Detección de melanomas de piel malignos mediante procesamiento digital de imágenes usando redes neuronales convolucionales

dc.contributorMateus, Armando
dc.contributorCamacho, Edgar Camilo
dc.contributorGuillermo Guarnizo, José
dc.contributorhttps://orcid.org/ 0000-0003-4938-2233
dc.contributorhttps://orcid.org/ 0000-0002-8401-4949
dc.contributorhttps://orcid.org/ 0000-0002-6084-2512
dc.contributorhttps://orcid.org/ 0000-0002-2399-4859
dc.contributorUniversidad Santo Tomás
dc.creatorRiaño Borda, Sebastian
dc.date.accessioned2022-06-30T20:36:38Z
dc.date.available2022-06-30T20:36:38Z
dc.date.created2022-06-30T20:36:38Z
dc.date.issued2022-06-30
dc.identifierRiaño Borda, S. (2022). Detección de melanomas de piel malignos mediante procesamiento digital de imágenes usando redes neuronales convolucionales. [Trabajo de Grado, Universidad Santo Tomás]. Repositorio institucional.
dc.identifierhttp://hdl.handle.net/11634/45517
dc.identifierreponame:Repositorio Institucional Universidad Santo Tomás
dc.identifierinstname:Universidad Santo Tomás
dc.identifierrepourl:https://repository.usta.edu.co
dc.description.abstractThis project aims to design a neural network for the recognition of melanomas (a type of skin cancer), through the use of a technique known as convolutional neural networks, mostly used in artificial vision (a branch of artificial intelligence), applied in the recognition of patterns on moles on the skin and determine the existence of a malignant melanoma, or not, from a limited dataset. For this, the convolutional network designed and trained to classify melanomas is made up of convolution and pooling layers stacked together to form the proposed network, a "fully connected layer" and a classifier with 1 or 2 outputs, and is parameterized with different values ​​in characteristics such as the dropout, the size of the filters, among others, performing the training in 5 different stages or experiments. The dataset proposed for the training of CNN (Convolutional Neural Networks) is the largest public collection of demoscopic images of skin lesions, provided free of charge by the "International Skin Imaging Collaboration (ISIC)", an effort to improve the diagnosis of melanomas, sponsored by the “International Society for Digital Imaging of the Skin (ISDIS)”. The purpose of this project is to design a convolutional neural network with a high level of precision that helps medical professionals with the diagnosis of melanomas, in this case it was possible to achieve an accuracy of up to 87.82% with the network designed with the best performance.
dc.languagespa
dc.publisherUniversidad Santo Tomás
dc.publisherMaestría Ingeniería Electrónica
dc.publisherFacultad de Ingeniería Electrónica
dc.relationF. L. Marqués, «Clinic cloud,» [En línea]. Available: https://clinic cloud.com/blog/aplicaciones-de-la-tecnologia-en-la-salud/. [Último acceso: 15 04 2022].
dc.relationC. TI, «Canales TI,» 10 06 2020. [En línea]. Available: https://itcomunicacion.com.mx/el uso-de-la-tecnologia-en-la-medicina/. [Último acceso: 15 04 2022].
dc.relationS. Lee, H. Huang y M. Zelen, «Early detection of disease and scheduling of screening examinations,» Statistical Methods in Medical Research, vol. 13, nº 6, pp. 443-456, 2004.
dc.relationO. T. Jones, C. K. Ranmuthu, P. N. Hall, G. Funston y F. M. Walter, «Recognising Skin Cancer in Primary Care,» Advances in Therapy, vol. 37, nº 1, p. 603–616, 2020.
dc.relationC. Garbe, K. Peris, A. Hauschild, P. Saiag, M. Middleton, L. Bastholt, J.-J. Grob, J. Malvehy, J. Newton-Bishop, A. J. Stratigos, H. Pehamberger y A. M. Eggermont, «Diagnosis and treatment of melanoma. European consensus-based interdisciplinary guideline – Update 2016,» European Journal of Cancer, vol. 63, pp. 201-217, 2016.
dc.relationI. P. Santos, R. van Doorn y P. Caspers, «Improving clinical diagnosis of early-stage cutaneous melanoma based on Raman spectroscopy,» British Journal of Cancer, vol. 119, p. 1339–1346, 2018.
dc.relationThe International Skin Imaging Collaboration, «ISIC,» [En línea]. Available: https://www.isic-archive.com/#!/topWithHeader/onlyHeaderTop/gallery. [Último acceso: January 2020].
