No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
On the combination of wavelet and curvelet for feature extraction to classify lung cancer on chest radiographs
Abstract
This paper investigates the combination of multiresolution methods for feature extraction for lung cancer. The focus is on the impact of combining wavelet and curvelet on the accuracy of the disease diagnosis. The paper investigates feature extraction with two different levels of wavelet, two different wavelet functions and the combination of wavelet and curvelet to obtain a high classification rate. The findings suggest the potential of combining different multiresolution methods in achieving high accuracy rates.
... Cluster-K-Nearest Neighbor (C-K-NN) [13], [14] is a classifier that combines two algorithms; the K-means modified algorithm [15] and the K-Nearest neighbor. Data is clustered into classes and sub-classes with a centre point to represent each class using K-means. ...
In biological studies, species identification is considered one of the most important issues. Several methods have been suggested to identify species using the whole DNA sequences. In this study, we present new insights for species identification using only part of the DNA sequence. The Clustering k-Nearest Neighbor (K-C-NN) and Support Vector Machine (SVM) classifiers were used to test and evaluate the improved statistical features extracted from DNA sequences for four species (Aquifex aeolicus, Bacillus subtilis, Aeropyrum pernix and Buchnera sp). The results show that part of DNA sequences can be used to identify species.
... Thus, Gabor wavelets and curvelets are mutually complementary. Recently, the combination of wavelet and curvelet transforms has been reported in some applications for image denoising and feature extraction [33][34][35][36], which their findings suggest the potential of the combination. Thus, we apply both methods to create texture feature vectors for the best classification accuracy. ...
In RBIR, texture features are crucial in determining the class a region belongs to since they can overcome the limitations of color and shape features. Two robust approaches to model texture features are Gabor and curvelet features. Although both features are close to human visual perception, sufficient information needs to be extracted from their sub-bands for effective texture classification. Moreover, shape irregularity can be a problem since Gabor and curvelet transforms can only be applied on the regular shapes. In this paper, we propose an approach that uses both the Gabor wavelet and the curvelet transforms on the transferred regular shapes of the image regions. We also apply a fitting method to encode the sub-bands’ information in the polynomial coefficients to create a texture feature vector with the maximum power of discrimination. Experiments on texture classification task with ImageCLEF and Outex databases demonstrate the effectiveness of the proposed approach.
OBJECTIVE. We developed a digital image database (www.macnet.or.jp/jsrt2/cdrom_nodules.html) of 247 chest radiographs with and without a lung nodule. The aim of this study was to investigate the characteristics of image databases for potential use in various digital image research projects. Radiologists' detection of solitary pulmonary nodules included in the database was evaluated using a receiver operating characteristic (ROC) analysis.MATERIALS AND METHODS. One hundred and fifty-four conventional chest radiographs with a lung nodule and 93 radiographs without a nodule were selected from 14 medical centers and were digitized by a laser digitizer with a 2048 × 2048 matrix size (0.175-mm pixels) and a 12-bit gray scale. Lung nodule images were classified into five groups according to the degrees of subtlety shown. The observations of 20 participating radiologists were subjected to ROC analysis for detecting solitary pulmonary nodules. Experimental results (areas under the curve, Az) obtained from observer...
