Internet of medical things embedding deep learning with data augmentation for mammogram density classification

• Published in: Microscopy research and technique Vol. 84; no. 9; pp. 2186 - 2194
• Main Authors: Sadad, Tariq, Khan, Amjad Rehman, Hussain, Ayyaz, Tariq, Usman, Fati, Suliman Mohamed, Bahaj, Saeed Ali, Munir, Asim
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01-09-2021; Wiley Subscription Services, Inc
• Subjects: Artificial neural networks; Breast cancer; breast density; cancer; Classification; computer‐aided diagnosis; Data augmentation; Deep learning; Density; Embedding; healthcare; Image analysis; Image enhancement; Image processing; Internet of medical things; Internet of Medical Things (IoMT); Machine learning; Mammography; masses; Medical imaging; Medical research; Neural networks; Transfer learning; mammography; breast density; cancer; computer-aided diagnosis; Internet of Medical Things (IoMT); healthcare; masses
• ISSN: 1059-910X; 1097-0029
• DOI: 10.1002/jemt.23773

Females are approximately half of the total population worldwide, and most of them are victims of breast cancer (BC). Computer‐aided diagnosis (CAD) frameworks can help radiologists to find breast density (BD), which further helps in BC detection precisely. This research detects BD automatically using mammogram images based on Internet of Medical Things (IoMT) supported devices. Two pretrained deep convolutional neural network models called DenseNet201 and ResNet50 were applied through a transfer learning approach. A total of 322 mammogram images containing 106 fatty, 112 dense, and 104 glandular cases were obtained from the Mammogram Image Analysis Society dataset. The pruning out irrelevant regions and enhancing target regions is performed in preprocessing. The overall classification accuracy of the BD task is performed and accomplished 90.47% through DensNet201 model. Such a framework is beneficial in identifying BD more rapidly to assist radiologists and patients without delay.
The study proposed and evaluated IoMT based breast density detection from mammogram images. Two pre‐trained CNN models: DenseNet201 and ResNet50 were applied through a transfer learning approach. Promising results achieved on a benchmark dataset. Graphical representation of the research architecture.