Automatic Liver Tumor Segmentation in CT Modalities Using MAT-ACM

作     者：S.Priyadarsini Carlos Andrés Tavera Romero Abolfazl Mehbodniya P.Vidya Sagar Sudhakar Sengan 

作者机构：Department of Computer Science and EngineeringP.S.R.Engineering CollegeSivakasiTamil Nadu626123India COMBA R&D LaboratoryFaculty of EngineeringUniversidad Santiago de CaliCali76001Colombia Department of Electronics and Communications EngineeringKuwait College of Science and TechnologyKuwait Department of Computer Science and EngineeringKoneru Lakshmaiah Education FoundationVaddeswaramAndhra Pradesh522502India Department of Computer Science and EngineeringPSN College of Engineering and TechnologyTirunelveliTamil Nadu627152India 

出 版 物：《Computer Systems Science & Engineering》 (计算机系统科学与工程（英文）)

年 卷 期：2022年第43卷第12期

页      面：1057-1068页

核心收录：

学科分类：1002[医学-临床医学] 100214[医学-肿瘤学] 10[医学] 

基　　金：funded by Dirección General de Investigaciones of Universidad Santiago de Cali under call No.01-2021 

主　　题：Computed tomography contrast enhancement adaptive edge modeling multi-angle texture active contour liver tumor segmentation 

摘      要：In the recent days, the segmentation of Liver Tumor (LT) has beendemanding and challenging. The process of segmenting the liver and accuratelyspotting the tumor is demanding due to the diversity of shape, texture, and intensity of the liver image. The intensity similarities of the neighboring organs of theliver create difficulties during liver segmentation. The manual segmentation doesnot provide an accurate segmentation because the results provided by differentmedical experts can vary. Also, this manual technique requires a large numberof image slices and time for segmentation. To solve these issues, the Fully Automatic Segmentation (FAS) technique is proposed. In this proposed Multi-AngleTexture Active Contour Model (MAT-ACM) method, the input Computed Tomography (CT) image is preprocessed by Contrast Enhancement (CE) with Non-Linear Mapping Technique (NLMT), in which the liver is differentiated from itsneighbouring soft tissues with related strength. Then, the filtered images are givenas the input to Adaptive Edge Modeling (AEM) with Canny Edge Detection(CED) technique, which segments the Liver Region (LR) from the given CTimages. An AEM with a CED model is implemented, which increases the convergence speed of the iterative process for decreasing the Volumetric Overlap Error(VOE) is 6.92% rates when compared with the traditional Segmentation Techniques (ST). Finally, the Liver Tumor Segmentation (LTS) is developed by applyingthe MAT-ACM, which accurately segments the LR from the segmented LRs. Theevaluation of the proposed method is compared with the existing LTS methodsusing various performance measures to prove the superiority of the proposedMAT-ACM method.