Mammographic Mass Detection Based On Multi-scale Spatial Pyramid Ensemble

In recent years, with the improvement of living standard, people pay more and more attention to their health, which makes the doctor confront more and more heavily burden, especially for the radiologist abundant inspection not only increase their workload but also reduce the accuracy of inspection. Moreover, the rapid development of medical imaging technology make all parts of the body inspect more directly and clearly, which provides more favourable conditions for the computer-aided diagnosis of the medical imaging. This paper does the work on the basis of previous studies, which carry on research on mammograms as following:1. In order to solve problem that the suspicious regions detection in mammographic images, this paper proposed a detection approach that based on mulit-scale spatial pyramid ensemble. First, we cut the whole image into lots of patches which have different sizes. So we call it multi-scale. Then we extract the features from the patches. We send the traning data into classifier. And we send the testing data into the trained classifier. Finally, we ensemble the classification results. So that we can have the result of the detection.2. After the multi-scale spatial pyramid cutting. The number of the ROIs are far less than the number of the normal regions. In order to deal with the imbalanced data, we introduce the Multi-objective genetic algorithm so that we converted the problem into a multi-objective problem. In this chapter, we use NSGA-II to select the features we extract from the patches. Ultimately this method forecast a case which is ill or not and further to forecast which part the suspicious region belongs to, facilitated the following procedure.3. Mammogram has the features that personalized greatly, more interference informatio. To these problems, in this chapter, we introduce the model of the Convolutional Neural Network(CNN) model to learn the advanced feathures from the patches which based on the multi-scale spatial pyramid cutting. detection of breast cancer. Based on the detecting result, doctors can pay attention on only a local region than the whole; furthermore, the proposed algorithm can provide a useful method for other researcher studying on the detection of the breast cancer..