dc.relationBiblioteca Nacional de Medicina de EE. UU. , «Lunar | Nevos | MedlinePlus en español,» [En línea]. Available: https://medlineplus.gov/spanish/moles.html. [Último acceso: 08 09 2021].
dc.relationAmerican Cancer Society, «Estadísticas importantes sobre el cáncer de piel tipo melanoma,» [En línea]. Available: https://www.cancer.org/es/cancer/cancer-de-piel-tipo melanoma/acerca/estadisticas-clave.html. [Último acceso: 09 09 2021].
dc.relationBiblioteca Nacional de Medicina de EE. UU. , «Melanoma: MedlinePlus en español,» [En línea]. Available: https://medlineplus.gov/spanish/melanoma.html. [Último acceso: 08 09 2021].
dc.relationAmerican Cancer Society, «Etapas del cáncer de piel tipo melanoma,» [En línea]. Available: https://www.cancer.org/es/cancer/cancer-de-piel-tipo-melanoma/deteccion diagnostico-clasificacion-por-etapas/clasificacion-por-etapas-el-cancer-de-piel-tipo melanoma.html. [Último acceso: 09 09 2021].
dc.relationJ. A. Avilés‐Izquierdo, C. Ciudad‐Blanco, A. Sánchez‐Herrero, A. Mateos‐Mayo, L. M. Nieto‐Benito y E. Rodríguez‐Lomba, «Dermoscopy of cutaneous melanoma metastases: A color-based pattern classification,» Journal of Dermatology, vol. 46, nº 7, pp. 564-569, 2019.
dc.relationV. Teigens, Inteligencia Artificial General, Cambridge Stanford Books, 2000.
dc.relationV. Advany, «What is Artificial Intelligence? How does AI work, Types and Future of it?,» 19 Octubre 2021. [En línea]. Available: https://www.mygreatlearning.com/blog/what-is artificial-intelligence/#comments. [Último acceso: 25 Noviembre 2021].
dc.relationS. Khan, H. Rahmani, S. A. A. Shah y M. Bennamoun, A Guide to Convolutional Neural Networks for Computer Vision, Morgan & Claypool, 2018.
dc.relationA. Hintze, «goverment technology,» 14 11 2016. [En línea]. Available: https://www.govtech.com/computing/understanding-the-four-types-of-artificial intelligence.html#:~:text=2.-,Limited%20memory,and%20monitoring%20them%20over% 20time.. [Último acceso: 10 04 2022].
dc.relationGoogle, «Google Trends,» [En línea]. Available: https://trends.google.es/trends/explore?date=all&q=Convolutional%20neural%20network, deep%20learning,machine%20learning. [Último acceso: Agosto 2021].
dc.relationR. Wason, «Deep learning: Evolution and expansion,» Cognitive Systems Research, vol. 52, pp. 701-708, 2018.
dc.relationW. Liu, Z. Wang, X. Liu, N. Zeng, Y. Liu y F. Alsaadi, «A survey of deep neural network architectures and their applications,» Neurocomputing, vol. 234, pp. 11-26, 2017.
dc.relationY. Guo, Y. Liu, A. Oerlemans, S. Lao, S. Wu y M. S. Lew, «Deep learning for visual understanding: A review,» Neurocomputing, vol. 187, pp. 27-48, 2016.
dc.relationR. Zhao, R. Yan, Z. Chen, K. Mao, P. Wang y R. X. Gao, «Deep learning and its applications to machine health monitoring,» Mechanical Systems and Signal Processing, vol. 115, pp. 213-237, 2019.
dc.relationF. Ercal, A. Chawla, W. Stoecker, H.-C. Lee y R. Moss, «Neural Network Diagnosis of Malignant Melanoma From Color Images,» IEEE Transactions on Biomedical Engineering, vol. 41, nº 9, pp. 837-845, 1994.
dc.relationP. Vannoorenberghe, O. Colot y D. De Brucq, «Dempster-Shafer's theory as an aid to color information processing. Application to melanoma detection in dermatology,» de Proceedings 10th International Conference on Image Analysis and Processing, Venice, Italy, 1999.
dc.relationL. Yu, H. Chen, Q. Dou, J. Qin y P.-A. Heng, «Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks,» IEEE TRANSACTIONS ON MEDICAL IMAGING, vol. 36, nº 4, pp. 994-1004, 2017.
