Learning contextual relationships in mammograms using a hierarchical pyramid neural network

This paper describes a pattern recognition architecture, which we term hierarchical pyramid/neural network (HPNN), that learns to exploit image structure at multiple resolutions for detecting clinically significant features in digital/digitized mammograms. The HPNN architecture consists of a hierarchy of neural networks, each network receiving feature inputs at a given scale as well as features constructed by networks lower in the hierarchy. Networks are trained using a novel error function for the supervised learning of image search/detection tasks when the position of the objects to be found is uncertain or ill defined. We have evaluated the HPNN's ability to eliminate false positive (FP) regions of interest generated by the University of Chicago's (UofC) Computer-aided diagnosis (CAD) systems for microcalcification and mass detection. Results show that the HPNN architecture, trained using the uncertain object position (UOP) error function, reduces the FP rate of a mammographic CAD system by approximately 50% without significant loss in sensitivity. Investigation into the types of FPs that the HPNN eliminates suggests that the pattern recognizer is automatically learning and exploiting contextual information. Clinical utility is demonstrated through the evaluation of an integrated system in a clinical reader study. We conclude that the HPNN architecture learns contextual relationships between features at multiple scales and integrates these features for detecting microcalcifications and breast masses.     

Segmentation algorithms for detecting microcalcifications inmammograms

The presence of microcalcification clusters in mammograms contributes evidence for the diagnosis of early stages of breast cancer. In many cases, microcalcifications are subtle and their detection can benefit from an automated system serving as a diagnostic aid. The potential contribution of such a system may become more significant as the number of mammograms screened increases to levels that challenge the capacity of radiology clinics. Many techniques for detecting microcalcifications start with a segmentation algorithm that indicates all candidate structures for the subsequent phases. Most algorithms used to segment microcalcifications have aspects that might raise operational difficulties, such as thresholds or windows that must be selected, or parametric models of the data. We present a new segmentation algorithm and compare it to two other algorithms: the multi-tolerance region-growing algorithm, which operates without the aspects mentioned above, and the active contour model, which has not been applied previously to segment microcalcifications. The new algorithm operates without threshold or window selection or parametric data models, and it is more than an order of magnitude faster than the other two     

Analysis of mammographic microcalcifications using gray-level image structure features

At present, mammography associated with clinical breast examination and breast self-examination is the only effective and viable method for mass breast screening. The presence of microcalcifications is one of the primary signs of breast cancer. It is, difficult however, to distinguish between benign and malignant microcalcifications associated with breast cancer. Here, the authors define a set of image structure features for classification of malignancy. Two categories of correlated gray-level image structure features are defined for classification of "difficult-to-diagnose" cases. The first category of features includes second-order histogram statistics-based features representing the global texture and the wavelet decomposition-based features representing the local texture of the microcalcification area of interest. The second category of features represents the first-order gray-level histogram-based statistics of the segmented microcalcification regions and the size, number, and distance features of the segmented microcalcification cluster. Various features in each category were correlated with the biopsy examination results of 191 "difficult-to-diagnose" cases for selection of the best set of features representing the complete gray-level image structure information. The selection of the best features was performed using the multivariate cluster analysis as well as a genetic algorithm (GA)-based search method. The selected features were used for classification using backpropagation neural network and parameteric statistical classifiers. Receiver operating characteristic (ROC) analysis was performed to compare the neural network-based classification with linear and k-nearest neighbor (KNN) classifiers. The neural network classifier yielded better results using the combined set of features selected through the GA-based search method for classification of "difficult-to-diagnose" microcalcifications.     

