Optimization of a Convolutional Neural Network for the Automated Diagnosis of Melanoma


  • Kemka Ihemelandu McDonogh School
  • Chukwuemeka Ihemelandu Mentor, Georgetown University




Melanoma, Convolutional neural network, Optimization, Diagnosis


The incidence of melanoma has been increasing rapidly over the past two decades, making melanoma a current public health crisis. Unfortunately, even as screening efforts continue to expand in an effort to ameliorate the death rate from melanoma, there is a need to improve diagnostic accuracy to decrease misdiagnosis. Artificial intelligence (AI) a new frontier in patient care has the ability to improve the accuracy of melanoma diagnosis. Convolutional neural network (CNN) a form of deep neural network, most commonly applied to analyze visual imagery, has been shown to outperform the human brain in pattern recognition. However, there are noted limitations with the accuracy of the CNN models. Our aim in this study was the optimization of convolutional neural network algorithms for the automated diagnosis of melanoma. We hypothesized that Optimal selection of the momentum and batch hyperparameter increases model accuracy. Our most successful model developed during this study, showed that optimal selection of momentum of 0.25, batch size of 2, led to a superior performance and a faster model training time, with an accuracy of ~ 83% after nine hours of training. We did notice a lack of diversity in the dataset used, with a noted class imbalance favoring lighter vs. darker skin tone. Training set image transformations did not result in a superior model performance in our study.


Download data is not yet available.

References or Bibliography



Elmore, J. G., Barnhill, R. L., Elder, D. E., Longton, G. M., Pepe, M. S., Reisch, L. M., Carney, P. A., Titus, L. J., Nelson, H. D., Onega, T., Tosteson, A., Weinstock, M. A., Knezevich, S. R., & Piepkorn, M. W. (2017). Pathologists' diagnosis of invasive melanoma and melanocytic proliferations: observer accuracy and reproducibility study. BMJ (Clinical research ed.), 357, j2813. https://doi.org/10.1136/bmj.j2813.

Merlino, G., Herlyn, M., Fisher, D. E., Bastian, B. C., Flaherty, K. T., Davies, M. A., Wargo, J. A., Curiel-Lewandrowski, C., Weber, M. J., Leachman, S. A., Soengas, M. S., McMahon, M., Harbour, J. W., Swetter, S. M., Aplin, A. E., Atkins, M. B., Bosenberg, M. W., Dummer, R., Gershenwald, J. E., Halpern, A. C., … Ronai, Z. A. (2016). The state of melanoma: challenges and opportunities. Pigment cell & melanoma research, 29(4), 404–416. https://doi.org/10.1111/pcmr.12475

Valueva, M.V.; Nagornov, N.N.; Lyakhov, P.A., Valuev G.V., Chervyakov N.I. (2020). Application of the residue number system to reduce hardware costs of the convolutional neural network implementation. Mathematics and Computers in Simulation. Elsevier BV, 177: 232–243.

Stuart J. Russell, Peter Norvig (2010) Artificial Intelligence: A Modern Approach, Third Edition, Prentice Hall ISBN 9780136042594

Doaa A. Shoieb, Sherin M. Youssef, and Walid M. Aly, (2016) "Computer-Aided Model for Skin Diagnosis Using Deep Learning," Journal of Image and Graphics, Vol. 4, No. 2, pp. 122-129. doi: 10.18178/joig.4.2.122-129

Kieffer, B., Babaie, M., Kalra, S. and Tizhoosh, H.R. (2017). Convolutional Neural Networks for Histopathology Image Classification: Training vs. Using Pre-Trained Networks. 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA).

Chee, Jerry, and Ping Li. 2020. “Understanding and Detecting Convergence for Stochastic Gradient Descent with Momentum.” arXiv [cs.LG]. arXiv. http://arxiv.org/abs/2008.12224.

Urbancek S, Fedorcova P, Tomkova J, Sutka R (2015) Misdiagnosis of Melanoma: A 7 Year Single-Center Analysis. Pigmentary Disorders 2: 208. doi:10.4172/2376-0427.1000208



How to Cite

Ihemelandu, K., & Ihemelandu, C. (2021). Optimization of a Convolutional Neural Network for the Automated Diagnosis of Melanoma. Journal of Student Research, 10(3). https://doi.org/10.47611/jsrhs.v10i3.2130



HS Research Articles