Skip navigation

Repositorio Institucional Continental


Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.12394/7813
Title: Detection of microcalcifications in digital mammography images, using deep learning techniques, based on peruvian casuistry
Alternative Titles: Detección de microcalcificaciones en imágenes de mamografía digital, utilizando técnicas de aprendizaje profundo, basadas en la casuística peruana
Authors: Auccahuasi, W.
Delrieux, C.
Sernaque, F.
Flores, E.
Moggiano, N.
Keywords: Mamografía
Pantallas de rayos X
Publisher: Universidad Continental
Issue Date: 23-Nov-2019
Date available: 17-Jul-2020
Creation date: 2020
Bibliographic citation: Auccahuasi, W., Delrieux, C., Sernaque,, F., Flores, E., Moggiano, N. (2019). Detection of microcalcifications in digital mammography images, using deep learning techniques, based on peruvian casuistry. E-Health and Bioengineering Conference, EHB 2019, 1(1). https://doi. 10.1109/EHB47216.2019.8969906
DOI: 10.1109/EHB47216.2019.8969906
Abstract: Breast cancer is one of the most critical and aggressive pathologies suffered in the majority of women in the world, women in Peru are not free to suffer from this pathology, this paper presents a technique for detection of the malignant and benign microcalcifications, using digital mammography images, for the training and validation stage the use of a database containing images corresponding to microcalcifications classified as benign and malignant was used, these images of the database were created From mammographic images containing microcalcifications, these images correspond to Peruvian patients, the Python programming language was used with the TensorFlow and Keras library, with the use of them a deep learnig network was designed with which results were obtained that give a high probability of being used in the clinical environment, these results are the order of 0.94. This article presents as a proposed methodology the design of the database of the images used for the training of the deep learning network as well as the structure of the network.
Notes: El texto completo de este trabajo no está disponible en el Repositorio Institucional - Continental por restricciones de la casa editorial donde ha sido publicado.
Included in: https://ieeexplore.ieee.org/document/8969906
Access: Restringido
Source: Universidad Continental
Repositorio Institucional - Continental
Appears in Collections:Artículos de conferencias

Files in This Item:
There are no files associated with this item.
Show full item record


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.