dc.relationY. Yuan, M. Chao y Y.-C. Lo, «Automatic Skin Lesion Segmentation Using Deep Fully Convolutional Networks with Jaccard Distance,» IEEE TRANSACTIONS ON MEDICAL IMAGING, vol. 36, pp. 1876-1886, 2017.
dc.relationN. Codella, Q.-B. Nguyen, S. Pankanti, D. Gutman, B. Helba, A. Halpern y J. R. Smith, «Deep learning ensembles for melanoma recognition in dermoscopy images,» IBM Journal of Research and Development, vol. 21, pp. 5:1-5:15, 2017.
dc.relationI. González-Díaz, «DermaKNet: Incorporating the knowledge of dermatologists to Convolutional Neural Networks for skin lesion diagnosis,» IEEE Journal of Biomedical and Health Informatics, vol. 23, nº 2, pp. 547-559, 2018.
dc.relationE. Nasr-Esfahani, S. Samavi, N. Karimi y S. Soroushmehr, «Melanoma Detection by Analysis of Clinical Images Using Convolutional Neural Network,» de 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando, 2016.
dc.relationM. u. Rehman, S. H. Khan, S. M. D. Rizvi, Z. Abbas y A. Zafar, «Classification of Skin Lesion by Interference of Segmentation and Convolotion Neural Network,» de 2018 2nd International Conference on Engineering Innovation (ICEI), Bangkok, 2018.
dc.relationZ. Yu, D. Ni, S. Chen, J. Qin, S. Li, T. Wang y B. Lei, «Hybrid dermoscopy image classification framework based on deep convolutional neural network and Fisher vector,» de 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), Melbourne, 2017.
dc.relationS. Sigurdsson, P. A. Philipsen, L. K. Hansen, J. Larsen, M. Gniadecka y H. C. Wulf, «Detection of skin cancer by classification of Raman spectra,» IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, vol. 51, nº 10, pp. 1784 - 1793, 2004.
dc.relationI. Pirnog, R. O. Preda, C. Oprea y C. Paleologu, «Automatic lesion segmentation for melanoma diagnostics in macroscopic images,» de 23rd European Signal Processing Conference (EUSIPCO), Nice, 2015.
dc.relationR. Kasmi y K. Mokrani, «Classification of malignant melanoma and benign skin lesions: implementation of automatic ABCD rule,» IET Image Processing, vol. 10, nº 6, pp. 448- 455, 2016.
dc.relationJ. R. Varatharaj, N. J, P. R y A. K. L, «Detection of melanoma skin cancer using digital camera images,» ARPN Journal of Engineering and Applied Sciences, vol. 10, pp. 3082- 3085, 2015.
dc.relationK. Shimizu, H. Iyatomi, . M. E. Celebi, K.-A. Norton y M. Tanaka, «Four-Class Classification of Skin Lesions With Task Decomposition Strategy,» IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, vol. 62, nº 1, pp. 274 - 283, 2014.
dc.relationM. Sadeghi, T. K. Lee, D. McLean, H. Lui y M. S. Atkins, «Detection and Analysis of Irregular Streaks in Dermoscopic Images of Skin Lesions,» Detection and Analysis of Irregular Streaks in Dermoscopic Images of Skin Lesions, vol. 32, nº 5, pp. 849 - 861, 2013.
dc.relationY. Gu, Z. Ge, C. P. Bonnington y J. Zhou, «Progressive Transfer Learning and Adversarial Domain Adaptation for Cross-Domain Skin Disease Classification,» IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFOMATICS, vol. 24, nº 5, pp. 1379 - 1393, 2020.
dc.relationQ. Zhou, Y. Shi, Z. Xu, R. Qu y G. Xu, «Classifying Melanoma Skin Lesions Using Convolutional Spiking Neural Networks With Unsupervised STDP Learning Rule,» IEEE Access, vol. 8, pp. 101309 - 101319, 2020.
dc.relationL. Wei, K. Ding y H. Hu, «Automatic Skin Cancer Detection in Dermoscopy Images based on Ensemble Lightweight Deep Learning Network,» IEEE Access, vol. 8, pp. 99633 - 99647, 2020.
dc.relationQ. Zhou, C. Ren y S. Qi, «An Imbalanced R-STDP Learning Rule in Spiking Neural Networks for Medical Image Classification,» IEEE Access , vol. 8, pp. 224162 - 224177, 2020.
dc.relationA. A. Adegun y S. Viriri, «Deep Learning-Based System for Automatic Melanoma Detection,» IEEE Access, vol. 8, pp. 7160 - 7172, 2019.
