Deep Multi-View Breast Cancer Detection: A Multi-View Concatenated Infrared Thermal Images Based Breast Cancer Detection System Using Deep Transfer Learning

Abstract

This paper simply presents a fully automated breast cancer detection system as “Deep Multi-view Breast cancer Detection” based on deep transfer learning. The deep transfer learning model i.e., Visual Geometry Group 16 (VGG 16) is used in this approach for the correct classification of Breast thermal images into either normal or abnormal. This VGG 16 model is trained with the help of Static as well as Dynamic breast thermal images dataset consisting of multi-view, single view breast thermal images. These Multi-view breast thermal images are generated in this approach by concatenating the conventional left, frontal and right view breast thermal images taken from the Database for Mastology Research with Infrared image for the first time in order to generate a more informative and complete thermal temperature map of breast for enhancing the accuracy of the overall system. For the sake of genuine comparison, three other popular deep transfer learning models like Residual Network 50 (ResNet50V2), InceptionV3 network and Visual Geometry Group 19 (VGG 19) are also trained with the same augmented dataset consisting of multi-view as well as single view breast thermal images. The VGG 16 based Deep Multi-view Breast cancer Detect system delivers the best training, validation as well as testing accuracies as compared to their other deep transfer learning models. The VGG 16 achieves an encouraging testing accuracy of 99% on the Dynamic breast thermal images testing dataset utilizing the multi-view breast thermal images as input. Whereas the testing accuracies of 95%, 94% and 89% are achieved by the VGG 19, ResNet50V2, InceptionV3 models respectively over the Dynamic breast thermal images testing dataset utilizing the same multi-view breast thermal images as input.

A Hybrid Model Particle Swarm Optimization Based Mammogram Classification Using Kernel Support Vector Machine

“…Also, it leads to a high risk of deaths in middle-aged and elderly women, particularly in countries of western world [1]. In Middle East countries, at least one out of every eight women is expected to develop this type of cancer at some point in their lives [2][3][4]. In the year 2012, around 14.1 million breast cancer patients were diagnosed in and around the world.…”

“…In the year 2012, around 14.1 million breast cancer patients were diagnosed in and around the world. With 8.2 million women dying as a result of the disease [2][3][4]. Early breast cancer detection and characterization has the potential to significantly improve treatment options and patient survival rate.…”

“…Nowadays, though we have lots of awareness, still we lag behind in identifying symptoms and causes of carcinoma. Of course, preventive measures and remedies are very less [4]. As a result, early detection is the most effective mode to develop the prediction of breast cancer.…”

“…In general, CAD systems aim to increase the likelihood of detecting and evaluating proper lesions [2][3][4]. The most important work in the image processing is to identify a group of significant attributes of images which are capable of distinguishing between normal and abnormal mammograms.…”

“…The CAD system can able to improve tumor abnormality prediction accuracy such as micro calcification, misrepresentation and masses. Sensitivity accuracy is increased by 12% to the radiologist by using the CAD system [2][3][4].…”