Microcalcification clusters are often an important indicator for the detection of malignancy in mammograms. In many cases, microcalcifications are the only indication of a malignancy. However, the detection of microcalcifications can be a difficult process. They are small and can be embedded in dense tissue. This paper presents a method for automatically detecting microcalcifications. We utilize a high-boost filter to suppress background clutter enabling segmentation even in very dense breast tissue. We then use a threshholding and region growing technique to extract candidate microcalcifications. Likely microcalcifications are then identified by a linear classifier. We apply this method to images selected from the LLNL/UCSF Digital Mammogram Library, and produce a receiver operating characteristic (ROC) curves to detail the trade-off between probability of detection and false alarms. Finally, we exam the ability to properly select a threshold to achieve a desired probability of detection based upon a training set.
digital mammography; microcalcifications; high-boost filtering; detection
Screening mammography can locate small breast cancer lesions not detectable on physical examination. In this study, the records of 57 patients undergoing radiographically guided preoperative needle localization were reviewed for the period August 1986 to May 1988. Of the 57 cases, 15.8% were positive for cancer and 84.2% were benign breast lesions. Invasive ductal carcinoma was the pathologic diagnosis in all malignant biopsies, except for one case of carcinoma in situ. All positive lesions had shown as microcalcifications on mammogram. The authors examine the criteria for biopsy and discuss their experience with needle localization of occult breast lesion suspicious of breast cancer.
The purpose of this study was to determine whether the interpretation of microcalcifications assessed on images zoomed (× 2.0) from digital mammograms is at least equivalent to that from digital magnification mammography (× 1.8) with respect to diagnostic accuracy and image quality. Three radiologists with different levels of experience in mammography reviewed each full-field digital mammography reader set for 185 patients with pathologically proven microcalcification clusters, which consisted of digital magnification mammograms (MAGs) with a magnification factor of 1.8 and images zoomed from mammograms (ZOOM) with a zoom factor of 2.0. Each radiologist rated their suspicion of breast cancer in microcalcific lesions using a six-point scale and the image quality and their confidence in the decisions using a five-point scale. Results were analysed according to display methods using areas under the receiver operating characteristic curves (Az value) for ZOOM and MAGs to interpret microcalcifications, and the Wilcoxon matched pairs signed rank test for image quality and confidence levels. There was no statistically significant difference in the level of suspicion of breast cancer between the ZOOM and MAG groups (Az = 0.8680 for ZOOM; Az = 0.8682 for MAG; p = 0.9897). However, MAG images were significantly better than ZOOM images in terms of visual imaging quality (p < 0.001), and the confidence level with MAG was better than with ZOOM (p < 0.001). In conclusion, the performance of radiologists in the diagnosis of microcalcifications using ZOOM was similar to that using MAGs, although image quality and confidence levels were better using MAGs.
Mammographic microcalcifications are associated with many benign lesions, ductal carcinoma in situ (DCIS) and invasive cancer. Careful assessment criteria are required to minimise benign biopsies while optimising cancer diagnosis. We wished to evaluate the assessment outcomes of microcalcifications biopsied in the setting of population-based breast cancer screening.
Between January 1992 and December 2007, cases biopsied in which microcalcifications were the only imaging abnormality were included. Patient demographics, imaging features and final histology were subjected to statistical analysis to determine independent predictors of malignancy.
In all, 2545 lesions, with a mean diameter of 21.8 mm (s.d. 23.8 mm) and observed in patients with a mean age of 57.7 years (s.d. 8.4 years), were included. Using the grading system adopted by the RANZCR, the grade was 3 in 47.7% 4 in 28.3% and 5 in 24.0%. After assessment, 1220 lesions (47.9%) were malignant (809 DCIS only, 411 DCIS with invasive cancer) and 1325 (52.1%) were non-malignant, including 122 (4.8%) premalignant lesions (lobular carcinoma in situ, atypical lobular hyperplasia and atypical ductal hyperplasia). Only 30.9% of the DCIS was of low grade.
