Algorithm for the detection of fine clustered calcifications on film mammograms

Anniversary paper: History and status of CAD and quantitative image analysis: the role of Medical Physics and AAPM

The roles of physicists in medical imaging have expanded over the years, from the study of imaging systems (sources and detectors) and dose to the assessment of image quality and perception, the development of image processing techniques, and the development of image analysis methods to assist in detection and diagnosis. The latter is a natural extension of medical physicists' goals in developing imaging techniques to help physicians acquire diagnostic information and improve clinical decisions. Studies indicate that radiologists do not detect all abnormalities on images that are visible on retrospective review, and they do not always correctly characterize abnormalities that are found. Since the 1950s, the potential use of computers had been considered for analysis of radiographic abnormalities. In the mid-1980s, however, medical physicists and radiologists began major research efforts for computer-aided detection or computer-aided diagnosis (CAD), that is, using the computer output as an aid to radiologists-as opposed to a completely automatic computer interpretation-focusing initially on methods for the detection of lesions on chest radiographs and mammograms. Since then, extensive investigations of computerized image analysis for detection or diagnosis of abnormalities in a variety of 2D and 3D medical images have been conducted. The growth of CAD over the past 20 years has been tremendous-from the early days of time-consuming film digitization and CPU-intensive computations on a limited number of cases to its current status in which developed CAD approaches are evaluated rigorously on large clinically relevant databases. CAD research by medical physicists includes many aspects-collecting relevant normal and pathological cases; developing computer algorithms appropriate for the medical interpretation task including those for segmentation, feature extraction, and classifier design; developing methodology for assessing CAD performance; validating the algorithms using appropriate cases to measure performance and robustness; conducting observer studies with which to evaluate radiologists in the diagnostic task without and with the use of the computer aid; and ultimately assessing performance with a clinical trial. Medical physicists also have an important role in quantitative imaging, by validating the quantitative integrity of scanners and developing imaging techniques, and image analysis tools that extract quantitative data in a more accurate and automated fashion. As imaging systems become more complex and the need for better quantitative information from images grows, the future includes the combined research efforts from physicists working in CAD with those working on quantitative imaging systems to readily yield information on morphology, function, molecular structure, and more-from animal imaging research to clinical patient care. A historical review of CAD and a discussion of challenges for the future are presented here, along with the extension to quantitative image analysis.

Mammography and computerized decision systems: a review

Computer-aided diagnosis (CAD) systems in mammography have been developed and investigated for several years and recently they have left the research stage to enter the clinical stage. The purpose of this article is to review the present situation of mammography for breast cancer detection and the role played by CAD systems. Results from the recent literature show that CAD systems have the potential to improve the sensitivities of radiologists in the detection of malignant clustered microcalcifications and masses, while keeping specificities at acceptable levels. This leads to the conclusion that CAD systems can be incorporated into clinical practice as a double reading option to radiologists. However, some issues have yet to be tackled for CAD systems to gain better acceptance and more widespread use worldwide.

Use of artificial neural networks (computer analysis) in the diagnosis of microcalcifications on mammography

INTRODUCTION/OBJECTIVE

The purpose of this study was to evaluate a computer based method for differentiating malignant from benign clustered microcalcifications, comparing it with the performance of three physicians.

METHODS AND MATERIAL

Materials for the study are 240 suspicious microcalcifications on mammograms from 220 female patients who underwent breast biopsy, following hook wire localization under mammographic guidance. The histologic findings were malignant in 108 cases (45%) and benign in 132 cases (55%). Those clusters were analyzed by a computer program and eight features of the calcifications (density, number, area, brightness, diameter average, distance average, proximity average, perimeter compacity average) were quantitatively estimated by a specific artificial neural network. Human input was limited to initial identification of the calcifications. Three physicians-observers were also evaluated for the malignant or benign nature of the clustered microcalcifications.

RESULTS

The performance of the artificial network was evaluated by receiver operating characteristics (ROC) curves. ROC curves were also generated for the performance of each observer and for the three observers as a group. The ROC curves for the computer and for the physicians were compared and the results are:area under the curve (AUC) value for computer is 0.937, for physician-1 is 0.746, for physician-2 is 0.785, for physician-3 is 0.835 and for physicians as a group is 0.810. The results of the Student's t-test for paired data showed statistically significant difference between the artificial neural network and the physicians' performance, independently and as a group.