In this paper a computational alternative to classify lung nodules inside CT thorax images in the frequency domain is presented. After image acquisition, a region of interest is manually selected. Then, the spectrums of the two dimensional Discrete Cosine Transform (2D-DCT) and the two dimensional Fast Fourier Transform (2D-FFT) were calculated. Later, two statistical texture features were extracted from the histogram computed from the spectrum of each CT image. Finally, a support vector machine with a radial basis function as a kernel was used as the classifier. Seventy five tests with different diagnosis and number of images were used to validate the methodology presented. After experimentation and results, ten false negatives (FN) and two false positives (FP) were obtained, and a sensitivity and specificity of 96.15% and 52.17% respectively. The total preciseness obtained with the methodology proposed was 82.66%.},
keywords={computerised tomography;discrete cosine transforms;fast Fourier transforms;image classification;lung;medical image processing;support vector machines;2D-DCT;2D-FFT;CT thorax images;frequency domain;image acquisition;lung nodule classification;radial basis function;statistical texture features;support vector machines;two dimensional discrete cosine transform;two dimensional fast Fourier transform;Cancer;Computed tomography;Discrete cosine transforms;Feature extraction;Frequency domain analysis;Lungs;Support vector machines;Computer Tomography (CT);Discrete Cosine Transform (DCT);Fast Fourier Transform (FFT);Lung nodule detection (LND);Support Vector Machine (SVM)
This paper describes two digital implementations of a new mathematical transform, namely, the second generation curvelet transform in two and three dimensions. The first digital transformation is based on unequally spaced fast Fourier transforms, while the second is based on the wrapping of specially selected Fourier samples. The two implementations essentially differ by the choice of spatial grid used to translate curvelets at each scale and angle. Both digital transformations return a table of digital curvelet coefficients indexed by a scale parameter, an orientation parameter, and a spatial location parameter. And both implementations are fast in the sense that they run in O(n^2 log n) flops for n by n Cartesian arrays; in addition, they are also invertible, with rapid inversion algorithms of about the same complexity. Our digital transformations improve upon earlier implementations—based upon the first generation of curvelets—in the sense that they are conceptually simpler, faster, and far less redundant. The software CurveLab, which implements both transforms presented in this paper, is available at http://www.curvelet.org.
Multiresolution representations are effective for analyzing the
information content of images. The properties of the operator which
approximates a signal at a given resolution were studied. It is shown
that the difference of information between the approximation of a signal
at the resolutions 2<sup>j+1</sup> and 2<sup>j</sup> (where j is an
integer) can be extracted by decomposing this signal on a wavelet
orthonormal basis of L <sup>2</sup>( R <sup>n</sup>), the
vector space of measurable, square-integrable n -dimensional
functions. In L <sup>2</sup>( R ), a wavelet orthonormal
basis is a family of functions which is built by dilating and
translating a unique function ψ( x ). This decomposition
defines an orthogonal multiresolution representation called a wavelet
representation. It is computed with a pyramidal algorithm based on
convolutions with quadrature mirror filters. Wavelet representation lies
between the spatial and Fourier domains. For images, the wavelet
representation differentiates several spatial orientations. The
application of this representation to data compression in image coding,
texture discrimination and fractal analysis is discussed
Lung cancer is the most common fatal malignancy in both men and women. Early detection and treatment of lung cancer can greatly improve the survival rate of patient. The present work describes the design and development of a two stage computer-aided diagnosis (CAD) system that can automatically detect and diagnose histological images such as CT scan of lung with a nodule into cancerous or non- cancerous nodule. In the first stage the input image is pre- processed and the cancerous nodule region is segmented and the second stage involves in diagnosis of the nodal based on fuzzy system based on the area and the grey level of the nodule region. The aim of the proposed work is also to reduce the false positive classifications while maintaining a high degree of true- positive diagnosis. The proposed method attains an accuracy of 90% with high true positive rates and also high detection sensitivity and specificity that can meet basically the requirement of clinical diagnosis.
By taking advantage of both k-NN which is highly accurate and K-means cluster which is able to reduce the time of classification, we can introduce Cluster-k-Nearest Neighbor as "variable k"-NN dealing with the centroid or mean point of all subclasses generated by clustering algorithm. In general the algorithm of K-means cluster is not stable, in term of accuracy, for that reason we develop another algorithm for clustering our space which gives a higher accuracy than K-means cluster, less subclass number, stability and bounded time of classification with respect to the variable data size. We find between 96% and 99.7 % of accuracy in the classification of 6 different types of Time series by using K-means cluster algorithm and we find 99.7% by using the new clustering algorithm.
