Search

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of South-Central Minzu University (Natural Science Edition) is the property of Journal of South-Central Minzu University (Natural Science Edition) Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The liver tumor is a disease with a high incidence and probability of deterioration, and the rapid diagnosis of liver disease requires accurate segmentation of liver and tumor from computed tomography (CT) scan. To analyze the status and the trend of the liver and tumor image segmentation field, this paper investigated the segmentation methods for liver and tumor images and summarized the segmentation methods for liver and tumor images in recent years. Liver and tumor image segmentation methods included conventional methods and deep learning methods. The conventional methods required more manual involvement and could not be fully automated. Deep learning methods could be divided into 2 D, 2.5 D and 3 D methods from the dimension of segmentation network. These methods had high segmentation accuracy and high hardware requirements. While considering the advantages and disadvantages of deep learning and conventional methods, their combination was constantly explored, and conventional methods such as graph cuts and conditional random fields often used to refine the segmentation results of deep learning methods. [ABSTRACT FROM AUTHOR]

Due to the complexity of the liver region in abdominal images and the limitations of traditional segmentation methods, there are still many challenges in the field of liver segmentation. Aiming at the shortcomings of the existing segmentation network in the global and local information processing of the liver area, a segmentation method of cyclic densely connected network that integrates more local features is designed. This method integrates the cyclic dense connection module and the local feature supplement module into the learning unit of the coding process, so that the coding unit integrates deep-level global information and more-scale local feature information. Finally, after the decoding process, the softmax function is used to output the segmentation results. On the Li TS data set, the method performed well in multiple evaluation indicators, with an accuracy of 95.1%. In addition, in the Data . 6 related experimental data set 7 is also proved that the method has good generalization performance. Experiments show that dense connections and more local information can make the performance of the liver segmentation model better. [ABSTRACT FROM AUTHOR]

Remapping the pixel intensity range of the high data depth computed tomography( CT ) image to an observable range for window technology will lose image information, and the method of automatic segmentation after only one pre-processing of CT images is not well adapted to the tumor segmentation. This paper presented a two-step optimized intensity windowing preprocessing method for segmented CT values. It used the histogram of CT value and window technology of liver and its tumors to preprocess the original and liver image respectively, improved the contrast of the area of interest. Compared the automatic segmentation accuracy of liver and tumor with different intensity windows in the cascaded convolutional neural network (CNN), obtained the optimal CT range ofliver and tumor, which were [ -40, 190] HU and [ - 25, 145] HU, respectively. This method was tested on the 3 DIRCADb dataset with three mainstream segmentation networks, UN et, ResN et, and FCN. It proves that the influence of different CT value ranges on liver segmentation accuracy can reach 6. 75 %, and the segmentation accuracy of different networks can be improved by about 2%. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Image & Graphics is the property of Editorial Office of Journal of Image & Graphics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

For the sake of high accuracy and efficiency of liver segmentation, we propose an improved Fast Marching method based on self-adaptive parameter adjustment. The arrival time parameter T is adjusted according to the intensity statistics of the liver region on set of abdominal CT images, which can used to estimate the size of liver region on the corresponding CT slices. This method is efficient for elimination the influence of traditional same parameter values on the efficiency and accuracy of liver segmentation. When tested on 10 sets of abdominal CT images, experimental results show that the proposed approach can segment liver automatically, quickly and accurately. The average time for processing a slice of CT image resulted to be 0. 3s, and the average accuracy is up to 97%. It is accurate and efficient enough for the use in clinical diagnosis and surgical navigation. [ABSTRACT FROM AUTHOR]

For liver segmentation on abdominal CT images, a novel algorithm is proposed which is based on the threshold method and modified GGVF-Snake model. Firstly, the CT image is converted into grayscale by using Window-Leveling algorithm, and then Modified Curvature anisotropic diffusion fiter is applied. Secondly, a threshold method is used to obtain the initial contour of liver. Finally, the accurate liver boundary is obtained by using a modified GGVF-Snake model. Experimental results show that the proposed algorithm can be applied to the segmentation of liver on abdominal CT images effectively. [ABSTRACT FROM AUTHOR]