Dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) is a sensitive imaging modality for the detection of breast cancer. Automated segmentation of breast lesions in DCE-MRI images is challenging due to inherent signal-to-noise ratios and high inter-patient variability. A novel 3D segmentation method based on FCM and MRF is proposed in this study. In this method, a MRI image is segmented by spatial FCM, firstly. And then MRF segmentation is conducted to refine the result. We combined with the 3D information of lesion in the MRF segmentation process by using segmentation result of contiguous slices to constraint the slice segmentation. At the same time, a membership matrix of FCM segmentation result is used for adaptive adjustment of Markov parameters in MRF segmentation process. The proposed method was applied for lesion segmentation on 145 breast DCE-MRI examinations (86 malignant and 59 benign cases). An evaluation of segmentation was taken using the traditional overlap rate method between the segmented region and hand-drawing ground truth. The average overlap rates for benign and malignant lesions are 0.764 and 0.755 respectively. Then we extracted five features based on the segmentation region, and used an artificial neural network (ANN) to classify between malignant and benign cases. The ANN had a classification performance measured by the area under the ROC curve of AUC=0.73. The positive and negative predictive values were 0.86 and 0.58, respectively. The results demonstrate the proposed method not only achieves a better segmentation performance in accuracy also has a reasonable classification performance.
Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) of breast yields high sensitivity but relatively
lower specificity. To improve diagnostic accuracy of DCE-MRI, we investigated the association between bilateral
asymmetry of kinetic features computed from the left and right breasts and breast cancer detection with the hypothesis that due to the growth of angiogenesis associated with malignant lesions, the average dynamic contrast enhancement computed from the breasts depicting malignant lesions should be higher than negative or benign breasts. To test this hypothesis, we assembled a database involving 130 DCE-MRI examinations including 81 malignant and 49 benign cases. We developed a computerized scheme that automatically segments breast areas depicted on MR images and computes kinetic features related to the bilateral asymmetry of contrast enhancement ratio between two breasts. An artificial neural network (ANN) was then used to classify between malignant and benign cases. To identify the optimal approach to compute the bilateral kinetic feature asymmetry, we tested 4 different thresholds to select the enhanced pixels (voxels) from DCE-MRI images and compute the kinetic features. Using the optimal threshold, the ANN had a classification performance measured by the area under the ROC curve of AUC=0.79±0.04. The positive and negative predictive values were 0.75 and 0.67, respectively. The study suggested that the bilateral asymmetry of kinetic features or contrast enhancement of breast background tissue could provide valuable supplementary information to distinguish between the malignant and benign cases, which can be fused into existing computer-aided detection schemes to improve classification performance.