Automatic extraction of pectoral muscle in the MLO view of mammograms.

A mammogram is the standard modality used for breast cancer screening. Computer-aided detection (CAD) approaches are helpful for improving breast cancer detection rates when applied to mammograms. However, automated analysis of a mammogram often leads to inaccurate results in the presence of the pectoral muscle. Therefore, it is necessary to first handle pectoral muscle segmentation separately before any further analysis of a mammogram. One difficulty to overcome when segmenting out pectoral muscle is its strong overlapping with dense glandular tissue which tampers with its extraction. This paper introduces an automated two-step approach for pectoral muscle extraction. The pectoral region is firstly estimated through segmentation by mean of a modified Fuzzy C-Means clustering algorithm. After contour validation, the final boundary is delineated through iterative refinement of edge point using average gradient. The proposed method is quite simple in implementation and yields accurate results. It was tested on a set of images from the MIAS database and yielded results which, compared to those of some state-of-the-art approaches, were better.

Zonal segmentation of prostate using multispectral magnetic resonance images.

PURPOSE: To investigate the performance of a new method of automatic segmentation of prostatic multispectral magnetic resonance images into two zones: the peripheral zone and the central gland. METHODS: The proposed method is based on a modified version of the evidential C-means clustering algorithm. The evidential C-means optimization process was modified to introduce spatial neighborhood information. A priori knowledge of the prostate's zonal morphology was modeled as a geometric criterion and used as an additional data source to enhance the differentiation of the two zones. RESULTS: Thirty-one clinical magnetic resonance imaging series were used to validate the method, and interobserver variability was taken into account in assessing its accuracy. The mean Dice Similarity Coefficient was 89% for the central gland and 80% for the peripheral zone, as validated by a consensus from expert radiologist segmentation. CONCLUSIONS: The method was statistically insensitive to variations in patient age, prostate volume and the presence of tumors, which increases its feasibility in a clinical context.

A non rigid registration and deformation algorithm for ultrasound & MR images to guide prostate cancer therapies.

Multimodality image registration is a critical issue in image-guided cancer ablation techniques. Focal therapies of prostate cancer are usually monitored using ultrasound imaging, while the dose planning is performed on MRI. In this study, a new multimodality images registration and deformation method, based on the Thin Plate Splines -Rigid Point Matching (TPS-RPM) algorithm, is introduced. The Method combines non-rigid mapping and interpolation to deform the images. Preliminary results obtained on phantom and clinical images showed that the registration is accurate and robust against landmarks initialization.

Combining a deformable model and a probabilistic framework for an automatic 3D segmentation of prostate on MRI.

PURPOSE: Accurate localization and contouring of prostate are crucial issues in prostate cancer diagnosis and/or therapies. Although several semi-automatic and automatic segmentation methods have been proposed, manual expert correction remains necessary. We introduce a new method for automatic 3D segmentation of the prostate gland from magnetic resonance imaging (MRI) scans. METHODS: A statistical shape model was used as an a priori knowledge, and gray levels distribution was modeled by fitting histogram modes with a Gaussian mixture. Markov fields were used to introduce contextual information regarding voxels' neighborhoods. Final labeling optimization is based on Bayesian a posteriori classification, estimated with the iterative conditional mode algorithm. RESULTS: We compared the accuracy of this method, free from any manual correction, with contours outlined by an expert radiologist. In 12 cases, including prostates with cancer and benign prostatic hypertrophy, the mean Hausdorff distance and overlap ratio were 9.94 mm and 0.83, respectively. CONCLUSION: This new automatic prostate MRI segmentation method produces satisfactory results, even at prostate's base and apex. The method is computationally feasible and efficient.

Automatic 3D segmentation of prostate in MRI combining a priori knowledge, Markov fields and Bayesian framework.

Accurate localization and contouring of prostate are important issues in prostate cancer diagnosis and/or therapies. Although several semi-automatic and automatic segmentation methods have been proposed, manual expert correction remains necessary. Our paper introduces an original method for automatic 3D segmentation of the prostate gland from Magnetic Resonance Imaging data. We use a statistical shape model as a priori knowledge, and we model gray levels distribution by fitting histogram modes with a Gaussian mixture. Markov fields are used to introduce contextual information regarding voxels neighbourhood. Final labelling optimization is based on Bayesian a posteriori classification, estimated with the Iterative Conditional Mode algorithm (ICM). We compared the accuracy of this method, free from any manual correction, with contours outlined by an expert radiologist. In 6 random cases, including prostates with cancer and benign prostatic hypertrophy (BPH), mean Hausdorff distance (HD) and Overlap Ratio (OR) were 9.94 mm and 0.83, respectively. Beyond fast computing times, this new method showed satisfying results, even at prostate's base and apex.