AI-Driven Detection of Skin Cancer Using Deep Neural Networks
Keywords:
AI-driven diagnosis, Cancer detection, Medical Imaging, Neural Networks, Skin CancerAbstract
This work presents a deep learning-based framework for automated skin cancer detection using dermoscopic images from the PH2 dataset, which comprises 200 high-resolution images. The methodology encompasses a two-stage process: initial lesion segmentation utilizing the U-Net architecture, followed by classification through the Inception V3 model. To enhance image quality and model performance, pre-processing techniques such as median filtering were applied to reduce noise, and data augmentation strategies including rotation, flipping, and scaling were employed to address dataset limitations. The implementation and training of the models were conducted on the Google Colab platform, leveraging its computational resources. The proposed system achieved a sensitivity of 92.5%, specificity of 93.75%, and an overall accuracy of 93.33%, indicating its efficacy in accurately identifying malignant lesions while minimizing false positives. These results underscore the potential of integrating advanced deep learning techniques with effective pre-processing and augmentation strategies in developing reliable computer-aided diagnostic tools for early skin cancer detection.
References
S. Poovizhi and Ganesh Babu Tr, “An efficient skin cancer diagnostic system using bendlet transform and support vector machine,” Anais Da Academia Brasileira De Ciencias, vol. 92, no. 1, Jan. 2020, doi: https://doi.org/10.1590/0001-3765202020190554
S. Poovizhi, R. Ganesh, and R. Praveena, “Certain investigations on melanoma detection using non-subsampled Bendlet transform with different classifiers,” Molecular & Cellular Biomechanics, vol. 18, no. 4, pp. 201–219, Jan. 2021, doi: https://doi.org/10.32604/mcb.2021.017984
T. Sreelatha, M. V. Subramanyam, and M. N. G. Prasad, “Early detection of skin cancer using melanoma segmentation technique,” Journal of Medical Systems, vol. 43, no. 7, May 2019, doi: https://doi.org/10.1007/s10916-019-1334-1
A. Soudani and W. Barhoumi, “An image-based segmentation recommender using crowdsourcing and transfer learning for skin lesion extraction,” Expert Systems with Applications, vol. 118, pp. 400–410, Mar. 2019, doi: https://doi.org/10.1016/j.eswa.2018.10.029
R. D. Seeja, and A. Suresh “Melanoma segmentation and classification using deep learning,” International Journal of Innovative Technology and Exploring Engineering, vol. 8, no. 12, pp. 2667–2672, Oct 2019, Available: https://www.ijitee.org/wp-content/uploads/papers/v8i12/L25161081219.pdf
B. N. Walker et al., “Dermoscopy diagnosis of cancerous lesions utilizing dual deep learning algorithms via visual and audio (sonification) outputs: Laboratory and prospective observational studies,” EBioMedicine, vol. 40, pp. 176–183, Feb. 2019, doi: https://doi.org/10.1016/j.ebiom.2019.01.028
X. Wang, X. Jiang, H. Ding, and J. Liu, “Bi-directional dermoscopic feature learning and multi-scale consistent decision fusion for skin lesion segmentation,” in IEEE Transactions on Image Processing, vol. 29, pp. 3039-3051, 2020, doi: https://doi.org/10.1109/TIP.2019.2955297
T. Y. Tan, L. Zhang, and C. P. Lim, “Intelligent skin cancer diagnosis using improved particle swarm optimization and deep learning models,” Applied Soft Computing, vol. 84, p. 105725, Nov. 2019, doi: https://doi.org/10.1016/j.asoc.2019.105725
A. Lembhe, P. Motarwar, R. Patil, and S. Elias, “Enhancement in skin cancer detection using image super resolution and convolutional neural network,” Procedia Computer Science, vol. 218, pp. 164–173, 2023, doi: https://doi.org/10.1016/j.procs.2022.12.412
D. Verma and Prajwala R, “Skin cancer cell detection using machine learning and image processing,” International Journal of Advanced Medical Sciences and Technology, vol. 5, no. 1, pp. 5–9, Dec. 2024, doi: https://doi.org/10.54105/ijamst.c3014.05011224
M. Hajiarbabi, “Skin cancer detection using multi-scale deep learning and transfer learning,” Journal of Medical Artificial Intelligence, vol. 6, no. 23, Nov. 2023, doi: https://doi.org/10.21037/jmai-23-67
I. A. Kandhro et al., “Performance evaluation of E-VGG19 model: Enhancing real-time skin cancer detection and classification,” Heliyon, vol. 10, no. 10, pp. e31488, May 2024, doi: https://doi.org/10.1016/j.heliyon.2024.e31488
P. Princy Magdaline and T. R. G. Babu, “Detection of lung cancer using novel attention gate residual U-Net model and KNN classifier from computer tomography images,” Journal of Intelligent & Fuzzy Systems, vol. 45, no. 4, pp. 6289–6302, Jul. 2023, doi: https://doi.org/10.3233/jifs-233787
Y. Pan et al., “Fundus image classification using Inception V3 and ResNet-50 for the early diagnostics of fundus diseases,” Frontiers in Physiology, vol. 14, Feb. 2023, doi: https://doi.org/10.3389/fphys.2023.1126780
I. A. Ozkan and M. Koklu, “Skin lesion classification using machine learning algorithms”, Int J. Intell Syst Appl Eng, vol. 5, no. 4, pp. 285–289, Dec. 2017, Available: https://ijisae.org/index.php/IJISAE/article/view/714
