Shape factors for analysis of breast tumors in mammograms

Elfaramawy, Nourhan; Rangayyan, Rangaraj M.; Desautels, J. E. Leo; Alim, O.A.

doi:10.1109/ccece.1996.548110

Cited by 17 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their use in medical applications includes probabilistic models for 2D medical image segmentation of the distal femur [17] and the left ventricle during cardiac motion [18] as well as to classify different shapes of the corpus callus in 2D [19] and 3D [20]. 2D Fourier descriptors have further shown feasibility in distinguishing between benign and malignant breast tumours from mammograms in [21,22], as well as to analyse blood cell types from blood samples in order to identify malignant cells and distinguish between lymphomas and leukemia [23]. Other than the related studies of [24,25], this appears to be the first application of Fourier descriptors to the nasal cavity geometry.…”

Section: Introductionmentioning

confidence: 99%

Modelling nasal airflow using a Fourier descriptor representation of geometry

Gambaruto

Taylor

Doorly

2008

Numerical Methods in Fluids

View full text Add to dashboard Cite

General rightsThis document is made available in accordance with publisher policies. Please cite only the published version using the reference above. SUMMARYProcedures capable of providing both compact representations and rational simplifications of complex anatomical flow conduits are essential to explore how form and function are related in the respiratory, cardiovascular and other physiological flow systems. This work focuses on flow in the human nasal cavity. Methods to derive the cavity wall boundary from medical images are first outlined. Anisotropic smoothing of the boundary surface is shown to provide less geometric distortion in regions of high curvature, such as at the ends of the narrow nasal passages. A reversible decomposition of the surface into a stack of planar contours is then effected using an implicit function formulation. Fourier descriptors provide a continuous representation of each contour as a modal expansion, and permit simplification of the geometry by retaining only dominant modes via filtering.Computations of the steady inspiratory flow field are performed for replica and reduced geometries, where the reduced geometry is derived by retaining only the first fifteen modes in the expansion of each slice contour. The overall pressure drop and integrated wall shear are shown to be virtually unaffected by simplification. More sensitive measures, such as the Lagrangian particle trajectories and residence time distributions show slight changes as discussed.Comparison of the Fourier descriptor method applied to three different patient data sets indicate the potential of the technique as a means to characterise complex flow conduit geometry, and the scope for further work is outlined.

show abstract

Section: Introductionmentioning

confidence: 99%

Modelling nasal airflow using a Fourier descriptor representation of geometry

Gambaruto

Taylor

Doorly

2008

Numerical Methods in Fluids

View full text Add to dashboard Cite

show abstract

“…The texture features were extracted from "original ROl" and shape features from "segmented ROl". We examined fourteen shape features (table 1) : circularity, compactness, Gupta descriptors, Shen descriptors, Hu descriptors, Fourier descriptor, and Wee descriptors [5,8,[17][18][19][20][21][22] and fourteen texture features proposed by Haralick et a!. (variance, entropy, energy, contrast, correlation, inverse difference moment, sum average, sum variance, sum entropy, difference average, difference entropy, information measure of correlation 1 and information measure of correlation 2) [23].…”

Section: Shape and Texture Featuresmentioning

confidence: 99%

“…El-Faramawy et al examined the useflulness of shape factors such as compactness, moments, Fourier descriptors, and statistics of chord lengths in distinguishing between circumscribed/spiculated and benign/malignant masses. Features are evaluated by mahalanobis distance procedures in the BMDP program [5]. Giger et a!.…”

Section: Introductionmentioning

confidence: 99%

<title>Comparative of shape and texture features in classifications of breast masses in digitized mammograms</title>

et al. 2000

View full text Add to dashboard Cite

The aim of this work was to determine a methodology to selection of the best features subset and artificial neural network (ANN) topology to classify masses lesions. The backpropagation training algorithm was used to adjust the weights of ANN. A total of 118 regions of interest images were chosen (68 benign and 50 malignant lesions). In a first step, images were submitted to a combined process of thresholding, mathematical morphology, and region growing techniques. After, fourteen texture features (Haralick descriptors) and fourteen shape features (circularity, compactness, Gupta descriptors, Shen descriptors, Hu descriptors, Fourier descriptor and Wee descriptors) were extracted. The Jeffries-Matusita method was used to select the best features. Three shape features sets and three texture features sets were selected. The Receiver Operating Characteristic (ROC) analyses were conducted to evaluated the classifier performance. The best result for shape features set was accurate classification rate of 98.21%, specificity of 98.37%, sensitivity of 98.00% and the area under ROC curve of 0.99, for a ANN with 5 hidden units. The best result for texture feature set was accurate classification rate of 97.08%, specificity of98.53%, sensitivity of95.l 1% and the area under ROC curve of0.98, for an ANN with 4 hidden units.

show abstract

“…Most of the shape analysis methods [5], [6], are focused on computing global measures characterizing the boundary's shape. Such methods are relatively insensitive to important local changes due to lobulations and spicules.…”

Section: Mass Descriptor Based On Occurrence Intersection Coding (Mdo)mentioning

confidence: 99%

“…The most used descriptors are: circularity, rectangularity [2], compactness(C), spiculation index (SI), fractional concavity (F cc ) [3], fractal dimension [4], Fourier descriptors [5] and statistics based on the distribution of the Normalized Radial Length [6]. One important feature in automated malignity recognition is spiculation level characterization.…”

Section: Introductionmentioning

confidence: 99%

Mass Description for Breast Cancer Recognition

Cheikhouhou

Djemal

Maaref

2010

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In this paper, we present a robust shape descriptor named the Mass Descriptor based on Occurrence intersection coding (MDO) using the contour fluctuation detection. This descriptor allows a good characterization of the breast lesions and so a good classification performance. The efficiency of the proposed descriptor is evaluated on known Digital Database for Screening Mammography DDSM using the area under the Receiver Operating Characteristics (ROC) curve analysis. Results show that the specified descriptor has proven its performance in breast mass recognition using Support Vector Machine (SVM) classifier.

show abstract

Shape factors for analysis of breast tumors in mammograms

Cited by 17 publications

References 8 publications

Modelling nasal airflow using a Fourier descriptor representation of geometry

Modelling nasal airflow using a Fourier descriptor representation of geometry

<title>Comparative of shape and texture features in classifications of breast masses in digitized mammograms</title>

Mass Description for Breast Cancer Recognition

Contact Info

Product

Resources

About