DISCUSSION AND CONCLUSION

Our study showed that computer analysis achieves statistically significantly better performance than that of physicians in the classification of malignant and benign calcifications. This method, after further evaluation and improvement, may help radiologists and breast surgeons in better predictive estimation of suspicious clustered microcalcifications and reduce the number of biopsies for non-palpable benign lesions.

A computer-aided design mammography screening system for detection and classification of microcalcifications

This paper presents a prototype of a computer-aided design (CAD) diagnostic system for mammography screening to automatically detect and classify microcalcifications (MCCs) in mammograms. It comprises four modules. The first module, called the Mammogram Preprocessing Module, inputs and digitizes mammograms into 8-bit images of size 2048x2048, extracts the breast region from the background, enhances the extracted breast and stores the processed mammograms in a data base. Since only clustered MCCs are of interest in providing a sign of breast cancer, the second module, called the MCCs Finder Module, finds and locates suspicious areas of clustered MCCs, called regions of interest (ROIs). The third module, called the MCCs Detection Module, is a real time computer automated MCCs detection system that takes as inputs the ROIs provided by the MCCs Finder Module. It uses two different window sizes to automatically extract the microcalcifications from the ROIs. It begins with a large window of size 64x64 to quickly screen mammograms to find large calcified areas, this is followed by a smaller window of size 8x8 to extract tiny, isolated microcalcifications. Finally, the fourth module, called the MCCs Classification Module, classifies the detected clustered microcalcifications into five categories according to BI-RADS (Breast Imaging Reporting and Data System) format recommended by the American College of Radiology. One advantage of the designed system is that each module is a separate component that can be individually upgraded to improve the whole system. Despite that it is still is a prototype system a preliminary clinical evaluation at TaiChung Veterans General Hospital (TCVGH) has shown that the system is very flexible and can be integrated with the existing Picture Archiving and Communications System (PACS) currently implemented in the Department of Radiology at TCVGH.

Computer-aided detection and diagnosis of breast cancer

The limitations of radiologists when interpreting mammogram examinations provides a reasonable, if not compelling, basis for application of computer techniques that have the potential to improve diagnostic performance. Computer algorithms, at their present state of development, show great promise for clinical use. It can be expected that such use will only improve as computer technology and computer methods continue to become more formidable. The eventual role of computers in mammographic detection and diagnosis has not been fully defined, but their effect on practice may one day be very significant.

A wavelet-based algorithm for detecting clustered microcalcifications in digital mammograms

A computerized scheme to detect clustered microcalcifications in digital mammograms has been developed. Detection of individual microcalcifications in regions of interest (ROIs) was also performed. The mammograms were previously classified into fatty and dense, according to their breast tissue. The most appropriate wavelet basis and reconstruction levels were selected. To select the wavelet basis, 40 profiles of microcalcifications were decomposed and reconstructed using different types of wavelet functions and different combinations of wavelet coefficients. The symlets with a basis of length 8 were chosen for fatty tissue. For dense tissue, the Daubechies' wavelets with a four-element basis were employed. Two methods to detect individual microcalcifications were evaluated: (a) two-dimensional wavelet transform, and (b) one-dimensional wavelet transform. The second technique yielded the best results, and was used to detect clustered microcalcifications in the complete mammogram. When detecting individual microcalcifications by using two-dimensional wavelet transform we have obtained, for fatty ROIs, a sensitivity of 71.11% at a false positive rate of 7.13 per image. For dense ROIs the sensitivity was 60.76% and the false positive rate, 7.33. The areas (A1) under the AFROC curves were 0.33+/-0.04 and 0.28+/-0.02, respectively. The one-dimensional wavelet transform method yielded 80.44% of sensitivity and 6.43 false positives per image (A1=0.39+/-0.03) for fatty ROIs, and 62.17% and 5.82 false positives per image (A1=0.37+/-0.02) for dense ROIs. For the detection of clusters of microcalcifications in the entire mammogram, the sensitivity was 80.00% with 0.94 false positives per image (A1=0.77+/-0.09) for fatty mammograms, and 72.85% of sensitivity at a false positive detection rate of 2.21 per image (A1=0.64+/-0.07) for dense mammograms. Globally, a sensitivity of 76.43% at a false positive detection rate of 1.57 per image was obtained.