A novel approach to microcalcification detection using fuzzy logictechnique

Breast cancer continues to be a significant public health problem in the United States. Approximately, 182,000 new cases of breast cancer are diagnosed and 46,000 women die of breast cancer each year. Even more disturbing is the fact that one out of eight women in the United States will develop breast cancer at some point during her lifetime. Since the cause of breast cancer remains unknown, primary prevention becomes impossible. Computer-aided mammography is an important and challenging task in automated diagnosis. It has great potential over traditional interpretation of film-screen mammography in terms of efficiency and accuracy. Microcalcifications are the earliest sign of breast carcinomas and their detection is one of the key issues for breast cancer control. In this study, a novel approach to microcalcification detection based on fuzzy logic technique is presented. Microcalcifications are first enhanced based on their brightness and nonuniformity. Then, the irrelevant breast structures are excluded by a curve detector. Finally, microcalcifications are located using an iterative threshold selection method. The shapes of microcalcifications are reconstructed and the isolated pixels are removed by employing the mathematical morphology technique. The essential idea of the proposed approach is to apply a fuzzified image of a mammogram to locate the suspicious regions and to interact the fuzzified image with the original image to preserve fidelity. The major advantage of the proposed method is its ability to detect microcalcifications even in very dense breast mammograms. A series of clinical mammograms are employed to test the proposed algorithm and the performance is evaluated by the free-response receiver operating characteristic curve. The experiments aptly show that the microcalcifications can be accurately detected even in very dense mammograms using the proposed approach     

基于多尺度空间滤波和l1范数最近邻分类的乳腺图像微钙化点检测

钙化信息是乳腺癌早期诊断的一个重要依据,针对钙化点检测检出率较低和假阳性较高的问题,提出一种基于多尺度空间滤波和l1范数最近邻分类的乳腺图像微钙化点检测算法.首先利用多尺度空间滤波方法得到原图像的多尺度显著特征图,然后通过基于人眼视觉特性的钙化点分割方法得到粗检测钙化点的二值图像,并送入l1范数最近邻分类器去除假阳性点...     

Digital mammography: mixed feature neural network with spectral entropy decision for detection of microcalcifications

A computationally efficient mixed feature based neural network (MFNN) is proposed for the detection of microcalcification clusters (MCCs) in digitized mammograms. The MFNN employs features computed in both the spatial and spectral domain and uses spectral entropy as a decision parameter. Backpropagation with Kalman filtering (KF) is employed to allow more efficient network training as required for evaluation of different features, input images, and related error analysis. A previously reported, wavelet-based image-enhancement method is also employed to enhance microcalcification clusters for improved detection. The relative performance of the MFNN for both the raw and enhanced images is evaluated using a common image database of 30 digitized mammograms, with 20 images containing 21 biopsy proven MCCs and ten normal cases. The computed sensitivity (true positive (TP) detection rate) was 90.1% with an average low false positive (FP) detection of 0.71 MCCs/image for the enhanced images using a modified k-fold validation error estimation technique. The corresponding computed sensitivity for the raw images was reduced to 81.4% and with 0.59 FP's MCCs/image. A relative comparison to an earlier neural network (NN) design, using only spatially related features, suggests the importance of the addition of spectral domain features when the raw image data is analyzed.     

Statistical textural features for detection of microcalcificationsin digitized mammograms

Clustered microcalcifications on X-ray mammograms are an important sign for early detection of breast cancer. Texture-analysis methods can be applied to detect clustered microcalcifications in digitized mammograms. In this paper, a comparative study of texture-analysis methods is performed for the surrounding region-dependence method, which has been proposed by the authors, and conventional texture-analysis methods, such as the spatial gray-level dependence method, the gray-level run-length method, and the gray-level difference method. Textural features extracted by these methods are exploited to classify regions of interest (ROI's) into positive ROI's containing clustered microcalcifications and negative ROI's containing normal tissues. A three-layer backpropagation neural network is used as a classifier. The results of the neural network for the texture-analysis methods are evaluated by using a receiver operating-characteristics (ROC) analysis. The surrounding region-dependence method is shown to be superior to the conventional texture-analysis methods with respect to classification accuracy and computational complexity.     

Detection of microcalcifications in digital mammograms usingwavelets

This paper presents an approach for detecting micro-calcifications in digital mammograms employing wavelet-based subband image decomposition. The microcalcifications appear in small clusters of few pixels with relatively high intensity compared with their neighboring pixels. These image features can be preserved by a detection system that employs a suitable image transform which can localize the signal characteristics in the original and the transform domain. Given that the microcalcifications correspond to high-frequency components of the image spectrum, detection of microcalcifications is achieved by decomposing the mammograms into different frequency subbands, suppressing the low-frequency subband, and, finally, reconstructing the mammogram from the subbands containing only high frequencies. Preliminary experiments indicate that further studies are needed to investigate the potential of wavelet-based subband image decomposition as a tool for detecting microcalcifications in digital mammograms     

An adaptive density-weighted contrast enhancement filter for mammographic breast mass detection

