B-type ultrasound images have important applications in medical diagnosis. However, the widely spread intensity inhomogeneity, low-scale contrast, constructed defect, noise and blurred edges all make it difficult to implement automatic segmentation of lesion in the images. Based on region level set method, a subordinate degree region level set model was proposed, in which subordinate degree probability of each pixel was defined to reflect the pixel subjection grade to target and background respectively. Pixels were classified to either target or background by calculation of their subordinate degree probabilities, and edge contour was obtained by region level set iterations. In this paper, lesion segmentation is regarded as local segmentation of specific area, and the calculation is restrained to the local sphere abide by the contour, which greatly reduce the calculation complexity. Experiments on B-type ultrasound images showed improved results of the proposed method compared to those of some popular level set methods.
To realize the accurate positioning and quantitative volume measurement of tumor in head and neck tumor CT images, we proposed a level set method based on augmented gradient. With the introduction of gradient information in the edge indicator function, our proposed level set model is adaptive to different intensity variation, and achieves accurate tumor segmentation. The segmentation result has been used to calculate tumor volume. In large volume tumor segmentation, the proposed level set method can reduce manual intervention and enhance the segmentation accuracy. Tumor volume calculation results are close to the gold standard. From the experiment results, the augmented gradient based level set method has achieved accurate head and neck tumor segmentation. It can provide useful information to computer aided diagnosis.
In view of the problems of more artificial interventions and segmentation defects in existing two-dimensional segmentation methods and abnormal liver segmentation errors in three-dimensional segmentation methods, this paper presents a semi-automatic liver organ segmentation method based on the image sequence context. The method takes advantage of the existing similarity between the image sequence contexts of the prior knowledge of liver organs, and combines region growing and level set method to carry out semi-automatic segmentation of livers, along with the aid of a small amount of manual intervention to deal with liver mutation situations. The experiment results showed that the liver segmentation algorithm presented in this paper had a high precision, and a good segmentation effect on livers which have greater variability, and can meet clinical application demands quite well.
Glomerular filtration rate (GFR), which can be estimated by Gates method with dynamic kidney single photon emission computed tomography (SPECT) imaging, is a key indicator of renal function. In this paper, an automatic computer tomography (CT)-assisted detection method of kidney region of interest (ROI) is proposed to achieve the objective and accurate GFR calculation. In this method, the CT coronal projection image and the enhanced SPECT synthetic image are firstly generated and registered together. Then, the kidney ROIs are delineated using a modified level set algorithm. Meanwhile, the background ROIs are also obtained based on the kidney ROIs. Finally, the value of GFR is calculated via Gates method. Comparing with the clinical data, the GFR values estimated by the proposed method were consistent with the clinical reports. This automatic method can improve the accuracy and stability of kidney ROI detection for GFR calculation, especially when the kidney function has been severely damaged.
Optical coherence tomography (OCT) is a new technique applied in cardiovascular system. It can detect vessel intimal, small structure of plaque surface and discover small lesions with its high axial resolution and quantification character. Especially with the application of OCT in characterization of coronary atherosclerotic plaque, diagnosis and treatment strategy making, optimizing percutaneous coronary intervention therapy and assessment after stent planting make the OCT become an efficient tool for cardiovascular disease diagnosis and treatment. This paper presents a novel coronary vessel intimal sequence extraction method based on prior boundary constraints in OCT image. On the basis of conventional Chan-Vese model, we modified the evolutionary weight function to control the evolutionary rate of boundary by adding local information of boundary curve. At the same time, we added the gradient energy term and intimal boundary constraint term based on priori boundary condition to further control the evolutionary of boundary curve. At last, coronary vessel intimal is extracted in a sequence way. The comparison with vessel intimal, manual segmented by clinical scientists (golden standard), indicates that our coronary vessel intimal extraction method is robust to intimal boundary blur, distortion, guide wire shadow and plaque disturbs. The results of this study can be applied to clinical aid diagnosis and precise diagnosis and treatment.
A multi-label based level set model for multiple sclerosis lesion segmentation is proposed based on the shape, position and other information of lesions from magnetic resonance image. First, fuzzy c-means model is applied to extract the initial lesion region. Second, an intensity prior information term and a label fusion term are constructed using intensity information of the initial lesion region, the above two terms are integrated into a region-based level set model. The final lesion segmentation is achieved by evolving the level set contour. The experimental results show that the proposed method can accurately and robustly extract brain lesions from magnetic resonance images. The proposed method helps to reduce the work of radiologists significantly, which is useful in clinical application.
Kidney tumor is one of the diseases threatening human health. Ultrasound is widely applied in kidney tumor diagnosis due to its high popularization, low price and no radiation. Accurate segmentation of kidney tumor is the basis of precise treatment. Kidney tumors often grow in the middle of cortex, so that segmentation is easy disturbed by nearby organs. Besides, ultrasound images own low contrast and large speckle, leading to difficult segmentation. This paper proposed a novel kidney tumor segmentation method in ultrasound images using adaptive sub-regional evolution level set models (ASLSM). Regions of interest are firstly divided into subareas. Secondly, object function is designed by integrating inside and outside energy and gradient, in which the ratio of these two parts are adjusted adaptively. Thirdly, ASLSM adapts convolution radius and curvature according to centroid principle and similarity inside and outside zero level set. Hausdorff distance (HD) of (8.75 ± 4.21) mm, mean absolute distance (MAD) of (3.26 ± 1.69) mm, dice-coefficient (DICE) of 0.93 ± 0.03 were obtained in the experiment. Compared with traditional ultrasound segmentation method, ASLSM is more accurate in kidney tumor segmentation. ASLSM may offer convenience for doctor to locate and diagnose kidney tumor in the future.