Mammographic extent of microcalcifications >15 mm, imaging grade, their pattern of distribution, presence of a palpable mass and detection after the first screening episode showed significant univariate associations with malignancy. On multivariate modeling imaging grade, mammographic extent of microcalcifications >15 mm, palpable mass and screening episode were retained as independent predictors of malignancy. Radiological grade had the largest effect with lesions of grade 4 and 5 being 2.2 and 3.3 times more likely to be malignant, respectively, than grade 3 lesions.
The radiological grading scheme used throughout Australia and parts of Europe is validated as a useful system of stratifying microcalcifications into groups with significantly different risks of malignancy. Biopsy assessment of appropriately selected microcalcifications is an effective method of detecting invasive breast cancer and DCIS, particularly of non-low-grade subtypes.
breast cancer; screening; mammography; microcalcifications
Breast microcalcifications are key diagnostically significant radiological features for localisation of malignancy. This study explores the hypothesis that breast calcification composition is directly related to the local tissue pathological state.
A total of 236 human breast calcifications from 110 patients were analysed by mid-Fouries transform infrared (FTIR) spectroscopy from three different pathology types (112 invasive carcinoma (IC), 64 in-situ carcinomas and 60 benign). The biochemical composition and the incorporation of carbonate into the hydroxyapatite lattice of the microcalcifications were studied by infrared microspectroscopy. This allowed the spectrally identified composition to be directly correlated with the histopathology grading of the surrounding tissue.
The carbonate content of breast microcalcifications was shown to significantly decrease when progressing from benign to malignant disease. In this study, we report significant correlations (P<0.001) between microcalcification chemical composition (carbonate content and protein matrix : mineral ratios) and distinct pathology grades (benign, in-situ carcinoma and ICs). Furthermore, a significant correlation (P<0.001) was observed between carbonate concentrations and carcinoma in-situ sub-grades. Using the two measures of pathology-specific calcification composition (carbonate content and protein matrix : mineral ratios) as the inputs to a two-metric discriminant model sensitivities of 79, 84 and 90% and specificities of 98, 82 and 96% were achieved for benign, ductal carcinoma in situ and invasive malignancies, respectively.
We present the first demonstration of a direct link between the chemical nature of microcalcifications and the grade of the pathological breast disease. This suggests that microcalcifications have a significant association with cancer progression, and could be used for future objective analytical classification of breast pathology. A simple two-metric model has been demonstrated, more complex spectral analysis may yeild greater discrimination performance. Furthermore there appears to be a sequential progression of calcification composition.
breast cancer; calcifications; carbonate; DCIS; diagnose; FTIR; grade
Detection of clustered microcalcifications (MCs) in mammograms represents a significant step towards successful detection of breast cancer since their existence is one of the early signs of cancer. In this paper, a new framework that integrates Bayesian classifier and a pattern synthesizing scheme for detecting microcalcification clusters is proposed. This proposed work extracts textural, spectral, and statistical features of each input mammogram and generates models of real MCs to be used as training samples through a simplified learning phase of the Bayesian classifier. Followed by an estimation of the classifier's decision function parameters, a mammogram is segmented into the identified targets (MCs) against background (healthy tissue). The proposed algorithm has been tested using 23 mammograms from the mini-MIAS database. Experimental results achieved MCs detection with average true positive (sensitivity) and false positive (specificity) of 91.3% and 98.6%, respectively. Results also indicate that the modeling of the real MCs plays a significant role in the performance of the classifier and thus should be given further investigation.
In this work we propose a spatial point process (SPP) approach to improve the detection accuracy of clustered microcalcifications (MCs) in mammogram images. The conventional approach to MC detection has been to first detect the individual MCs in an image independently, which are subsequently grouped into clusters. Our proposed approach aims to exploit the spatial distribution among the different MCs in a mammogram image (i.e., MCs tend to appear in small clusters) directly during the detection process. We model the MCs by a marked point process (MPP) in which spatially neighboring MCs interact with each other. The MCs are then simultaneously detected through maximum a posteriori (MAP) estimation of the model parameters associated with the MPP process. The proposed approach was evaluated with a dataset of 141 clinical mammograms from 66 cases, and the results show that it could yield improved detection performance compared to a recently proposed SVM detector. In particular, the proposed approach achieved a sensitivity of about 90% with the FP rate at around 0.5 clusters per image, compared to about 83% for the SVM; the performance of the proposed approach was also demonstrated to be more stable over different composition of the test images.