Presents a novel approach for segmentation of suspicious mass regions in digitized mammograms using a new adaptive density-weighted contrast enhancement (DWCE) filter in conjunction with Laplacian-Gaussian (LG) edge detection. The DWCE enhances structures within the digitized mammogram so that a simple edge detection algorithm can be used to define the boundaries of the objects. Once the object boundaries are known, morphological features are extracted and used by a classification algorithm to differentiate regions within the image. This paper introduces the DWCE algorithm and presents results of a preliminary study based on 25 digitized mammograms with biopsy proven masses. It also compares morphological feature classification based on sequential thresholding, linear discriminant analysis, and neural network classifiers for reduction of false-positive detections.     

Scale-space signatures for the detection of clustered microcalculations in digital mammograms

A method is described for the automated detection of microcalcifications in digitized mammograms. The method is based on the Laplacian scale-space representation of the mammogram only. First, possible locations of microcalcifications are identified as local maxima in the filtered image on a range of scales. For each finding, the size and local contrast is estimated, based on the Laplacian response denoted as the scale-space signature. A finding is marked as a microcalcification if the estimated contrast is larger than a predefined threshold which depends on the size of the finding. It is shown that the signature has a characteristic peak, revealing the corresponding image features. This peak can be robustly determined. The basic method is significantly improved by consideration of the statistical variation of the estimated contrast, which is the result of the complex noise characteristic of the mammograms. The method is evaluated with the Nijmegen database and compared to other methods using these mammograms. Results are presented as the free-response receiver operating characteristic (FROC) performance. At a rate of one false positive cluster per image the method reaches a sensitivity of 0.84, which is comparable to the best results achieved so far.     

Optimization of wavelet decomposition for image compression and feature preservation

A neural-network-based framework has been developed to search for an optimal wavelet kernel that can be used for a specific image processing task. In this paper, a linear convolution neural network was employed to seek a wavelet that minimizes errors and maximizes compression efficiency for an image or a defined image pattern such as microcalcifications in mammograms and bone in computed tomography (CT) head images. We have used this method to evaluate the performance of tap-4 wavelets on mammograms, CTs, magnetic resonance images, and Lena images. We found that the Daubechies wavelet or those wavelets with similar filtering characteristics can produce the highest compression efficiency with the smallest mean-square-error for many image patterns including general image textures as well as microcalcifications in digital mammograms. However, the Haar wavelet produces the best results on sharp edges and low-noise smooth areas. We also found that a special wavelet whose low-pass filter coefficients are 0.32252136, 0.85258927, 1.38458542, and -0.14548269) produces the best preservation outcomes in all tested microcalcification features including the peak signal-to-noise ratio, the contrast and the figure of merit in the wavelet lossy compression scheme. Having analyzed the spectrum of the wavelet filters, we can find the compression outcomes and feature preservation characteristics as a function of wavelets. This newly developed optimization approach can be generalized to other image analysis applications where a wavelet decomposition is employed.     

Three-dimensional reconstruction of microcalcification clustersfrom two mammographic views

Classification of benign/malignant microcalcification clusters is a major diagnostic challenge for radiologists. Clinical studies have revealed that the shape of the cluster, and the spatial distribution of individual microcalcifications within it, are important indicators of its malignancy. However, mammographic images of clustered microcalcifications confound their three-dimensional (3-D) distribution with image projection and breast compression. This paper presents a novel model-based method for reconstructing microcalcification clusters in 3-D from two mammographic views (cranio-caudal and medio-lateral oblique--"shoulder to the opposite hip" or lateral-medio). We develop a 3-D breast representation and a parameterised breast compression model which constraints geometrically the possible 3-D positions of a calcification in a two-dimensional image. Corresponding calcifications in the two views are matched using an estimate of the calcification volume. Both the geometric constraint and the matching criterion are utilized in the final reconstruction step to build the 3-D reconstructed clusters. Validation experiments are described using 30 clusters to verify the individual steps of the model, and results consistent with known ground truth are obtained. Some of the approximations in the model and future work are discussed in the concluding section.     