In order to classify lung nodules, an approach combining rule-based and SVM is proposed in the paper. Firstly, the candidate ROIs shape features are calculated, and some blood vessels are get rid of using rule-based according to shape features; secondly, the remainder candidates gray and texture features are calculated; finally, the shape, gray and texture features are taken as the inputs of the SVM (Support Vector Machine) classifier to classify the candidates. Experimental results show that the rule-based approach has no omission, but the misclassification probability is too large; the approach combining rule-based and SVM has higher omission than SVM, but lower misclassification. The causes of nodules omission and misclassification are summarized and the solution is discussed in the paper at last.
A neural network ensemble (NNE) scheme was designed for distinguishing probably benign, uncertain and probably malignant lung nodules on thin-section CT images. To construct the NNE scheme, a multilayer neural network with the back-propagation algorithm (BPNN), a radial basis probabilistic neural network (RBPNN) and a learning vector quantization neural network (LVQNN) were employed, and the Bayesian criterion was used as combination rule to integrate the outputs of individual neural networks. Experimental results illustrated that the proposed classification scheme had higher classification accuracy (78.7%) as compared to the best individual classifier (LVQNN: 68.1%), as well as to another NNE scheme with the same individual neural networks but with majority voting combination rule.
An automated lung nodule detection system can help spot lung abnormalities in CT lung images. Lung nodule detection can be achieved using template-based, segmentation-based, and classification-based methods. The existing systems that include a classification component in their structures have demonstrated better performances than their counterparts. Ensemble learners combine decisions of multiple classifiers to form an integrated output. To improve the performance of automated lung nodule detection, an ensemble classification aided by clustering (CAC) method is proposed. The method takes advantage of the random forest algorithm and offers a structure for a hybrid random forest based lung nodule classification aided by clustering. Several experiments are carried out involving the proposed method as well as two other existing methods. The parameters of the classifiers are varied to identify the best performing classifiers. The experiments are conducted using lung scans of 32 patients including 5721 images within which nodule locations are marked by expert radiologists. Overall, the best sensitivity of 98.33% and specificity of 97.11% have been recorded for proposed system. Also, a high receiver operating characteristic (ROC) A(z) of 0.9786 has been achieved.
Lung cancer is a disease with significant prevalence in several countries around the world. Its difficult treatment and rapid progression make the mortality rates among people affected by this illness to be very high. Aiming to offer a computational alternative for helping in detection of nodules, serving as a second opinion to the specialists, this work proposes a totally automatic methodology based on successive detection refining stages. The automated lung nodules detection scheme consists of six stages: thorax extraction, lung extraction, lung reconstruction, structures extraction, tubular structures elimination, and false positive reduction. In the thorax extraction stage all the artifacts external to the patient's body are discarded. Lung extraction stage is responsible for the identification of the lung parenchyma. The objective of the lung reconstruction stage is to prevent incorrect elimination of portions belonging to the parenchyma. Structures extraction stage comprises the selection of dense structures from inside the lung parenchyma. The next stage, tubular structures elimination eliminates a great part of the pulmonary trees. Finally, the false positive stage selects only structures with great probability to be nodule. Each of the several stages has very specific objectives in detection of particular cases of lung nodules, ensuring good matching rates even in difficult detection situations. We use 33 exams with diversified diagnosis and slices numbers for validating the methodology. We obtained a false positive per exam rate of 0.42 and false negative rate of 0.15. The total classification sensitivity obtained, measured out of the nodule candidates, was 84.84%. The specificity achieved was 96.15% and the total accuracy of the method was 95.21%.
Methodology for automatic detection of lung nodules in computerized tomography images
- J R F Da Silva
- Sousa
J. R. F. da Silva Sousa, et al., "Methodology for automatic detection
of lung nodules in computerized tomography images," Computer
Methods and Programs in Biomedicine, vol. 98, pp. 1-14, 2010.
Robust and Automated Lung Nodule Diagnosis from CT Images Based on Fuzzy Systems
- S A Kumar
S. A. Kumar, et al., "Robust and Automated Lung Nodule Diagnosis
from CT Images Based on Fuzzy Systems," in Process Automation,
Control and Computing (PACC), 2011 International Conference on,
2011, pp. 1-6.
Modified k-means cluster
- B B Samir
B. B. Samir, "Modified k-means cluster," Universiti Teknologi
PETRONAS2008.