Clustered microcalcifications; computer-aided detection; spatial point process; marked point process
Microcalcifications are an important diagnostic marker for breast cancer on mammograms, yet the mechanism of their formation is poorly understood. Indeed, there is presently no short-latency, high-yield, syngeneic rodent model of the process. Bone morphogenetic protein-2 (BMP-2) is a key mediator of physiological bone formation and pathological vasculature calcification, but its role in breast cancer microcalcification is unknown. In this study, R3230 rat breast tumors were adapted to cell culture, transduced with adenoviral BMP-2, and inoculated into a syngeneic host. Tumor growth and calcium salt deposition were quantified in living animals over time using micro-computed tomography, and probed chemically using near-infrared fluorescence. Plasma BMP-2 levels were quantified over time by ELISA. Within three weeks, 100% of breast tumors developed microcalcifications, which were absent from all normal tissues. Importantly, when two tumors were initiated in a single host, the ipsilateral tumor expressing BMP-2 was able to induce microcalcification in the contralateral tumor that was not expressing BMP-2, suggesting that BMP-2 can act humorally. Taken together, we describe the first reproducible rodent model of breast cancer microcalcification, prove that BMP-2 expression is sufficient for initiating the process, and lay the foundation for a new generation of targeted diagnostic agents.
Bone Morphogenetic Protein-2; Breast Cancer; Microcalcification; Mammography; Animal Models
The detection of clustered microcalcifications can help the radiologist to detect early breast cancer. Microcalcifications exhibit some important characteristics, such as small size and high luminosity. Use of a computeraided diagnosis (CAD) method can prevent them being overlooked. In this report, a multiresolution analysis is performed based on a multilevel wavelet transformation. Decomposition produces sub-band images which become visible only as details of the different scales. Thereafter, all the images will be combined in a final image, in order to obtain an image that contains all the interest details at the scale where microcalcifications tend to appear. Once the image, called detail image, is obtained, it is necessary to determine which details correspond with microcalcifications. Statistical analysis of the histogram permits classification of the zones likely to contain microcalcifications. Applying this statistical techniques over the whole image and representing the results in a twodimensional map, clustered microcalcification regions are clearly distinguishable.
To evaluate the diagnostic accuracy of the use of an ultrasonography (US)-guided vacuum-assisted biopsy for microcalcifications of breast lesions and to evaluate the efficacy of the use of US-guided vacuum-assisted biopsy with long-term follow-up results.
Materials and Methods
US-guided vacuum-assisted biopsy cases of breast lesions that were performed between 2002 and 2006 for microcalcifications were retrospectively reviewed. A total of 62 breast lesions were identified where further pathological confirmation was obtained or where at least two years of mammography follow-up was obtained. These lesions were divided into the benign and malignant lesions (benign and malignant group) and were divided into underestimated group and not-underestimated lesions (underestimated and not-underestimated group) according to the diagnosis after a vacuum-assisted biopsy. The total number of specimens that contained microcalcifications was analyzed and the total number of microcalcification flecks as depicted on specimen mammography was analyzed to determine if there was any statistical difference between the groups.
There were no false negative cases after more than two years of follow-up. Twenty-nine lesions were diagnosed as malignant (two invasive carcinomas and 27 carcinoma in situ lesions). Two of the 27 carcinoma in situ lesions were upgraded to invasive cancers after surgery. Among three patients diagnosed with atypical ductal hyperplasia, the diagnosis was upgraded to a ductal carcinoma in situ after surgery in one patient. There was no statistically significant difference in the number of specimens with microcalcifications and the total number of microcalcification flecks between the benign group and malignant group of patients and between the underestimated group and not-underestimated group of patients.