Detection of Clustered Microcalcifications on Mammograms Using Surrounding Region Dependence Method and Artificial Neural Network

Clustered microcalcifications on X-ray mammograms are an important sign in the detection of breast cancer. A statistical texture analysis method, called the surrounding region dependence method (SRDM), is proposed for the detection of clustered microcalcifications on digitized mammograms. The SRDM is based on the second-order histogram in two surrounding regions. This method defines four textural features to classify region of interests (ROIs) into positive ROIs containing clustered microcalcifications and negative ROIs of normal tissues. The database is composed of 64 positive and 76 negative ROI images, which are selected from digitized mammograms with a pixel size of 100 × 100 m² and 12 bits per pixel. An ROI is selected as an area of 128 × 128 pixels on the digitized mammograms. In order to classify ROIs into the two types, a three-layer backpropagation neural network is employed as a classifier. A segmentation of individual microcalcifications is also proposed to show their morphologies. The classification performance of the proposed method is evaluated by using the round-robin method and a free-response receiver operating-characteristics (FROC) analysis. A receiver operating-characteristics (ROC) analysis is employed to present the results of the round-robin testing for the case of several hidden neurons. The area under the ROC curve, A _z, is 0.997, which is achieved in the case of 4 hidden neurons. The FROC analysis is performed on 20 cropped images. A cropped image is selected as an area of 512 × 512 pixels on the digitized mammograms. In terms of the FROC, a sensitivity of more than 90% is obtained with a low false-positive (FP) detection rate of 0.67 per cropped image.     

A computer-aided diagnosis system for digital mammograms based onfuzzy-neural and feature extraction techniques

An intelligent computer-aided diagnosis system can be very helpful for radiologist in detecting and diagnosing microcalcification patterns earlier and faster than typical screening programs. In this paper, we present a system based on fuzzy-neural and feature extraction techniques for detecting and diagnosing microcalcifications' patterns in digital mammograms. We have investigated and analyzed a number of feature extraction techniques and found that a combination of three features (such as entropy, standard deviation and number of pixels) is the best combination to distinguish a benign microcalcification pattern from one that is malignant. A fuzzy technique in conjunction with three features was used to detect a microcalcification pattern and a neural network was used to classify it into benign/malignant. The system was developed on a Microsoft Windows platform. It is an easy-to-use intelligent system that gives the user options to diagnose, detect, enlarge, zoom and measure distances of areas in digital mammograms     

Application of Artificial Neural Networks to Medical Image Pattern Recognition: Detection of Clustered Microcalcifications on Mammograms and Lung Cancer on Chest Radiographs

Three neural network models were employed to evaluate their performances in the recognition of medical image patterns associated with lung cancer and breast cancer in radiography. The first method was a pattern match neural network. The second was a conventional backpropagation neural network. The third method was a backpropagation trained neocognitron in which the signal propagation is operated with the convolution calculation from one layer to the next. In the convolution neural network (CNN) experiment, several output association methods and trainer imposed driving functions in conjunction with the convolution neural network are proposed for general medical image pattern recognition. An unconventional method of applying rotation and shift invariance is also used to enhance the performance of the neural nets.We have tested these methods for the detection of microcalcifications on mammograms and lung nodules on chest radiographs. Pre-scan methods were previously described in our early publications. The artificial neural networks act as final detection classifiers to determine if a disease pattern is presented on the suspected image area. We found that the convolution neural network, which internally performs feature extraction and classification, achieves the best performance among the three neural network models. These results show that some processing associated with disease feature extraction is a necessary step before a classifier can make an accurate determination.     

Computer-aided diagnosis scheme using a filter bank for detection of microcalcification clusters in mammograms

Mammography is considered the most effective method for early detection of breast cancers. However, it is difficult for radiologists to detect microcalcification clusters. Therefore, we have developed a computerized scheme for detecting early-stage microcalcification clusters in mammograms. We first developed a novel filter bank based on the concept of the Hessian matrix for classifying nodular structures and linear structures. The mammogram images were decomposed into several subimages for second difference at scales from 1 to 4 by this filter bank. The subimages for the nodular component (NC) and the subimages for the nodular and linear component (NLC) were then obtained from analysis of the Hessian matrix. Many regions of interest (ROIs) were selected from the mammogram image. In each ROI, eight features were determined from the subimages for NC at scales from 1 to 4 and the subimages for NLC at scales from 1 to 4. The Bayes discriminant function was employed for distinguishing among abnormal ROIs with a microcalcification cluster and two different types of normal ROIs without a microcalcification cluster. We evaluated the detection performance by using 600 mammograms. Our computerized scheme was shown to have the potential to detect microcalcification clusters with a clinically acceptable sensitivity and low false positives.     

