Zheng B, Qain W, Clarke LP. Digital mammography: Mixed feature neural network with spectral entropy decision for detection of microcalcifications. IEEE Trans Med Imag 1996;15(5):589--97.  Home/Search   Document Not in Database   Summary   Related Articles   Check

.... reported for the characterization of ROI such as, rule based systems [9,12] fuzzy logic systems [11] statistical methods based on Markov random fields [20] and support vector machines [3] Nevertheless, the most work reported in the literature employs neural networks for cluster characterization [10,27,33,37,51,54,55,58,59,61]. Typically, a neural network accepts as input features computed for a specific region of interest and provides as output a characterization of the region as true microcalcification cluster or not. Recently, neural networks have also been used to characterize a microcalcification as malignant or ....

Zheng B, Qain W, Clarke LP. Digital mammography: Mixed feature neural network with spectral entropy decision for detection of microcalcifications. IEEE Trans Med Imag 1996;15(5):589--97.

....applications has been on detection of microcalcification clusters (MCCs) which is technically an easier problem than detection of masses or architectural distortions. The inputs to the detection networks take two forms: i) 2 D images, e.g. 30] 42] and (ii) 1 D feature pattern vectors, e.g. [43] [48] Handling these fundamentally different inputs requires different architectures, in particular connections between layers and within layers. In both cases the emphasis is on feedforward architectures which utilize some form of backpropagation learning algorithm. Table 1 summarizes the ....

....for training and 50 for testing) 1 The cluster criterion (cc) determines the minimum number of microcalcifications on 1 mm 2 , required for a detected cluster. 3.2 Detection using ANN with 1 D input The ANNs using 1 D inputs also use feed forward architecture. The method proposed in [43] uses a single feed forward network, with a set of 4 spatial and spectral features for detection of the MCCs. The ROIs were first enhanced by nonlinear wavelet reconstruction. The cluster criterion of cc = 3 was used. Performance evaluation was done using modified leavegroup out scheme (without ....

B. Zheng, W. Qian, and L.P. Clarke, "Digital Mammography: Mixed Feature Neural Network with Spectral Entropy Decision for Detection of Microcalcifications, " IEEE Trans. Medical Imaging, vol. 15, no. 5, Oct. 1996.

.... denoising method for MRI images [12] which was the precursor of Donoho s wavelet shrinkage method [13] Perhaps most of the efforts in this area have been directed toward applying wavelets to digital mammography, for both image enhancement [14] and the detection of microcalcifications [15] [17]. In Section II, a brief review of the basic concepts of the wavelet transform is presented, with emphasis given to the selection of basis functions, and to implementation issues regarding multiple dimensions and discrete realizations. The present application of wavelets to the analysis of ....

B. Y. Zheng, W. Qian, and L. P. Clarke, "Digital mammography ---Mixed feature neural-network with spectral entropy decision for detecting microcalcifications," IEEE Trans. Med. Imag., vol. 15, pp. 589--597, Oct. 1996.

No context found.

Zheng B, Qian W, Clarke LP. Digital mammography: mixed feature neural network with spectral entropy decision for detection of microcalcifications. IEEE Trans Med Imaging 1996; 15:589--597.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC