Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{199064,
        author = {MUTHUKUMARESAN V and MUKILAN K and GOKUL S and SANTHOSH S and KAVINMATHI B},
        title = {A Deep Learning Approach for Skin Cancer Classification Using Efficient NetB0 With Imbalance-Aware Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {15174-15179},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199064},
        abstract = {The number of skin cancer cases is going up everywhere. This is making people want better tools to help doctors find skin cancer early. Doctors can use computers to look at pictures of skin and find skin cancer. These computers are not always right. This is because the computers are not good at finding the skin cancer when there are more good skin pictures than bad skin pictures. To make this better we made a way to help the computers find skin cancer. We used a kind of computer program called EfficientNetB0. This program is good at looking at pictures and finding things. We used a lot of pictures of skin 11,720 pictures to help the computer learn. We also did some things to the pictures to help the computer find skin cancer better.
We did not want the computer to just find the skin and not the bad skin cancer so we told the computer to pay more attention to the bad skin cancer. We did this by making the computer think that finding skin cancer was more important. We used a way to help the computer learn and we made sure the computer was not learning too fast or too slow. We tried our way and it worked well. The computer was 73.6 percent of the time and it was good at finding the bad skin cancer. This is news for doctors and people, with skin cancer. Our new way can help doctors find skin cancer early. This can help people get better. We think that using EfficientNetB0 and our new way can help make finding skin cancer easier and faster for doctors.},
        keywords = {Skin Cancer Detection, Deep Learning, EfficientNetB0, Class Imbalance, Dermoscopic Image Classification, Medical Image Analysis, Computer-Aided Diagnosis},
        month = {April},
        }