, “Skin Cancer Detection using Deep Learning”.
[8]Ilker Ali Ozkan, Murat Koklu, “Skin lesion classification using Machine Learning Algorithms”.
[9]R.D.Seeja, A.Suresh “Melanoma Segmentation and Classification using Deep Learning”.
[10]Bhuvaneshwari Shetty, Roshan Fernandes, Anisha P Rodrigues, and Kuruva Lakshmanna, “Skin Lesion Classification of Dermoscopic images using Machine Learning and Convolutional Neural Network”.
[11]H. Kittler, H. Pehamberger, K. Wolff, and M. Binder, “Diagnostic accuracy of Dermoscopy”.
[12]E.H.Page, “Description of skin lesion” https://google/m9ybFp.
[13]Skin Cancer Foundation. (June 2017). [Online]. Available: http://www.skincancer.org/skin-cancer-information/melanoma.
[14]N. K. Mishra and M. E. Celebi. ―An overview of melanoma detection in dermoscopy images using image processing and machine learning,‖ eprint arXiv: 1601.07843 2016.
[15]A. A. Abder-Rahman and T. M. Deserno, ―A systematic review of automated melanoma detection in dermatoscopic images and its ground truth data,‖ in Proc. SPIE, Medical Imaging 2012: Image Perception, Observer Performance, and Technology Assessment, 2012, vol. 8318.
[16]“Usage of objectives,” https://keras.io/objectives/.
[17]Sudhir Anakal, P Sandhya, "Decision Support System for Drug-Drug Interaction Pertaining to COPD and its Comorbidities", International Journal of Education and Management Engineering (IJEME), Vol.12, No.2, pp. 1-6, 2022. DOI: 10.5815/ijeme.2022.02.01