Computer-aided diagnosis in mammography: classification of mass and normal tissue by texture analysis

Computer-aided diagnosis schemes are being developed to assist radiologists in mammographic interpretation. In this study, we investigated whether texture features could be used to distinguish between mass and non-mass regions in clinical mammograms. Forty-five regions of interest (ROIs) containing true masses with various degrees of visibility and 135 ROIs containing normal breast parenchyma were extracted manually from digitized mammograms as case samples. Spatial-grey-level-dependence (SGLD) matrices of each ROI were calculated and eight texture features were calculated from the SGLD matrices. The correlation and class-distance properties of extracted texture features were analysed. Selected texture features were input into a modified decision-tree classification scheme. The performance of the classifier was evaluated for different feature combinations and orders of features on the tree. A classification accuracy of about 89% sensitivity and 76% specificity was obtained for ordered features, sum average, correlation, and energy, during the training procedure. With a leave-one-out method, the test result was about 76% sensitivity and 64% specificity. The results of this preliminary study demonstrate the feasibility of using texture information for classification of mass and normal breast tissue, which will be likely to be useful for classifying true and false detections in computer-aided diagnosis programmes.

A novel approach to microcalcification detection using fuzzy logic technique

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.

Real and simulated clustered microcalcifications in digital mammograms. ROC study of observer performance

We have developed a model to simulate clustered microcalcifications on digital mammograms. Wavelet transform techniques were used to detect real clustered microcalcifications. A feature analysis process was applied to automatically extract the features describing the individual simulated microcalcifications and clusters from the values of the real clustered microcalcifications present in the mammogram. Subsequently, a database of simulated and real clustered microcalcifications was created. Clusters of microcalcifications from this database were tested for indistinguishability from real ones. Two radiologists and one physicist were asked to indicate whether the microcalcifications were either real or simulated. The responses of the readers were evaluated with a ROC analysis and the area under the curve was calculated. The average ROC area was 0.54 +/- 0.03, indicating there was no statistical difference between real and simulated clustered microcalcifications. The method allows for the creations of simulated clustered microcalcifications that are virtually indistinguishable from real microcalcifications in digital mammograms and could be used to evaluate different image processing techniques.

Segmentation and numerical analysis of microcalcifications on mammograms using mathematical morphology

The top-hat and watershed algorithms of mathematical morphology have been applied to detect automatically and segment microcalcifications on mammograms digitized to a pixel resolution of 40 microns using a CCD camera. The database comprised 38 cases from the breast assessment clinic in Liverpool. For all cases, both craniocaudal (CC) and lateral oblique (LO) views were available. 19 cases were proven to be benign and 19 malignant based on cytology and histology. Malignant clusters contained more microcalcifications (14 malignant, 10 benign), occupied a larger area (37 mm2, 9 mm2) and had longer cluster perimeters than benign clusters (33.2 mm, 15.5 mm). Malignant microcalcifications exhibited a wider variety of shapes and were more heterogeneous in terms of image signal intensity than benign microcalcifications. Further mathematical morphology algorithms were applied to describe microcalcification shape in terms of the presence or absence of infoldings, elongation, narrow irregularities and wide irregularities. The three largest microcalcifications were selected for each case and, using a "leave-one-out" approach, each microcalcification was classified in respect of its five nearest neighbours as either malignant or benign. The area under the curve of a receiver operating characteristic (ROC) analysis of the proportion of the three microcalcifications which agreed with the true diagnosis increased from 0.73 (CC) and 0.63 (LO) to 0.79 when both views were considered. Next, each cluster in turn was ranked according to its agreement with the database as a whole over 21 features. An ROC analysis was performed to investigate the effect on sensitivity and specificity of the proportion of the nine nearest neighbours that agreed with the true classification. The largest area under the ROC curve was 0.84 produced by the four features of proportion of irregular microcalcifications, proportion of round microcalcifications, number of microcalcifications in the cluster and the interquartile range of microcalcification area. The shape of microcalcifications is confirmed as being of overriding importance in classifying cases as either malignant or benign. This observation motivates a further study enhanced by using magnified views digitized to a higher resolution by a laser scanner. This will enable the reliable assessment of the shape of a greater number of microcalcifications in each cluster, which is likely to increase further the discriminating power of the image analysis routines and lead to the development of an expert system for automatic mammographic screening.

Adaptive computer-aided diagnosis scheme of digitized mammograms

RATIONALE AND OBJECTIVES

We investigated an adaptive rule-based computer-aided diagnosis (CAD) scheme for digitized mammograms that can be optimized by using an image difficulty index as determined from global measures of image characteristics.

