Amir Hossein Foruzan1, Yen-Wei Chen2. 1. Department of Biomedical Engineering, Engineering Faculty, Shahed University, Tehran, Iran. a.foruzan@shahed.ac.ir. 2. Intelligent Image Processing Lab, College of Information Science and Engineering, Ritsumeikan University, Kusatsu, Shiga, Japan.
Abstract
PURPOSE: The intensity profile of an image in the vicinity of a tissue's boundary is modeled by a step/ramp function. However, this assumption does not hold in cases of low-contrast images, heterogeneous tissue textures, and where partial volume effect exists. We propose a hybrid algorithm for segmentation of CT/MR tumors in low-contrast, noisy images having heterogeneous/homogeneous or hyper-/hypo-intense abnormalities. We also model a smoothed noisy intensity profile by a sigmoid function and employ it to find the true location of boundary more accurately. METHODS: A novel combination of the SVM, watershed, and scattered data approximation algorithms is employed to initially segment a tumor. Small and large abnormalities are treated distinctly. Next, the proposed sigmoid edge model is fitted to the normal profile of the border. The estimated parameters of the model are then utilized to find true boundary of a tissue. RESULTS: We extensively evaluated our method using synthetic images (contaminated with varying levels of noise) and clinical CT/MR data. Clinical images included 57 CT/MR volumes consisting of small/large tumors, very low-/high-contrast images, liver/brain tumors, and hyper-/hypo-intense abnormalities. We achieved a Dice measure of [Formula: see text] and average symmetric surface distance of [Formula: see text] mm. Regarding IBSR dataset, we fulfilled Jaccard index of [Formula: see text]. The average run-time of our code was [Formula: see text] s. CONCLUSION: Individual treatment of small and large tumors and boundary correction using the proposed sigmoid edge model can be used to develop a robust tumor segmentation algorithm which deals with any types of tumors.
PURPOSE: The intensity profile of an image in the vicinity of a tissue's boundary is modeled by a step/ramp function. However, this assumption does not hold in cases of low-contrast images, heterogeneous tissue textures, and where partial volume effect exists. We propose a hybrid algorithm for segmentation of CT/MR tumors in low-contrast, noisy images having heterogeneous/homogeneous or hyper-/hypo-intense abnormalities. We also model a smoothed noisy intensity profile by a sigmoid function and employ it to find the true location of boundary more accurately. METHODS: A novel combination of the SVM, watershed, and scattered data approximation algorithms is employed to initially segment a tumor. Small and large abnormalities are treated distinctly. Next, the proposed sigmoid edge model is fitted to the normal profile of the border. The estimated parameters of the model are then utilized to find true boundary of a tissue. RESULTS: We extensively evaluated our method using synthetic images (contaminated with varying levels of noise) and clinical CT/MR data. Clinical images included 57 CT/MR volumes consisting of small/large tumors, very low-/high-contrast images, liver/brain tumors, and hyper-/hypo-intense abnormalities. We achieved a Dice measure of [Formula: see text] and average symmetric surface distance of [Formula: see text] mm. Regarding IBSR dataset, we fulfilled Jaccard index of [Formula: see text]. The average run-time of our code was [Formula: see text] s. CONCLUSION: Individual treatment of small and large tumors and boundary correction using the proposed sigmoid edge model can be used to develop a robust tumor segmentation algorithm which deals with any types of tumors.
Entities:
Keywords:
Medical image processing; Scattered data approximation; Sigmoid edge model; Tumor segmentation; Watershed algorithm
Authors: K D Hopper; C J Kasales; K D Eggli; T R TenHave; N M Belman; P S Potok; M A Van Slyke; G J Olt; P Close; A Lipton; H A Harvey; J S Hartzel Journal: J Comput Assist Tomogr Date: 1996 Nov-Dec Impact factor: 1.826
Authors: Srinivasa R Prasad; Kartik S Jhaveri; Sanjay Saini; Peter F Hahn; Elkan F Halpern; James E Sumner Journal: Radiology Date: 2002-11 Impact factor: 11.105
Authors: Marius George Linguraru; William J Richbourg; Jianfei Liu; Jeremy M Watt; Vivek Pamulapati; Shijun Wang; Ronald M Summers Journal: IEEE Trans Med Imaging Date: 2012-08-07 Impact factor: 10.048
Authors: Yuhua Gu; Virendra Kumar; Lawrence O Hall; Dmitry B Goldgof; Ching-Yen Li; René Korn; Claus Bendtsen; Emmanuel Rios Velazquez; Andre Dekker; Hugo Aerts; Philippe Lambin; Xiuli Li; Jie Tian; Robert A Gatenby; Robert J Gillies Journal: Pattern Recognit Date: 2013-03-01 Impact factor: 7.740
Authors: Assaf Hoogi; Christopher F Beaulieu; Guilherme M Cunha; Elhamy Heba; Claude B Sirlin; Sandy Napel; Daniel L Rubin Journal: Med Image Anal Date: 2017-01-13 Impact factor: 8.545