AI Summary & Key Takeaways
AI InsightTherefore,it can be more convenient to use deep neural network technology in computer aided detectionsystems for mass detection from breast ultrasonography images.
📌 3 Key Takeaways
Abstract
In this study, mass detection from breast ultrasonography images was realized using deepneural networks. Dataset is a collection of publicly available ultrasonography images whichwere classified by their biopsy results. A total of 153 breast ultrasonography images thatcontain 89 malign and 64 benign tumours were used. Image augmentation and deep neuralnetwork software was developed using Python 3,5 environment on Visual Studio Community2017 IDE. A hybrid method including Keras ImageDataGenerator Class and imagepreprocessing techniques was introduced. Twenty images from both classes were randomlysplit from the dataset for testing after the network was designed. The network had a successrate of 100% at an epoch value of 70. The result of this study was compared with the result ofanother study that implemented type-2 fuzzy inference system with a success rate of 99,34%.As a conclusion, it can be expressed that the deep neural networks are more successful thanfuzzy inference systems in tumour detection from breast ultrasonography images. Therefore,it can be more convenient to use deep neural network technology in computer aided detectionsystems for mass detection from breast ultrasonography images.