METHODS

First, we defined an image "difficulty" index based on image feature measurements in both the spatial and frequency domains. The CAD scheme then segmented the database into three groups. An image database of 428 digitized mammograms with 220 verified masses was randomly divided into two subsets, one for training (rule-setting) and the other for testing the adaptive CAD scheme. Each of the image difficulty groups in the training set was optimized independently to achieve a low false-positive detection rate while maintaining high detection sensitivity. Scheme performance was then evaluated with the test set, and the results were compared with a global rule-based system that was optimized without the adaptive method.

RESULTS

In this preliminary study, a relatively simple adaptive scheme reduced false-positive mass detections compared with the nonadaptive scheme from 0.85 to 0.53 per image. At the same time sensitivity was not significantly changed.

CONCLUSION

This adaptive CAD scheme has distinct advantages in improving CAD scheme performance as long as the training database includes a large number of cases in each image difficulty group with a variety of true-positive abnormalities.

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.

Computer-aided detection of clustered microcalcifications in digitized mammograms

RATIONALE AND OBJECTIVES

We investigated a computer-aided detection (CAD) scheme for clustered microcalcifications in digitized mammograms.

METHODS

A multistage CAD scheme was developed and tested. To increase sensitivity, the scheme uses a Gaussian band-pass filter and nonlinear threshold. A multistage local minimum searching routine and a multilayer topographic feature analysis are used to reduce the false-positive detection rate. One hundred ten digitized mammograms were used in this preliminary test, with 55 images containing one or two verified microcalcification clusters.

RESULTS

The CAD scheme achieved 100% sensitivity and had an average false-positive detection rate of 0.18 per image.

CONCLUSION

The CAD scheme performs as well as many published schemes and has some unique advantages to further improve detection sensitivity and specificity of future CAD schemes.

Computer-aided detection of clustered microcalcifications on digital mammograms

A computer-aided diagnosis scheme to assist radiologists in detecting clustered microcalcifications from mammograms is being developed. Starting with a digital mammogram, the scheme consists of three steps. First, the image is filtered so that the signal-to-noise ratio of microcalcifications is increased by suppression of the normal background structure of the breast. Secondly, potential microcalcifications are extracted from the filtered image with a series of three different techniques: a global thresholding based on the grey-level histogram of the full filtered image, an erosion operator for eliminating very small signals, and a local adaptive grey-level thresholding. Thirdly, some false-positive signals are eliminated by means of a texture analysis technique, and a non-linear clustering algorithm is then used for grouping the remaining signals. With this method, the scheme can detect approximately 85% of true clusters, with an average of two false clusters detected per image.

Classification of microcalcifications in radiographs of pathologic specimens for the diagnosis of breast cancer

RATIONALE AND OBJECTIVES

Early detection of breast cancer depends on accurate classification of microcalcifications. We have developed a computer vision system that has the potential to classify microcalcifications objectively and consistently to aid radiologists in diagnosing breast cancer.

METHODS

A convolution neural network (CNN) was used to classify benign and malignant microcalcifications in radiographs of pathologic specimens. Digital images were acquired by digitizing radiographs at a high resolution of 21 microns x 21 microns.

RESULTS

Eighty regions of interest selected from digitized radiographs of pathologic specimens were used for training and testing of the neural network system. The CNN achieved an Az value (area under the receiver operating characteristic curve) of 0.90 in classifying clusters of microcalcifications associated with benign and malignant processes.

CONCLUSION

Classification of microcalcifications in pathologic specimens for diagnosis of breast cancer was achieved at a high level in our computer vision system, which consists of high-resolution digitization of mammograms and a CNN.

Application of shape analysis to mammographic calcifications

The authors have developed a set of shape factors to measure the roughness of contours of calcifications in mammograms and for use in their classification as malignant or benign. The analysis of mammograms is performed in three stages. First, a region growing technique is used to obtain the contours of calcifications. Then, three measures of shape features, including compactness, moments, and Fourier descriptors are computed for each region. Finally, their applicability for classification is studied by using the three shape measures to form feature vectors. Classification of 143 calcifications from 18 biopsy-proven cases as benign or malignant using the three measures with the nearest-neighbor method was 100% accurate.

