Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)Villamarín Muñoz, Julián AntonioPapamija Manzano, Ginna MildrethPiamba Muelas, Juan José2021-03-032021-03-032020-06-06http://repositorio.uan.edu.co/handle/123456789/2484Breast cancer is the second leading cause of death in the world. There are several methods to diagnose this disease, however, mammography has become the main exam to determine the presence of benign or malignant lesions in the breast. For their part, radiologist doctors use the BI-RADS protocol (Breast Imaging Report and Database System) to categorize the lesions according to the degree of suspicion and to inform the patient in simple terms of their respective diagnosis. Breast ultrasound is used as a complementary examination to mammography and is used in the first instance for the identification of suspicions that can be confirmed by better resolution images, thrown by the mammographer, a robust, high-cost equipment that uses ionizing radiation, for this reason, in this work, a software application for the automated calculation of BI-RADS1 ultrasound descriptors (echogenic pattern, orientation, edges, morphology) was analyzed, implementing computational algorithms in digital format of biomedical images captured by the use of an INTERSON USB ultrasound probe on an acoustic phantom of mom, with nodular lesions and processed on the Matlab platform, whose long-term objective is to support the qualitative analysis of the radiologist, to reduce the times of diagnosis and false positives.El cáncer de mama es la segunda causa de mortalidad en el mundo. Existen diversos métodos para diagnosticar esta enfermedad, sin embargo, la mamografía se ha convertido en el principal examen para determinar la presencia de lesiones benignas o malignas en la mama. Por su parte, los médicos radiólogos hacen uso del protocolo BI-RADS (Breast Imaging Report and Database System) para categorizar las lesiones según el grado de sospecha e informar al paciente en términos sencillos su respectivo diagnóstico. La ecografía mamaria, se emplea como examen complementario a la mamografía y se utiliza en primera instancia para la identificación de sospechas que pueden ser confirmadas mediante imágenes con mejor resolución, arrojadas por el mamógrafo, un equipo robusto de alto costo que emplea radiación ionizante, por esta razón, en el presente trabajo, se desarrolló una aplicación software para el cálculo automatizado de descriptores ecográficos BI-RADS1 (patrón ecogénico, orientación, bordes, morfología), implementando algoritmos computacionales basados en procesamiento digital de imágenes biomédicas captadas mediante el uso de una sonda ecográfica INTERSON USB sobre un phantom acústico de mama, con lesiones nodulares y procesadas en la plataforma Matlab, cuyo objetivo a largo plazo es brindar apoyo al análisis cualitativo del médico radiólogo, para disminuir los tiempos de diagnóstico y falsos positivos.spaAcceso abiertoBI-RADSCáncerSoftwareUltrasonidoTrabajo de grado (Pregrado y/o Especialización)BI-RADSCáncerSoftwareUltrasoundinfo:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2Kharel, Nabin & Alsadoon, Abeer & Prasad, P. & Elchouemi, A.. Early diagnosis of breast cancer using contrast limited adaptive histogram equalization (CLAHE) and Morphology methods. URL.Disponible en:https://www.researchgate.net/publication/316902635_Early_diagnosis_of_breast_cancer_using_contrast_limited_adaptive_histogram_equalization_CLAHE_and_Morphology_methods.(2017) 120-124. Fecha de acceso 26 de abril de 2020R., Meena & Bhuvaneshwari, K. & Divya, M. & Sri, K. & Begum, A.. (2017). Segmentation of thermal infrared breast images using K-means, FCM and EM algorithms for breast cancer detection.URL. Disponible en: https://www.researchgate.net/publication/322998849_Segmentation_of_thermal_infrared_breast_images_using_K-means_FCM_and_EM_algorithms_for_breast_cancer_detection. (2017) 1-4. Fecha de acceso 26 de abril de 2020Asuntha, A. & Srinivasan, Andy.Deep learning for lung Cancer detection and classification. Multimedia Tools and Applications. URL. Disponible en: https://www.researchgate.net/publication/338344242_Deep_learning_for_lung_Cancer_detection_and_classification/citation/download.79 (2020). Fecha de acceso 26 de abril de 2020.Sahar, Muzni & Nugroho, Hanung Adi & Tianur, Tianur & Ardiyanto, Igi & Choridah, Lina. Automated detection of breast cancer lesions using adaptive thresholding and morphological operation.URL. Disponible en: https://www.researchgate.net/publication/313870230_Automated_detection_of_breast_cancer_lesions_using_adaptive_thresholding_and_morphological_operation.