dc.relationS. Albahli, N. Nida, A. Irtaza, M. H. Yousaf y M. T. Mahmood, «Melanoma Lesion Detection and Segmentation Using YOLOv4-DarkNet and Active Contour,» IEEE Access, vol. 8, pp. 198403 - 198414, 2020.
dc.relationQ. Wang, L. Sun, Y. Wang, M. Zhou, M. Hu, J. Chen, Y. Wen y Q. Li, «Identification of Melanoma From Hyperspectral Pathology Image Using 3D Convolutional Networks,» IEEE Transactions on Medical Imaging , vol. 40, nº 1, pp. 218 - 227, 2021.
dc.relationK. Thurnhofer-Hemsi, E. López-Rubio, E. Domínguez y D. A. Elizondo , «Skin Lesion Classification by Ensembles of Deep Convolutional Networks and Regularly Spaced Shifting,» IEEE Access, vol. 9, pp. 112193 - 112205, 2021.
dc.relationM. Goyal, A. Oakley, P. Bansal, D. Dancey y M. H. Yap, «Skin Lesion Segmentation in Dermoscopic Images With Ensemble Deep Learning Methods,» IEEE Access, vol. 8, pp. 4171-4181, 2020.
dc.relationL. Ichim y D. Popescu, «Melanoma Detection Using an Objective System Based on Multiple Connected Neural Networks,» IEEE Access, vol. 8, pp. 179189-179202, 2020.
dc.relationL. Talavera-Martínez, P. Bibiloni y M. González-Hidalgo, «Hair Segmentation and Removal in Dermoscopic Images Using Deep Learning,» IEEE Access, vol. 9, pp. 2694- 2704, 2021.
dc.relationA. Gong, X. Yao y W. Lin, «Dermoscopy Image Classification Based on StyleGANs and Decision Fusion,» IEEE Access, vol. 8, pp. 70640-70650, 2020.
dc.relationT.-C. Pham, A. Doucet, C.-M. Luong, C.-T. Tran y V.-D. Hoang, «Improving Skin-Disease Classification Based on Customized Loss Function Combined With Balanced Mini-Batch Logic and Real-Time Image Augmentation,» IEEE Access, vol. 8, pp. 150725-150737, 2020.
dc.relationB. Zhang, Z. Wang, J. Gao, C. Rutjes, K. Nufer, D. Tao, D. D. Feng y S. W. Menzies, «Short-Term Lesion Change Detection for Melanoma Screening With Novel Siamese Neural Network,» IEEE Transactions on Medical Imaging, vol. 40, nº 3, pp. 840-851, 2021.
dc.relationH. Arab, L. Chioukh, M. Dashti Ardakani, S. Dufour y S. O. Tatu, «Early-Stage Detection of Melanoma Skin Cancer Using Contactless Millimeter-Wave Sensors,» IEEE Sensors Journal, vol. 20, nº 13, pp. 7310-7317, 2020.
dc.relationL. Song, J. Lin, Z. J. Wang y H. Wang, «An End-to-End Multi-Task Deep Learning Framework for Skin Lesion Analysis,» IEEE Journal of Biomedical and Health Informatics, vol. 24, nº 10, pp. 2912-2921, 2020.
dc.relationR. Rastghalam, H. Danyali, M. S. Helfroush, M. E. Celebi y M. Mokhtari, «Skin Melanoma Detection in Microscopic Images Using HMM-Based Asymmetric Analysis and Expectation Maximization,» IEEE Journal of Biomedical and Health Informatics, vol. 25, nº 9, pp. 3486-3497, 2021.
dc.relationM. A. Khan, K. Muhammad, M. Sharif, T. Akram y V. H. C. d. Albuquerque, «Multi-Class Skin Lesion Detection and Classification via Teledermatology,» IEEE Journal of Biomedical and Health Informatics, vol. 25, nº 12, pp. 4267-4275, 2021.
dc.relationnovaderma, «novaderma CLINICA DERMATOLOGICA,» [En línea]. Available: https://www.clinicanovaderma.com/la-dermatoscopia-digital/. [Último acceso: 08 2021].
dc.relationE. Galán y D. Puerto, Manual para la detección temprana del cancer de piel y recomendaciones para la disminución de exposición a radiación ultravioleta, Bogotá: Instituto Nacional de Cancerología ESE, 2015.
dc.relationA. Karpathy , F.-F. Li, J. Johnson y S. Yeung, «CS231n: Convolutional Neural Networks for Visual Recognition.,» Stanford CS class, 2016-2019. [En línea]. Available: http://cs231n.github.io/. [Último acceso: January 2020].
