Medical Image Segmentation Methods Research Articles

SU‐GG‐I‐95: Simpler and Faster Watershed Medical Image Segmentation Algorithm

Purpose: A watershed medical image segmentation method has a drawback of producing a region for each local minimum, resulting in oversegmentation. To alleviate this problem, a post merging process such as a hybrid graph merging algorithm is used, which impedes interactive segmentation with a graphical user interface. An effective watershed algorithm without a post merging process is proposed. Method and Materials: Our algorithm, as the preprocessing, includes the edge‐preserving noise reduction and gradient‐based boundary sharpening steps. Because the initial oversegmentation depends on the gradient image intensity variations, the noise reduction algorithm can reduce the problem appreciably. A well‐known statistical edge‐preserving noise reduction algorithm is implemented to preserve the boundaries of the image objects which have different physiological properties. Gradient‐based boundary sharpening stage follows the novel edge‐preserving noise reduction step. Boundary sharpening process combined with watershed segmentation results in an effective watershed algorithm without a post merging process. The combination of the standard gradient values with two cross operators makes the edges sharper and thinner. A threshold value is controlled interactively with a steppedup graphical user interface in the boundary sharpening process. Results: We applied the method to both CT and MR images. Interactive real time medical image segmentation was possible with a graphical user interface. Threshold values were manipulated interactively with a mouse to get an appropriate segmentation of the abdomen CT image. It was also confirmed that this method produced the same segmentations as those of hybrid‐merging algorithm for the MR brain images. Conclusion: In the gradient‐based watershed, computing time is negligible and storage requirement can be reduced appreciably because a post hybrid merging algorithm is not necessary. Moreover, interactive real time segmentation is possible with the steppedup graphical user interface.

Segmentation of medical images using a geometric deformable model and its visualization

An automatic segmentation method for medical images that uses a geometric deformable model is presented, and the segmented results are visualized with the help of a modified marching cubes algorithm. The geometric deformable model is based on evolution theory and the level set method. In particular, the level set method utilizes a new derived speed function to improve the segmentation performance. This function is defined by the linear combination of three terms, namely, the alignment term, the minimal-variance term, and the smoothing term. The alignment term makes a level set as close as possible to the boundary of an object. The minimal-variance term best separates the interior and exterior of the contour. The smoothing term renders a segmented boundary less sensitive to noise. The use of the proposed speed function can improve the segmentation accuracy while making the boundaries of each object much smoother. Finally, it is demonstrated that the design of the speed function plays an important role in the reliable segmentation of synthetic and computed tomography (CT) images, and the segmented results are visualized effectively with the help of a modified marching cubes algorithm.

A directional distance aided method for medical image segmentation

A challenging problem in image segmentation is preventing boundary leakage through poorly resolved edges because not enough local information can be provided along them. In this article, we propose a new directional distance aided image segmentation method, formulated under the level set framework, to prevent the leakage. At each evolution step, the zero level set is extracted and smoothed. For each point on the zero level set, a new directional distance (DD) term, defined as the vector starting from itself and pointing to its counterpart on the smoothed version of the zero level set, is calculated to measure its "degree of protrusion." The evolution speed of the points that are considered to be protruding out will be penalized. Other terms, e.g., curvature and gradient terms and user specified constraints, are used along with the DD term to influence the level set evolution. Our smoothing technique augments traditional Gaussian smoothing with a new antishrinkage operation. The novelty of our method is that the DD term does not depend on intensity or gradient boundaries to regulate the regional shape and, therefore, help prevent leakage and the method incorporates vertex-based curve/surface smoothing into curve evolution under the level set framework. Experimental results show that the new DDA method achieves promising results and reasonable stability in segmenting simulated objects as well as abdominal aortic aneurysms in computed tomography (CT) angiograms, in both 2D and 3D, by preventing leakage into adjacent structures while preserving local shape details.

SVM for density estimation and application to medical image segmentation

A method of medical image segmentation based on support vector machine (SVM) for density estimation is presented. We used this estimator to construct a prior model of the image intensity and curvature profile of the structure from training images. When segmenting a novel image similar to the training images, the technique of narrow level set method is used. The higher dimensional surface evolution metric is defined by the prior model instead of by energy minimization function. This method offers several advantages. First, SVM for density estimation is consistent and its solution is sparse. Second, compared to the traditional level set methods, this method incorporates shape information on the object to be segmented into the segmentation process. Segmentation results are demonstrated on synthetic images, MR images and ultrasonic images.

Current methods in medical image segmentation.

Image segmentation plays a crucial role in many medical-imaging applications, by automating or facilitating the delineation of anatomical structures and other regions of interest. We present a critical appraisal of the current status of semi-automated and automated methods for the segmentation of anatomical medical images. Terminology and important issues in image segmentation are first presented. Current segmentation approaches are then reviewed with an emphasis on the advantages and disadvantages of these methods for medical imaging applications. We conclude with a discussion on the future of image segmentation methods in biomedical research.