#### DMCA

## Segmentation of magnetic resonance images using fuzzy algorithms for learning vector quantization (1999)

Venue: | IEEE Transactions on Medical Imaging |

Citations: | 14 - 1 self |

### Citations

3696 |
Leaming internal representations by error propagation
- Rumelhart, Hinton, et al.
- 1986
(Show Context)
Citation Context ...n this study, neural networks provided better boundary definition for nonidealized data [3]. Hall et al. [5] compared MR-image segmentation techniques based on supervised multilayered neural networks =-=[20]-=- and the unsupervised fuzzy ™-means algorithm [1]. These segmentation techniques were tested on MR images from healthy volunteers and selected patients with brain tumors surrounded by edema. The super... |

2132 |
Vector Quantization and Signal Compression
- Gersho, Gray
- 1992
(Show Context)
Citation Context ...e performed by clustering algorithms, which are typically developed by solving a constrained minimization problem using alternating optimization. These clustering techniques include the crisp ™-means =-=[4]-=-, fuzzy ™-means [1], generalized fuzzy ™-means [9], and entropyconstrained fuzzy clustering algorithms [11]. Clustering algorithms can be divided into crisp and fuzzy, depending on the strategy they e... |

2068 |
Pattern Recognition with Fuzzy Objective Function Algorithms
- Bezdek
- 1981
(Show Context)
Citation Context ...dary definition for nonidealized data [3]. Hall et al. [5] compared MR-image segmentation techniques based on supervised multilayered neural networks [20] and the unsupervised fuzzy ™-means algorithm =-=[1]-=-. These segmentation techniques were tested on MR images from healthy volunteers and selected patients with brain tumors surrounded by edema. The supervised and unsupervised segmentation techniques us... |

1622 |
Image Analysis and Mathematical Morphology
- Serra
- 1982
(Show Context)
Citation Context ... of the Marr–Hildreth operator [7] was used for edge detection. Morphological filters, dilation, and erosion, were subsequently applied to refine the detected edges and improve the surface definition =-=[21]-=-. Clarke [3] compared a maximum likelihood method with a neural-network technique for tissue classification. The two approaches were tested on idealized and nonidealized image data, all obtained with ... |

407 |
Image segmentation techniques
- Haralick, Shapiro
- 1985
(Show Context)
Citation Context ...the redundancy that is naturally present in images. In general, image segmentation is accomplished by dividing an image into segments with uniform and homogeneous attributes, such as tone and texture =-=[6]-=-. In the context of MR imaging, segmentation is the process of selectively removing the redundancy present in MR images without affecting the details that play a key role in the diagnostic process. Th... |

396 | Self-Organization and Associative - Kohonen - 1988 |

106 |
A comparison of neural network and fuzzy clustering techniques in segmenting magnetic resonance images of the brain.
- Hall, Bensaid, et al.
- 1992
(Show Context)
Citation Context ...uded healthy volunteers and selected patients with brain tumors undergoing radiation therapy. In this study, neural networks provided better boundary definition for nonidealized data [3]. Hall et al. =-=[5]-=- compared MR-image segmentation techniques based on supervised multilayered neural networks [20] and the unsupervised fuzzy ™-means algorithm [1]. These segmentation techniques were tested on MR image... |

91 |
Generalized clustering network and Kohonen’s self-organizing schemes,”
- Pal, Bezdek, et al.
- 1993
(Show Context)
Citation Context ...wn in Fig. 1. Kohonen [17] proposed an unsupervised learning scheme, known as the (unlabeled data) LVQ. This algorithm can be used to generate crisp ™ partitions of unlabeled data vectors. Pal et al. =-=[18]-=- identified a close relationship between this algorithm and a clustering procedure, proposed earlier by MacQueen, known as the sequential hard ™-means algorithm. Tsao et al. [22] proposed a batch lear... |

68 |
Fuzzy Kohonen clustering networks,”
- Bezdek, Tsao, et al.
- 1994
(Show Context)
Citation Context ...a vectors. Pal et al. [18] identified a close relationship between this algorithm and a clustering procedure, proposed earlier by MacQueen, known as the sequential hard ™-means algorithm. Tsao et al. =-=[22]-=- proposed a batch learning scheme, known as fuzzy LVQ (FLVQ). Karayiannis and Bezdek [14] derived a broad family of batch LVQ algorithms that can be implemented as the fuzzy ™-means or the FLVQ algori... |

50 |
3-D segmentation of MR images of the head for 3-D display,”
- Bomans, Hohne, et al.
- 1990
(Show Context)
Citation Context ... The task of formulating new rules involves studying statistical properties of voxels of different structures, formulating segmentation heuristics, and coding the heuristics into rules. Bomans et al. =-=[2]-=- combined edge-detection operators and morphological filtering for segmentation and reconstruction of anatomical surfaces from MR-image data. An extension of the Marr–Hildreth operator [7] was used fo... |

