Medical Image Segmentation Using Level Set Method with a New Hybrid Speed Function Based on Boundary and Region Segmentation

Abstract

SUMMARYThis paper presents a new hybrid speed function needed to perform image segmentation within the level-set framework. The proposed speed function uses both the boundary and region information of objects to achieve robust and accurate segmentation results. This speed function provides a general form that incorporates the robust alignment term as a part of the driving force for the proper edge direction of an active contour, an active region term derived from the region partition scheme, and the smoothing term for regularization. First, we use an external force for active contours as the Gradient Vector Flow field. This is computed as the diffusion of gradient vectors of a gray level edge map derived from an image. Second, we partition the image domain by progressively fitting statistical models to the intensity of each region. Here we adopt two Gaussian distributions to model the intensity distribution of the inside and outside of the evolving curve partitioning the image domain. Third, we use the active contour model that has the computation of geodesics or minimal distance curves, which allows stable boundary detection when the model's gradients suffer from large variations including gaps or noise. Finally, we test the accuracy and robustness of the proposed method for various medical images. Experimental results show that our method can properly segment low contrast, complex images. key words: image segmentation, geometric deformable model, level set method, gradient vector flow

Biomedical Image Segmentation: A Survey

“…9 Segmentation results using Deformable Models [52] Fig. 10 Level-set construction [95] Since level-set methods are not sensitive to noise, they can be implemented in various images modalities. Moreover, they are also capable of segmenting images efficaciously using low-intensity gradients lacking sharp boundaries.…”

Automatic Segmentation of Lumbar Spine MRI Images Based on Improved Attention U-Net

“…Medical image segmentation techniques can be divided into two categories: traditional segmentation techniques and deep learning-based methods. e former includes thresholdbased segmentation [8], edge-based segmentation [9], regionbased segmentation [10,11], and active contour model-based techniques [12,13], and the latter is mainly neural networkbased segmentation [14][15][16][17][18]. Earlier studies have been applied to the lumbar spine segmentation by traditional segmentation techniques.…”

MRI-Based Medical Image Recognition: Identification and Diagnosis of LDH

“…Target segmentation and recognition is a key step in processing patient image data analysis, which helps in the next step of symptom diagnosis and treatment plan [2][3][4]. Classical medical image segmentation techniques can be classi ed as threshold-based segmentation [5], edge or boundary-based segmentation [6], region-based segmentation [7,8], active contour model-based techniques [9,10], and neural network-based segmentation [11][12][13][14][15]. To increase the standardization and normality of the diagnosis, the severity of the disease is classi ed by some scholars.…”