Image segmentation in digital mammography: comparison of local thresholding and region growing algorithms

Local thresholding and region-growing algorithms are developed and applied to digitized mammograms to quantify the parenchymal densities. The algorithms are first evaluated and optimized on phantom images reflecting varying image contrast, X-ray exposure conditions, and time-related changes. The difference between the segmentation results of the two techniques is less than 6% on the phantom images and 11% on the mammograms. The agreement between the computerized procedures and a manual one is in the range of 74-98%, depending on the breast parenchymal pattern and segmentation algorithm. The results show that computerized parenchymal classification of digitized mammograms is possible and independent of exposure.

Mammographically indeterminate microcalcifications--can we do any better?

In the first round of the mammographic screening program of the South Australian Breast X-ray Service, 80 (0.73%) of the first 10,848 women screened over 18 months were referred after primary and second-stage assessment for definitive histology because of microcalcifications. Obvious mass lesions associated with calcification were excluded from this study, as were women whose calcification was regarded as sufficiently benign to warrant routine rescreening in two years. After classic patterns of malignant microcalcification were excluded, a large group (75%) remained, whose calcifications fell into the indeterminate grades of radiological suspicion. Of these, only 15% proved to have cancer, and in one third of these the cancer was mammographically occult. A high rate of discordant readings was noted in lesions which ultimately proved benign. Neither family history, distribution of calcification nor the presence of a faint soft tissue density proved to be unfailingly reliable predictors of benign or malignant histology in this group. Vigorous pursuit of histopathological correlation and performance statistics are urged to monitor and minimise the proportion of women who remain in this indeterminate group and to follow their natural history. Current mammographic techniques are still inadequate for the provision of definitive information on microcalcification in all cases, but a sustained commitment will reduce the number proceeding to histology for benign disease.

Early detection of breast cancer: mammography

Detection of early breast cancer utilizing mammography can be accomplished through more frequent and earlier use of the test as well as exploring techniques to improve sensitivity and specificity. Efforts at educating primary care physicians about the role of mammography as well as training technologists and radiologists in performing optimum examinations and correctly interpreting them is of prime importance. The use of computers may aid in increasing the sensitivity of the examinations and may also provide improved feature analysis for the radiologist, thus enhancing the separation of benign and malignant disease. New technologies also show promise to improve the accuracy of mammography. Direct digital mammography and digital enhancement of standard mammograms are actively being investigated. The use of MRI and specifically 31P spectroscopy shows initial promise to increase the specificity of mammography. Several clinical trials are also under way to assess a possible niche which fine needle aspiration biopsy (FNAB) may occupy in the quest for early breast cancer detection. Any future collaborative work between Japan and Western countries should take into account the potential of these new methods for improving the sensitivity and specificity of mammography.

Extraction of quantitative blur measures for circumscribed lesions in mammograms

This study investigates ways of improving lesion diagnosis in mammograms by deriving quantitative descriptions of the lesion periphery. The descriptions are derived by computer image analysis methods. The degree of blur at lesion boundaries is of prime concern, as poorly outlined lesions can indicate malignancy. The need for quantitative analysis arises from psychological evidence suggesting that the human visual system cannot precisely estimate the degree of blur. To help find suitable measures a set of 'artificial' lesions has been generated by convolving a step-like edge with a set of Gaussian functions G(sigma) where sigma characterizes the degree of blur. From these generated lesion images the parameters sigma are derived by the process involving deconvolution. As the edge changes are most important in radial directions, the measures of sigma are calculated for each radial profile of the lesion. The derived individual values correspond very closely to those used to generate the lesions. Statistical measures obtained from them allow distinction between edges which are blurred to different extents and yet are impossible to differentiate visually. The artificial lesions will be combined with mammographic data, and similar measures derived. The work will be validated on real lesions for which the histological findings are known from performed biopsies.

Automatic computer detection of clustered calcifications in digital mammograms

The automatic detection of clusters of calcifications in digital mammograms has been investigated using image analysis techniques. The calcifications were segmented from the background of normal breast structure in the mammogram using a local area thresholding process. This procedure also identified other breast structures and the digital image properties of all segmented objects were analysed to extract clusters of calcifications. Seventy five clinical mammograms were digitised. These were divided into training and test sets of 25 and 50 films respectively. The results for the test set of 50 complete clinical mammograms show that the computer system achieves a 25/25 true positive film classification (i.e. those containing clusters of calcifications) with false positive clusters detected in 4/50 films. There were no false negative film classifications.