42 |
The Detection of Intensity Changes by Computer and Biological Vision Systems
- Hildreth
- 1983
(Show Context)
Citation Context ...mans et al. [2] combined edge-detection operators and morphological filtering for segmentation and reconstruction of anatomical surfaces from MR-image data. An extension of the Marr–Hildreth operator =-=[7]-=- was used for edge detection. Morphological filters, dilation, and erosion, were subsequently applied to refine the detected edges and improve the surface definition [21]. Clarke [3] compared a maximu... |

42 |
Low-level segmentation of 3-D magnetic resonance brain images—A rule-based system
- Raya
- 1990
(Show Context)
Citation Context ... MR images of 45 volunteers and achieved a discrimination accuracy of 84% for 13 tissue types among three age groups, with classification accuracy for individual regions ranging from 50 to 100%. Raya =-=[19]-=- presented a rule-based system for low-level segmentation of MR brain images. In this approach, the proton-density and T2-weighted parameters were used to separate voxels of different structures. The ... |

35 |
Fuzzy Algorithms for Learning Vector Quantization.
- Karayiannis
- 1996
(Show Context)
Citation Context ...generalized LVQ (GLVQ) algorithm [18]. The GLVQ-F algorithms were then developed in an attempt to overcome scaling problems associated with the original GLVQ algorithm [13]. Karayiannis and Pai [12], =-=[15]-=-, [16] proposed a framework for the development of fuzzy algorithms for LVQ (FALVQ). This formulation resulted in the development of a broad variety of FALVQ algorithms, which are distinguished by the... |

25 | An integrated approach to fuzzy learning vector quantization and fuzzy c-means clustering
- Karayiannis, Bezdek
- 1997
(Show Context)
Citation Context ...lustering procedure, proposed earlier by MacQueen, known as the sequential hard ™-means algorithm. Tsao et al. [22] proposed a batch learning scheme, known as fuzzy LVQ (FLVQ). Karayiannis and Bezdek =-=[14]-=- derived a broad family of batch LVQ algorithms that can be implemented as the fuzzy ™-means or the FLVQ algorithms. Pal et al. [18] suggested that LVQ can be performed through an unsupervised learnin... |

24 | Repairs to GLVQ : a new family of competitive learning schemes". - Karayiannis, Bezdek, et al. - 1996 |

6 |
methodology for constructing fuzzy algorithms for learning vector quantization
- “A
- 1997
(Show Context)
Citation Context ...n the generalized LVQ (GLVQ) algorithm [18]. The GLVQ-F algorithms were then developed in an attempt to overcome scaling problems associated with the original GLVQ algorithm [13]. Karayiannis and Pai =-=[12]-=-, [15], [16] proposed a framework for the development of fuzzy algorithms for LVQ (FALVQ). This formulation resulted in the development of a broad variety of FALVQ algorithms, which are distinguished ... |

4 |
Characterization of normal brain tissue using seven calculated MRI parameters and a statistical analysis system,” Magn
- Hyman, Kurland, et al.
- 1989
(Show Context)
Citation Context ...ty of Houston, Houston, TX 77204-4793 USA. P.-I. Pai is with TransComm Technology System, Inc., Fremont, CA 94538 USA. Publisher Item Identifier S 0278-0062(99)03150-X. 0278–0062/99$10.00 © 1999 IEEE =-=[8]-=- used a maximum likelihood method for classifying normal brain tissue. This approach was used for the analysis of MR images of 45 volunteers and achieved a discrimination accuracy of 84% for 13 tissue... |

3 |
Learning vector quantization: A review,” Int
- Karayiannis
- 1997
(Show Context)
Citation Context ... local minima and depend rather strongly on the initialization of the clustering process. Recent developments in neural network architectures resulted in learning vector quantization (LVQ) algorithms =-=[10]-=-. LVQ is the name used for unsupervised learning algorithms associated with the competitive network shown in Fig. 1. The network consists of an input layer and an output layer. Each node in the input ... |

2 |
Mr image segmentation using mlm and artificial neural nets
- Clarke
- 1991
(Show Context)
Citation Context ...Hildreth operator [7] was used for edge detection. Morphological filters, dilation, and erosion, were subsequently applied to refine the detected edges and improve the surface definition [21]. Clarke =-=[3]-=- compared a maximum likelihood method with a neural-network technique for tissue classification. The two approaches were tested on idealized and nonidealized image data, all obtained with phantoms for... |

2 |
Generalized fuzzy ™-means algorithms
- Karayiannis
- 1996
(Show Context)
Citation Context ...pically developed by solving a constrained minimization problem using alternating optimization. These clustering techniques include the crisp ™-means [4], fuzzy ™-means [1], generalized fuzzy ™-means =-=[9]-=-, and entropyconstrained fuzzy clustering algorithms [11]. Clustering algorithms can be divided into crisp and fuzzy, depending on the strategy they employ for assigning feature vectors into clusters ... |

1 | partition entropies and entropy constrained clustering algorithms - “Fuzzy - 1997 |