(2016). 1-4. Fecha de acceso 26 de abril de 2020.Hamouda, Saeed & Ezz, Reda & Wahed, Mohammed. Enhancement Accuracy of Breast Tumor Diagnosis in Digital Mammograms. Journal of Biomedical Sciencies.URL. Disponible en: https://www.researchgate.net/publication/320761722_Enhancement_Accuracy_of_Breast_Tumor_Diagnosis_in_Digital_Mammograms. (2017). Vol 06. Fecha de acceso 26 de abril de 2020Hariraj, Venketkumar & Khairunizam, Wan & Vijean, Vikneswaran & Ibrahim, Zunaidi. (2017). An efficient data mining approaches for breast cancer detection and segmentation in mammogram. Journal of Advanced Research in Dynamical and Control Systems.URL disponible en: https://www.researchgate.net/publication/321127958_An_efficient_data_mining_approaches_for_breast_cancer_detection_and_segmentation_in_mammogram. Enero (2017). Vol 9. 185-194. fecha de acceso 26 de abril de 2020.Lestari, Dewi & Madenda, Sarifuddin & Ernastuti, Ernastuti & Prasetyo, Eri. Comparison of three segmentation methods for breast ultrasound images based on level set and morphological operations. International Journal of Electrical and Computer Engineering. URL. Disponible en: https://www.researchgate.net/publication/318091215_Comparison_of_three_segmentation_methods_for_breast_ultrasound_images_based_on_level_set_and_morphological_operations.(2017) Vol 7. 383-391. Fecha de acceso 26 de abril de 2020.Abdallah, Yousif & Elgak, Sami & Zain, Hosam & Rafiq, Mohammed Rafiq & Ebaid, Elabbas & Elnaema, Alaeldein. Breast cancer detection using image enhancement and segmentation algorithms. Biomedical Research. URL. Disponible en: https://www.researchgate.net/publication/329839535_Breast_cancer_detection_using_image_enhancement_and_segmentation_algorithms. (2018) 29. Fecha de acceso 26 de abril de 2020.Sarhan, Naglaa & Soliman, Naglaa & Abdalla, Mahmoud & Abd El-Samie, Fathi. An algorithm for pre-processing and segmentation of mammogram images. URL. Disponible en: https://www.researchgate.net/publication/312569417_An_algorithm_for_pre-processing_and_segmentation_of_mammogram_images. (2016) 187-190. Fecha de acceso 26 de abril de 2020.Jain, Nishant & Kumar, Vinod. Liver Ultrasound Image Segmentation Using Region-Difference Filters. Journal of Digital Imaging. URL. Disponible en: https://www.researchgate.net/publication/311916647_Liver_Ultrasound_Image_Segmentation_Using_Region-Difference_Filters. (2016). Fecha de acceso 26 de abril de 2020.Deepa, A. & Emmanuel, W.R. Sam. An efficient detection of brain tumor using fused feature adaptive firefly backpropagation neural network. Multimedia Tools and Applications. URL. Disponible en: https://www.researchgate.net/publication/328125994_An_efficient_detection_of_brain_tumor_using_fused_feature_adaptive_firefly_backpropagation_neural_network. Septiembre 2018. Fecha de acceso 26 de abril de 2020.Antonia Mihaylova, Veska Georgieva, Spleen segmentation in MRI sequence images using template matching and active contours, Procedia Computer Science,2018, Volume 131, Pages 15-22, ISSN 1877-0509, URL. Disponible en: (http://www.sciencedirect.com/science/article/pii/S1877050918305556)Duan Y, Li D, Stien LH, Fu Z, Wright DW, Gao Y, Automatic segmentation method for live fish eggs microscopic image analysis, Aquacultural Engineering, URL. Disponible en: https://www.sciencedirect.com/science/article/abs/pii/S0144860917301176. enero 2019. fecha de acceso 26 de abril de 2020.Rajesh C, Patil. A. S, Bhalchandra . Brain Tumour Extraction From MRI Image Using Matlab. En: internatonal journal electronics and communications (en línea). URL. Disponible en : http://www.hep.upatras.gr/class/download/psi_epe_iko/5-Brain-Tumour-Extraction-from-MRI-Images-Using-MATLAB.pdf .Vol 2, issue 1. septiembre, 2019. Fecha de acceso 26 de abril de 2020.instname:Universidad Antonio Nariñoreponame:Repositorio Institucional UANrepourl:https://repositorio.uan.edu.co/