Detection of Microcalcifications in Digital Mammography Images, using Deep Learning Techniques, based on Peruvian Casuistry

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.

[1]  Microcalcificaciones mamarias: revisión de los descriptores y categorías BI-RADS , 2013 .

[2]  David S. Fernández-McCann,et al.  Detección Automática de Microcalcificaciones en una Mamografía Digital, Usando Técnicas de Inteligencia Artificial , 2013 .

[3]  Yipeng Hu,et al.  Automatic segmentation of prostate MRI using convolutional neural networks: Investigating the impact of network architecture on the accuracy of volume measurement and MRI-ultrasound registration , 2019, Medical Image Anal..

[4]  Chunfeng Lian,et al.  Automated detection and classification of thyroid nodules in ultrasound images using clinical-knowledge-guided convolutional neural networks , 2019, Medical Image Anal..

[5]  Prakash Choudhary,et al.  A Study on Convolution Neural Network for Breast Cancer Detection , 2019, 2019 Second International Conference on Advanced Computational and Communication Paradigms (ICACCP).

[6]  Dong Ni,et al.  Multi-task learning for quality assessment of fetal head ultrasound images , 2019, Medical Image Anal..

[7]  Natan T. Shaked,et al.  TOP-GAN: Label-Free Cancer Cell Classification Using Deep Learning with a Small Training Set , 2018, ArXiv.

[8]  Pheng-Ann Heng,et al.  RMDL: Recalibrated multi-instance deep learning for whole slide gastric image classification , 2019, Medical Image Anal..

[9]  Philip J. Morrow,et al.  Breast pectoral muscle segmentation in mammograms using a modified holistically-nested edge detection network , 2019, Medical Image Anal..

[10]  Hao-Chun Lu,et al.  The Classification of Mammogram Using Convolutional Neural Network with Specific Image Preprocessing for Breast Cancer Detection , 2019, 2019 2nd International Conference on Artificial Intelligence and Big Data (ICAIBD).