US-guided vacuum-assisted biopsy can be an effective alternative to stereotactic-guided vacuum-assisted biopsy in cases where microcalcifications are visible with the use of high-resolution US.
Breast, US; Breast, Biopsy; Breast, Calcification
In this paper, a novel fast method for modeling mammograms by deterministic fractal coding approach to detect the presence of microcalcifications, which are early signs of breast cancer, is presented. The modeled mammogram obtained using fractal encoding method is visually similar to the original image containing microcalcifications, and therefore, when it is taken out from the original mammogram, the presence of microcalcifications can be enhanced. The limitation of fractal image modeling is the tremendous time required for encoding. In the present work, instead of searching for a matching domain in the entire domain pool of the image, three methods based on mean and variance, dynamic range of the image blocks, and mass center features are used. This reduced the encoding time by a factor of 3, 89, and 13, respectively, in the three methods with respect to the conventional fractal image coding method with quad tree partitioning. The mammograms obtained from The Mammographic Image Analysis Society database (ground truth available) gave a total detection score of 87.6%, 87.6%, 90.5%, and 87.6%, for the conventional and the proposed three methods, respectively.
Breast cancer; mammograms; deterministic fractals; fractal image modeling; microcalcifications
Stereotactic vacuum-assisted breast biopsy (VAB) has been used to evaluate microcalcifications or non-palpable breast lesions on mammography. Although stereotactic VAB is usually performed in a prone or upright position, an expensive prone table is necessary and vasovagal reactions often occur during the procedure. For these reasons, the lateral decubitus position can be applied for stereotactic VAB, and true lateral mammography can be used to detect the lesion. We report on 15 cases of lateral decubitus positioning for stereotactic VAB with true lateral mammography for non-palpable breast lesions or microcalcifications. The mean procedure time was approximately 30.1 minutes, and no complications occurred during the procedures. Fourteen cases had benign breast lesions and one case had a ductal carcinoma in situ. The lateral decubitus stereotactic VAB with true lateral mammography can be applied for microcalcifications or non-palpable breast lesions and helps to minimize anxiety and vasovagal reactions in patients.
Stereotactic techniques; Breast biopsy; Lateral positioning; Mammography
Pathologic complete response (pCR) after NC has been consistently associated with improved outcomes. Residual DCIS after NC does not portray worse prognosis compared to complete eradication of all disease but has clinical implications regarding surgical management. We report a case of pCR of DCIS associated with invasive carcinoma in an HER-2 + tumor after NC plus trastuzumab despite persistence of malignant-appearing microcalcifications mammographically. A 41-year-old Caucasian female presented with a 4 × 4 cm mass in the right breast and a 2.5 cm right axillary node. Mammogram showed a 2.5 cm mass and a 12 cm area of linear pleomorphic, suspicious calcifications in the upper part of the breast. Core biopsy revealed invasive ductal carcinoma and DCIS associated with calcifications (ER 85%, PR 6%, Her2neu 3+ by IHC). Axillary node FNA was positive for malignancy. The patient received doxorubicin/cyclophosphamide (AC) → paclitaxel plus T with complete clinical and radiologic response but no significant change in the microcalcifications. Final pathology showed no residual invasive carcinoma or DCIS despite the presence of numerous ducts with microcalcifications. Documented eradication of DCIS has not been reported following NC when malignant-appearing calcifications persist and this observation may have important clinical implications regarding surgical management.
A patient presented with a 2 cm lump in the lower outer quadrant of the left breast. Mammogram and ultrasonography showed a solid mass with a microlobulated contour, partially irregular border and microcalcifications. MRI showed an irregular mass with early enhancement and high signal intensity, and the late-phase image demonstrated a partial washout pattern. These findings suggest that the tumour was a malignant invasive carcinoma. Non-invasive ductal carcinoma was diagnosed after a fine needle aspiration and core needle biopsy followed by a partial breast excision and sentinel lymph node (SLN) biopsy. A pathological examination of the lesion displayed characteristic small monomorphic cells, solid proliferation and massive distension within the lobular unit. The tumour was immunohistochemically negative for E-cadherin and pure lobular carcinoma in situ (LCIS) was diagnosed. Pure LCIS is very rare and there have been no previous reports of pure LCIS forming a solid mass.
