Densely Convolutional Networks for Breast Cancer Classification with Multi-Modal Image Fusion

The international arab journal of information technology

article

Eman Hamdy¹  Osama Badawy¹ 

[1] College of Computing and Information Technology Arab Academy for Science

关键词: Breast cancer;    classification;    deep learning;    densenet;    diagnostic imaging;    multimodal imaging;   

DOI  :  10.34028/iajit/19/3A/6

学科分类：计算机科学（综合）

来源: Zarqa University

【 摘 要 】

Breast cancer is the main health burden worldwide. Cancer is located in the breast, starts when the cell growsunder control and begins as in-situ carcinoma and when spread into other parts known as invasive carcinoma. Breast cancermass can early be found by image modality when discovering mass early can easily diagnose and treated. Multimodalitiesused for the classification of breast cancer Such as mammography, ultrasound, and Magnetic resonance imaging. Two types offusion are used earlier fusion and later fusion. Early fusion it’s a simple relation between modalities while later fusion givesmore interest to fusion strategy to learn the complex relationship between various modalities as a result, can get highlyaccurate results when using the later fusion. When combining two image modalities (mammography, ultrasound) and using anexcel sheet containing the age, view, side, and status attribute associated with each mammographic image using DenseNet 201with Layer level fusion strategy as later fusion by making connections between the various paths and same path by usingConcatenated layer. Fusing at the feature level achieves the best performance in terms of several evaluation metrics(accuracy, recall, precision area under the curve, and F1 score) and performance.

【 授权许可】

Unknown