Chaos analysis of breast masses on dynamic magnetic resonance mammography

Abstract

Early detection of breast cancer plays an important role in reducing the mortality rate of the disease. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) of the breast is especially robust for the diagnosis of cancer in high risk women due to its high sensitivity. Despite excellent sensitivity of DCE-MRI, there is still some difficulty in the prediction of malignancy because of the lack of the optimum guideline for the interpretation of breast MR studies as well as the reported overlap in T1 and T2 relaxation times. In this research, we utilized chaos analysis and nonlinear dynamics in the interpretation of breast masses on DCE-MRI. The analysis is performed after injecting 11 patients with a contrast agent and 16 mass lesions were extracted from these patients. After pre-processing and segmentation stages, time series of the tumor has been generated for every slice image. The time series were further analyzed by extracting the largest Lyapunov exponent (LLE) for each mass lesion. Chaos features such as LLE are significant parameters which can improve the performance of classifiers in the early detection of breast cancer.