Image Processing in Medicine

Bezdek, James C.; Sutton, Melanie

doi:10.1007/978-1-4615-4601-6_12

Cited by 7 publications

(2 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Adjacent regions differ with respect to the same criteria; the criteria most commonly chosen are gray levels or texture, or both; see Haralick and Shapiro (11). For a detailed survey of image segmentation procedures, see Pal and Pal (12) and Bezdek and Sutton (13). In many situations, it is not clear whether a certain pixel should belong to a region or not.…”

Section: Image Segmentationmentioning

confidence: 99%

Framework for Automatic Condition Assessment of Culverts

Meegoda

Juliano

Banerjee

2006

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

A framework for real-time and automated monitoring of the condition of culverts based on identifying internal defects via video inspection is developed. Manual inspection using closed-circuit television has several drawbacks, such as inconsistency and subjectivity due to human evaluation. Analysis of digital video, consisting of thousands of megabytes even at lower resolutions, can be laborious and not suited for real-time implementation. An innovative approach is to extract image frames judiciously from the video and analyze frames to locate and categorize major defects. Rather than analyze all extracted frames, one can skip consecutive frames at a minimal loss of accuracy and bring considerable savings in memory and system requirements. Each frame is preprocessed to enhance contrast, through use of an adaptive scheme, and to reduce dimensionality in pixel-space by implemention of region-based processing. Preprocessing is followed by a two-step image segmentation process, which implements a background elimination procedure in the first step and shape detection in the second step. Fuzzy clustering is used as the underlying segmentation model. Defect shape and depth information after post-processing are used as input to an assessment methodology for automated condition state. A simple formulation based on both the damage area and depth is then used to assess the condition of culverts based on a four-point condition assessment scale. The proposed framework is demonstrated with a test example. Future research would entail consolidating the concept by extensive testing and integration for real-time application.

show abstract

Section: Image Segmentationmentioning

confidence: 99%

Framework for Automatic Condition Assessment of Culverts

Meegoda

Juliano

Banerjee

2006

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

show abstract

“…In many situations, it is not easy to determine if a pixel should belong to a region or not due to the features considered for determining the homogeneity within each region do not have sharp transitions at region boundaries [Bezdek 1999]. To alleviate this situation fuzzy set concepts can be introduced into the segmentation process, as is the case of Fuzzy C-Mean technique.…”

Section: Fuzzy C-meansmentioning

confidence: 99%

Contributions to Automatic and Unsupervised MRI Brain Tumor Segmentation: A New Fuzzy Approach

Gordillo¹

View full text Add to dashboard Cite

Brain tumors are part of a group of common, non-communicable, chronic and potentially lethal diseases affecting mostfamilies in Europe. Imaging plays a central role in brain tumor management, from detection and classification to staging andcomparison. Increasingly, magnetic resonance imaging (MRI) scan is being used for suspected brain tumors, because in addition tooutline the normal brain structures in great detail, has a high sensitivity for detecting the presence of, or changes within, a tumor.Currently most of the process related to brain tumors such as diagnosis, therapy, and surgery planning are based on its previoussegmentation from MRI. Brain tumor segmentation from MRI is a challenging task that involves various disciplines. The tumors to besegmented are anatomical structures, which are often non-rigid and complex in shape, vary greatly in size and position, and exhibitconsiderable variability from patient to patient. Moreover, the task of labeling brain tumors in MRI is highly time consuming and thereexists significant variation between the labels produced by different experts. The challenges associated with automated brain tumor segmentation have given rise to many different segmentationapproaches. Although the reported accuracy of the proposed methods is promising, these approaches have not gained wide acceptance among the neuroscientists for every day clinical practice. Two of the principal reasons are the lack of standardizedprocedures, and the deficiency of the existing methods to assist medical decision following a technician way of work. For a brain tumor segmentation system has acceptance among neuroscientists in clinical practice, it should supportmedical decision in a transparent and interpretable way emulating the role of a technician, considering his experience and knowledge. This includes knowledge of the expected appearance, location, variability of normal anatomy, bilateral symmetry, andknowledge about the expected intensities of different tissues. The image related problems and the variability in tissue distribution among individuals in the human population makes that some degree of uncertainty must be considered together with segmentationresults. A possible solution for designing complex systems, in which it is required to incorporate the experience of an expert, or the related concepts appear uncertain, is the use of soft computing techniques such as fuzzy systems. An important advantage of fuzzysystems is their ability for handling vague information. In this work, it is proposed the development of a method to assist the specialists in the process of segmenting braintumors. The main objective is to develop a system that can follow a technician way of work, considering his experience andknowledge. More concretely, it is presented a fully automatic and unsupervised segmentation method, which considers humanknowledge. The method successfully manages the ambiguity of MR image features being capable of describing knowledge about thetumors in vague terms. The method was developed making use of the powerful tools provided by fuzzy set theory. This thesis presents a step-by-step methodology for the automatic MRI brain tumor segmentation. For achieving the fullyautomatic and unsupervised segmentation, objective measures are delineated by means of adaptive histogram thresholds for defining the non-tumor and tumor populations. For defining the tumor population a symmetry analysis is conducted. The proposed approach introduces a new way to automatically define the membership functions from the histogram. The proposed membership functions are designed to adapt well to the MRI data and efficiently separate the populations. Since any post-processing is needed, and the unique pre-processing operation is the skull stripping, the proposed segmentation technique reduces the computational times. The proposed approach is quantitatively comparable to the most accurate existing methods, even thoughthe segmentation is done in 2D.

show abstract

Generation of brightness membership functions for labeled image segmentation

Sobrevilla

Montseny

10th IEEE International Conference on Fuzzy Systems. (Cat. No.01CH37297)

View full text Add to dashboard Cite

A common problem in segmentation of monochrome images occurs when an image has a background of varying gray level such as gradually changing shades, or when collections we would like to call regions, or classes, assume some broad range of gray scales. These problems hinder the use of brightness feature within segmentation algorithms of monochrome images. In this paper we propose a method for deriving membership functions for the labels related to the Brightness feature, to be included within fuzzy labeled segmentation algorithms. With the aim to be useful for a wide range of detection and segmentation applications, the method is based on the use of a rule base analysis of the brightness histogram, heuristics, and probability to possibility transformations. We illustrate the suitability and applicability of our membership functions' generation method with applications to real data sets.

show abstract

Image Processing in Medicine

Cited by 7 publications

References 51 publications

Framework for Automatic Condition Assessment of Culverts

Framework for Automatic Condition Assessment of Culverts

Contributions to Automatic and Unsupervised MRI Brain Tumor Segmentation: A New Fuzzy Approach

Generation of brightness membership functions for labeled image segmentation

Contact Info

Product

Resources

About