We are developing new techniques to improve the accuracy of computerized microcalcification detection by using the joint two-view information on craniocaudal (CC) and mediolateral-oblique (MLO) views. After cluster candidates were detected using a single-view detection technique, candidates on CC and MLO views were paired using their radial distances from the nipple. Candidate pairs were classified with a similarity classifier that used the joint information from both views. Each cluster candidate was also characterized by its single-view features. The outputs of the similarity classifier and the single-view classifier were fused and the cluster candidate was classified as a true microcalcification cluster or a false-positive (FP) using the fused two-view information. A data set of 116 pairs of mammograms containing microcalcification clusters and 203 pairs of normal images from the University of South Florida (USF) public database was used for training the two-view detection algorithm. The trained method was tested on an independent test set of 167 pairs of mammograms, which contained 71 normal pairs and 96 pairs with microcalcification clusters collected at the University of Michigan (UM). The similarity classifier had a very low FP rate for the test set at low and medium levels of sensitivity. However, the highest mammogram-based sensitivity that could be reached by the similarity classifier was 69%. The single-view classifier had a higher FP rate compared to the similarity classifier, but it could reach a maximum mammogram-based sensitivity of 93%. The fusion method combined the scores of these two classifiers so that the number of FPs was substantially reduced at relatively low and medium sensitivities, and a relatively high maximum sensitivity was maintained. For the malignant microcalcification clusters, at a mammogram-based sensitivity of 80%, the FP rates were 0.18 and 0.35 with the two-view fusion and single-view detection methods, respectively. When the training and test sets were switched, a similar improvement was obtained, except that both the fusion and single-view detection methods had superior test performances on the USF data set than those on the UM data set. Our results indicate that correspondence of cluster candidates on two different views provides valuable additional information for distinguishing FPs from true microcalcification clusters.
computer-aided diagnosis; microcalcification clusters; segmentation
Breast cancer is usually associated with metastases to lungs, bones and liver. Breast carcinoma metastasizing to the gallbladder is very rare.
A 59-year-old woman presented with bilateral synchronous breast lesions. A palpable, retroareolar solid lesion of diameter equal to 5 cm was present in the right breast, and a newly developed, non-palpable lesion with microcalcifications (diameter equal to 0.7 cm) was present in the upper outer quadrant of the left breast. Modified radical mastectomy was performed on the right breast and lumpectomy after hook-wire localization was performed on the left breast, combined with lymph node dissection in both sides. The pathological examination revealed invasive lobular carcinoma grade II in the right breast and invasive ductal carcinoma grade I in the left breast. Chemotherapy, radiation therapy, trastuzumab and letrozole were appropriately administered. At her 18-month follow-up, the patient was free of symptoms; the imaging tests (chest CT, abdominal U/S, bone scan), biochemical tests, blood cell count and tumor markers were also normal. At the 20th month after surgery however, the patient developed symptoms of cholecystitis and underwent cholecystectomy. The histopathological examination revealed metastasis of the lobular carcinoma to the gallbladder.
This extremely rare case confirms on a single patient the results of large series having demonstrated the preferential metastasis of lobular breast cancer to the gallbladder. Symptoms of cholecystitis should not be neglected in such patients, as they might indicate metastasis to the gallbladder.
In this paper we propose a microcalcification classification scheme, assisted by content-based mammogram retrieval, for breast cancer diagnosis. We recently developed a machine learning approach for mammogram retrieval where the similarity measure between two lesion mammograms was modeled after expert observers. In this work we investigate how to use retrieved similar cases as references to improve the performance of a numerical classifier. Our rationale is that by adaptively incorporating local proximity information into a classifier, it can help to improve its classification accuracy, thereby leading to an improved “second opinion” to radiologists. Our experimental results on a mammogram database demonstrate that the proposed retrieval-driven approach with an adaptive support vector machine (SVM) could improve the classification performance from 0.78 to 0.82 in terms of the area under the ROC curve.
