ENHANCING DIAGNOSTIC ACCURACY IN SKIN CANCER: A STUDY ON AI-BASED IMAGE CLASSIFICATION
Main Article Content
Keywords
Medical pictures, sorter, skin cancer, classification algorithms are all possible
Abstract
Background: Systems based on artificial intelligence (AI) are increasingly being used to process massive numbers of medical images in an automated and efficient manner. This practice eliminates the need for human experts to examine each photograph individually, with the ultimate diagnosis being made by a medical professional.
Objective: The primary objective of this study is to investigate various scenarios and classification approaches to identify improvements or poor performance in the evaluation metrics used for skin cancer detection.
Methods: Medical images depicting different types of skin cancer were sourced from the HAM10000 database. These images were used to train and test AI-based classification systems. Various machine learning models and techniques were employed to classify the images and assess their performance.
Results: The results of the classification of medical images corresponding to patients with skin cancer are presented. Performance metrics were analyzed to evaluate the effectiveness of different classification approaches and identify areas of improvement.
Conclusion: The study highlights the potential of AI-based systems in automating the classification of skin cancer images. Further research and refinement of classification models are necessary to enhance diagnostic accuracy and reliability.
References
2. Ceran, Y., Ergüder, H., Ladner, K., Korenfeld, S., Deniz, K., Padmanabhan, S., Wong, P., Baday, M., Pengo, T., & Lou, E. (2022). TNTdetect. AI: A deep learning model for automated detection and counting of tunneling nanotubes in microscopy images. Cancers, 14(19), 4958.
3. Combalia, M., Codella, N., Rotemberg, V., Carrera, C., Dusza, S., Gutman, D., Helba, B., Kittler, H., Kurtansky, N. R., & Liopyris, K. (2022). Validation of artificial intelligence prediction models for skin cancer diagnosis using dermoscopy images: the 2019 International Skin Imaging Collaboration Grand Challenge. The Lancet Digital Health, 4(5), e330-e339.
4. de Freitas Nader, G. P., Agüera-Gonzalez, S., Routet, F., Gratia, M., Maurin, M., Cancila, V., Cadart, C., Palamidessi, A., Ramos, R. N., & San Roman, M. (2021). Compromised nuclear envelope integrity drives TREX1-dependent DNA damage and tumour cell invasion. Cell, 184(20), 5230-5246. e5222.
5. Dubey, N., Johri, P., Sabharwal, M., & Rajesh, E. Pathology for gastrointestinal and hepatobiliary cancers using artificial intelligence. International Journal of Health Sciences(I), 12837-12850.
6. Guo, Q.-r., Zhang, L.-l., Liu, J.-f., Li, Z., Li, J.-j., Zhou, W.-m., Wang, H., Li, J.-q., Liu, D.-y., & Yu, X.-y. (2021). Multifunctional microfluidic chip for cancer diagnosis and treatment. Nanotheranostics, 5(1), 73.
7. Jojoa Acosta, M. F., Caballero Tovar, L. Y., Garcia-Zapirain, M. B., & Percybrooks, W. S. (2021). Melanoma diagnosis using deep learning techniques on dermatoscopic images. BMC Medical Imaging, 21, 1-11.
8. Kalaiarasan, R., Sridhar, S., & Yuvarai, M. (2022). Deep Learning-based Transfer Learning for Classification of Skin Cancer. 2022 International Conference on Applied Artificial Intelligence and Computing (ICAAIC),
9. Marquez-Sosa, M., & Muñoz-Gordillo, D. (2022). Characterization of Dermatoscopic Images for Melanoma Diagnosis utilizing the ABCD Criteria. 2022 IEEE ANDESCON,
10. Martorell, A., Martin-Gorgojo, A., Ríos-Viñuela, E., Rueda-Carnero, J., Alfageme, F., & Taberner, R. (2022). [Translated article] Artificial intelligence in dermatology: A threat or an opportunity? Actas dermo-sifiliograficas, 113(1), T30-T46.
11. Merchán Vargas, D. P., Navarro Báez, H., Barrero Pérez, J. G., & Castillo Bohórquez, J. A. (2021). Design of a tool for the classification of skin cancer images using Deep Neural Networks (DNN). Revista de Ciencia y Tecnología(21).
12. Montero-Valverde, J. A., Organista-Vázquez, V. D., Martínez-Arroyo, M., de la Cruz-Gámez, E., Hernández-Hernández, J. L., Hernández-Bravo, J. M., & Hernández-Hernández, M. (2023). Automatic Detection of Melanoma in Human Skin Lesions. International Conference on Technologies and Innovation,
13. Murar, M., Albertazzi, L., & Pujals, S. (2022). Advanced optical imaging-guided nanotheranostics towards personalized cancer drug delivery. Nanomaterials, 12(3), 399.
a. Riaño Borda, S., Guarnizo, J. G., Camacho Poveda, E. C., & Mateus Rojas, A. (2022). Automated Malignant Melanoma Classification Using Convolutional Neural Networks. Ciencia e Ingeniería Neogranadina, 32(2), 171-185.
14. Romo, V. A. V., Arguelles, S. V. T., Roman, J. D. D., Aceves, J. M. S., Morales, S. N., & Dino, C. G. N. (2023). Industry 4.0 in the Health Sector: System for Melanoma Detection. In Innovation and Competitiveness in Industry 4.0 Based on Intelligent Systems (pp. 43-70). Springer.
15. Saeed, S., Abdullah, A., Jhanjhi, N., Naqvi, M., & Nayyar, A. (2022). New techniques for efficiently k-NN algorithm for brain tumour detection. Multimedia Tools and Applications, 81(13), 18595-18616.
16. Sanchez-Reyes, L.-M., Rodriguez-Resendiz, J., Salazar-Colores, S., Avecilla-Ramírez, G. N., & Pérez-Soto, G. I. (2020). A High-accuracy mathematical morphology and multilayer perceptron-based approach for melanoma detection. Applied Sciences, 10(3), 1098.
17. Vargas, D. P. M., Báez, H. N., & Guillermo, J. de cáncer de piel utilizando Redes Neuronales Profundas (DNN).
18. Yélamos i Pena, O. (2019). Usefulness of in vivo reflectance confocal microscopy and automated videomosaics in the treatment and management of skin cancers= Ús de la microscòpia confocal de reflectància in vivo i dels videomosaics automatitzats en el tractament i seguiment dels càncers cutanis.
19. Yuan, Z., Puyol-Antón, E., Jogeesvaran, H., Smith, N., Inusa, B., & King, A. P. (2022). Deep learning-based quality-controlled spleen assessment from ultrasound images. Biomedical Signal Processing and Control, 76, 103724.
Article Sidebar
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
All articles published in JPTCP are licensed under Copyright Creative Commons Attribution-NonCommercial 4.0 International License.
Sergio Rodrigo Oliveira Souza Lima
MD, Department of Plastic Surgery, General Surgery Institute, Bahia Hospital, Brazil
Malvinder Kaur Mahinder Singh
General Practitioner with Special Interest (Dermatology), MBBS (MSU, Malaysia), MSc Clinical Dermatology (Cardiff, UK), Universal Dermatology & Vein Care (Part-Time Assistant), USA
Mohit Lakkimsetti
MBBS, Mamata Medical College, Khammam, India
Rabia Tehseen
Assistant Professor, Department of Computer Science, University of Central Punjab, Lahore, Pakistan
Tariq Rafique
Assistant Professor, Dadabhoy Institute of Higher Education, Karachi, Pakistan