Noise equalization for detection of microcalcification clusters in direct digital mammogram images

Equalizing image noise is shown to be an important step in the automatic detection of microcalcifications in digital mammography. This study extends a well established film-screen noise equalization scheme developed by Veldkamp et al. for application to full-field digital mammogram (FFDM) images. A simple noise model is determined based on the assumption that quantum noise is dominant in direct digital X-ray imaging. Estimation of the noise as a function of the gray level is improved by calculating the noise statistics using a truncated distribution method. Experimental support for the quantum noise assumption is presented for a set of step wedge phantom images. Performance of the noise equalization technique is also tested as a preprocessing stage to a microcalcification detection scheme. It is shown that the square root model based approach which FFDM allows leads to a robust estimation of the high frequency image noise. This provides better microcalcification detection performance when compared to the film-screen noise equalization method developed by Veldkamp. Substantially better results are obtained than when noise equalization is omitted. A database of 124 direct digital mammogram images containing 28 microcalcification clusters was used for evaluation of the method.     

Wavelet transforms for detecting microcalcifications in mammograms

Clusters of fine, granular microcalcifications in mammograms may be an early sign of disease. Individual grains are difficult to detect and segment due to size and shape variability and because the background mammogram texture is typically inhomogeneous. The authors develop a 2-stage method based on wavelet transforms for detecting and segmenting calcifications. The first stage is based on an undecimated wavelet transform, which is simply the conventional filter bank implementation without downsampling, so that the low-low (LL), low-high (LH), high-low (HL), and high-high (HH) sub-bands remain at full size. Detection takes place in HH and the combination LH+HL. Four octaves are computed with 2 inter-octave voices for finer scale resolution. By appropriate selection of the wavelet basis the detection of microcalcifications in the relevant size range can be nearly optimized. In fact, the filters which transform the input image into HH and LH+HL are closely related to prewhitening matched filters for detecting Gaussian objects (idealized microcalcifications) in 2 common forms of Markov (background) noise. The second stage is designed to overcome the limitations of the simplistic Gaussian assumption and provides an accurate segmentation of calcification boundaries. Detected pixel sites in HH and LH+HL are dilated then weighted before computing the inverse wavelet transform. Individual microcalcifications are greatly enhanced in the output image, to the point where straightforward thresholding can be applied to segment them. FROG curves are computed from tests using a freely distributed database of digitized mammograms.     

Uncertainty in the output of artificial neural networks

Analysis of the performance of artificial neural networks (ANNs) is usually based on aggregate results on a population of cases. In this paper, we analyze ANN output corresponding to the individual case. We show variability in the outputs of multiple ANNs that are trained and "optimized" from a common set of training cases. We predict this variability from a theoretical standpoint on the basis that multiple ANNs can be optimized to achieve similar overall performance on a population of cases, but produce different outputs for the same individual case because the ANNs use different weights. We use simulations to show that the average standard deviation in the ANN output can be two orders of magnitude higher than the standard deviation in the ANN overall performance measured by the Az value. We further show this variability using an example in mammography where the ANNs are used to classify clustered microcalcifications as malignant or benign based on image features extracted from mammograms. This variability in the ANN output is generally not recognized because a trained individual ANN becomes a deterministic model. Recognition of this variability and the deterministic view of the ANN present a fundamental contradiction. The implication of this variability to the classification task warrants additional study.     

Segmentation of microcalcifications in mammograms

A systematic method for the detection and segmentation of microcalcifications in mammograms is presented. It is important to preserve size and shape of the individual calcifications as exactly as possible. A reliable diagnosis requires both rates of false positives as well as false negatives to be extremely low. The proposed approach uses a two-stage algorithm for spot detection and shape extraction. The first stage applies a weighted difference of Gaussians filter for the noise-invariant and size-specific detection of spots. A morphological filter reproduces the shape of the spots. The results of both filters are combined with a conditional thickening operation. The topology and the number of the spots are determined with the first filter, and the shape by means of the second. The algorithm is tested with a series of real mammograms, using identical parameter values for all images. The results are compared with the judgement of radiological experts, and they are very encouraging. The described approach opens up the possibility of a reproducible segmentation of microcalcifications, which is a necessary precondition for an efficient screening program.