microcalcification classification; adaptive support vector machine; image retrieval
Introduction. Does high-resolution visualization of microcalcifications improve diagnostic reliability? Method. X-rays were taken of mamma specimens with microcalcifications in 32 patients (10 malignant; 22 benign) using conventional radiography (12 Lp/mm) and high-resolution radiography (2000 Lp/mm). Histological sections were subsequently prepared and correlated to the microradiographic image and every calcification was assigned an exact malignant or benign histological diagnosis. Five radiologists classified single groups of calcifications in both methods according to the BIRADS classification system. Results. Using microradiography microcalcifications can be shown in high resolution at the cell level including histological correlation. In some cases, the diagnostic validity was improved by the high resolution in microradiography. In other cases, the high resolution resulted in more visible calcifications, thus giving benign calcifications a malignant appearance. In the BIRADS 2 and 3 group, the probability of malignancy was 28.6% in the conventional radiography evaluation and 37.8% in the microradiography evaluation. In the BIRADS 4 and 5 group, the probability of malignancy was 34.2% in the conventional radiography evaluation and 24.4% in the microradiography evaluation. The differences were not significant. Summary. Overall, the improved resolution in microradiography did not show an improvement in diagnostic accuracy compared to conventional radiography.
Mammographic density is a strong, independent risk factor for breast cancer. A critical unanswered question is whether cancers tend to arise in mammographically dense tissue (i.e. are densities directly related to risk or are they simply a marker of risk). This question cannot be addressed by studying invasive tumors because they manifest as densities and cannot be confidently differentiated from the densities representing fibrous and glandular tissue. We addressed this question by studying ductal carcinoma in situ (DCIS), as revealed by microcalcifications.
We studied the cranio-caudal and the mediolateral-oblique mammograms of 28 breasts with a solitary DCIS lesion. Two experienced radiologists independently judged whether the DCIS occurred in a mammographically dense area, and determined the density of different areas of the mammograms.
It was not possible to determine whether the DCIS was or was not in a dense area for six of the tumors. Of the remaining 22 lesions, 21 occurred in dense tissue (test for difference from expected taken as the percentage of density of the 'mammographic quadrant' containing DCIS; P < 0.0001). A preponderance of DCIS (17 out of 28) occurred in the mammographic quadrant with the highest percentage density.
DCIS occurs overwhelmingly in the mammographically dense areas of the breast, and pre-DCIS mammograms showed that this relationship was not brought about by the presence of the DCIS. This strongly suggests that some aspect of stromal tissue comprising the mammographically dense tissue directly influences the carcinogenic process in the local breast glandular tissue.
We have developed a computer-aided detection (CAD) system to detect clustered microcalcification automatically on full-field digital mammograms (FFDMs) and a CAD system for screen-film mammograms (SFMs). The two systems used the same computer vision algorithms but their false positive (FP) classifiers were trained separately with sample images of each modality. In this study, we compared the performance of the CAD systems for detection of clustered microcalcifications on pairs of FFDM and SFM obtained from the same patient. For case-based performance evaluation, the FFDM CAD system achieved detection sensitivities of 70%, 80%, and 90% at an average FP cluster rate of 0.07, 0.16, and 0.63 per image, compared with an average FP cluster rate of 0.15, 0.38, and 2.02 per image for the SFM CAD system. The difference was statistically significant with the alternative free-response receiver operating characteristic (AFROC) analysis. When evaluated on data sets negative for microcalcification clusters, the average FP cluster rates of the FFDM CAD system were 0.04, 0.11, and 0.33 per image at detection sensitivity level of 70%, 80%, and 90%, compared with an average FP cluster rate of 0.08, 0.14, and 0.50 per image for the SFM CAD system. When evaluated for malignant cases only, the difference of the performance of the two CAD systems was not statistically significant with AFROC analysis.