dc.relationT. Guo, J. Dong, H. Li y Y. Gao, «Simple convolutional neural network on image classification,» de IEEE 2nd International Conference on Big Data Analysis (ICBDA)(, Beijing, 2017.
dc.relationS. ALBAWI, T. A. MOHAMMED y S. AL-ZAWI, «Understanding of a convolutional neural network,» de International Conference on Engineering and Technology (ICET), Antalya, 2017.
dc.relationR. Sarkar, C. C. Chatterjee y A. Hazra, «Diagnosis of melanoma from dermoscopic images using a deep depthwise separable residual convolutional network,» IET Image Processing, vol. 13, 2019.
dc.relationM. A. Khan, M. Sharif, M. Raza, A. Anjum, T. Saba y S. A. Shad, «Skin lesion segmentation and classification: A unified framework of deep neural network features fusion and selection,» Expert Systems, 2019.
dc.relationZ. Yu, X. Jiang, F. Zhou, J. Qin, D. Ni, S. Chen, B. Lei y T. Wang, «Melanoma Recognition in Dermoscopy Images via Aggregated Deep Convolutional Features,» IEEE Transactions on Biomedical Engineering, vol. 66, nº 4, pp. 1006-1016, 2019.
dc.relationK. Jayapriya y I. J. Jacob, «Hybrid fully convolutional networks-based skin lesion segmentation and melanoma detection using deep feature,» International Journal of Imaging Systems and Technology, 2019.
dc.relationA. Namozov y Y. I. Cho, «Convolutional Neural Network Algorithm with Parameterized Activation Function for Melanoma Classification,» de 2018 International Conference on Information and Communication Technology Convergence (ICTC), Jeju, Korea (South), 2018.
dc.relationJ. Yang, F. Xie, H. Fan, Z. Jiang y J. Liu, «Classification for Dermoscopy Images Using Convolutional Neural Networks Based on Region Average Pooling,» IEEE Access, vol. 6, pp. 65130-65138, 2018.
dc.relationY. Li y L. Shen, «Skin Lesion Analysis towards Melanoma Detection Using Deep Learning Network,» Sensors, vol. 18, nº 2, p. 556, 2018.
dc.relationP. Tang, Q. Liang, X. Yan, S. Xiang y D. Zhang, «GP-CNN-DTEL: Global-Part CNN Model With Data-Transformed Ensemble Learning for Skin Lesion Classification,» IEEE Journal of Biomedical and Health Informatics, vol. 24, nº 10, pp. 2870 - 2882, 2020.
dc.relationR. Ashraf, S. Afzal, A. U. Rehman, S. Gul, J. Baber, M. Bakhtyar, I. Mehmood, O.-Y. Song y M. Maqsood, «Region-of-Interest Based Transfer Learning Assisted Framework for Skin Cancer Detection,» IEEE Access, vol. 8, pp. 147858 - 147871, 2020.
dc.relationH. Wu, J. Pan, Z. Li, Z. Wen y J. Qin, «Automated Skin Lesion Segmentation Via an Adaptive Dual Attention Module,» IEEE Transactions on Medical Imaging, vol. 40, nº 1, pp. 357-370, 2021.
dc.relationY. Jiang, S. Cao, S. Tao y H. Zhang, «Skin Lesion Segmentation Based on Multi-Scale Attention Convolutional Neural Network,» IEEE Access, vol. 8, pp. 122811-122825, 2020.
dc.relationA. Gong, X. Yao y W. Lin, «Classification for Dermoscopy Images Using Convolutional Neural Networks Based on the Ensemble of Individual Advantage and Group Decision,» IEEE Access, vol. 8, p. 2020, 2020.
dc.relationJ. Zhang, Y. Xie, Y. Xia y C. Shen, «Attention Residual Learning for Skin Lesion Classification,» IEEE Transactions on Medical Imaging, vol. 38, nº 9, pp. 2092-2103, 2019.
dc.rightshttp://creativecommons.org/licenses/by/2.5/co/
dc.rightsAbierto (Texto Completo)
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rightshttp://purl.org/coar/access_right/c_abf2
dc.rightsAtribución 2.5 Colombia
dc.rightsAtribución 2.5 Colombia
dc.rightsAtribución 2.5 Colombia
dc.titleDetección de melanomas de piel malignos mediante procesamiento digital de imágenes usando redes neuronales convolucionales


Este ítem pertenece a la siguiente institución