High-grade ductal carcinoma in situ is incredibly rare in male patients. The prognosis for ductal carcinoma in situ (DCIS) in a male patient is the same as it would be for a female with the same stage disease; therefore, early recognition and diagnosis are of the utmost importance. We present a case of a male with unilateral invasive ductal carcinoma who was diagnosed with DCIS in the contralateral breast. The DCIS presented as microcalcifications on mammography and was found to be biopsy proven grade 3 papillary DCIS. This case also illustrates the importance of family history and risk factors, all of which need to be evaluated in any male presenting with a breast mass or nipple discharge.
It is helpful in planning treatment for patients with ductal carcinoma in situ (DCIS) if the size and grade could be reliably predicted from the mammography. The aims of this study were to determine if the type of calcification can be best used to predict histopathological grade from the mammograms, to examine the association of mammographic appearance of DCIS with grade and to assess the correlation between mammographic size and pathological size.
Mammographic films and pathological slides of 115 patients treated for DCIS between 1986 and 2000 were reviewed and reclassified by a single radiologist and a single pathologist respectively. Prediction models for the European Pathologist Working Group (EPWG) and Van Nuys classifications were generated by ordinal regression. The association between mammographic appearance and grade was tested with the χ2-test. Relation of mammographic size with pathological size was established using linear regression. The relation was expressed by the correlation coefficient (r).
The EPWG classification was correctly predicted in 68%, and the Van Nuys classification in 70% if DCIS was presented as microcalcifications. High grade was associated with presence of linear calcifications (p < 0.001). Association between mammograhic- and pathological size was better for DCIS presented as microcalcifications (r = 0.89, p < 0.001) than for DCIS presented as a density (r = 0.77, p < 0.001).
Prediction of histopathological grade of DCIS presenting as microcalcifications is comparable using the Van Nuys and EPWG classification. There is no strict association of mammographic appearance with histopathological grade. There is a better linear relation between mammographic- and pathological size of DCIS presented as microcalcifications than as a density, although both relations are statistically significant.
ductal carcinoma in situ; imaging; size; prediction; pathological classification; breast
This paper presents a method to provide contrast enhancement in dense breast digitized images, which are difficult cases in testing of computer-aided diagnosis (CAD) schemes. Three techniques were developed, and data from each method were combined to provide a better result in relation to detection of clustered microcalcifications. Results obtained during the tests indicated that, by combining all the developed techniques, it is possible to improve the performance of a processing scheme designed to detect microcalcification clusters. It also allows operators to distinguish some of these structures in low-contrast images, which were not detected via conventional processing before the contrast enhancement. This investigation shows the possibility of improving CAD schemes for better detection of microcalcifications in dense breast images.
Image processing; contrast enhancement; dense breasts; microcalcifications; mammography
Breast metastasis from gastric carcinoma is rare. We present a case of right breast mass with microcalcification in which the diagnosis of poorly differentiated adenocarcinoma from the stomach was made after a biopsy. Pleomorphic microcalcification was noted in the ill-defined breast mass, which is a rare feature in breast metastasis. Since breast metastasis usually signifies advanced metastatic disease, differentiating primary breast cancer from metastasis is important for appropriate treatment.
Breast neoplasms; Metastasis; Microcalcification; Stomach neoplasms
Wavelet transform (WT) is a potential tool for the detection of microcalcifications, an early sign of breast cancer. This article describes the implementation and evaluates the performance of two novel WT-based schemes for the automatic detection of clustered microcalcifications in digitized mammograms. Employing a one-dimensional WT technique that utilizes the pseudo-periodicity property of image sequences, the proposed algorithms achieve high detection efficiency and low processing memory requirements. The detection is achieved from the parent–child relationship between the zero-crossings [Marr-Hildreth (M-H) detector] /local extrema (Canny detector) of the WT coefficients at different levels of decomposition. The detected pixels are weighted before the inverse transform is computed, and they are segmented by simple global gray level thresholding. Both detectors produce 95% detection sensitivity, even though there are more false positives for the M-H detector. The M-H detector preserves the shape information and provides better detection sensitivity for mammograms containing widely distributed calcifications.
DWT; microcalcification detection; edge detection; multiplexed wavelet transform; computer-aided methods for breast cancer detection.