Diagnosis Of Microcalcifications Research Articles

SqueezeU-Net-based detection and diagnosis of microcalcification in mammograms

SqueezeU-Net-based detection and diagnosis of microcalcification in mammograms

Deep Learning Features for Discriminating Between Benign and Malignant Microcalcification Lesions

Accurate diagnosis of microcalcification (MC) lesions in mammograms as benign or malignant is a challenging clinical task. In this study we investigate the potential discriminative power of deep learning features in MC lesion diagnosis. We consider two types of deep learning networks, of which one is a convolutional neural network developed for MC detection and the other is a denoising autoencoder network. In the experiments, we evaluated both the separability between malignant and benign lesions and the classification performance of image features from these two networks using Fisher's linear discriminant analysis on a set of mammographic images. The results demonstrate that the deep learning features from the MC detection network are most discriminative for classification of MC lesions when compared to both features from the autoencoder network and traditional handcrafted texture features.

Diagnosis of microcalcifications as a factor initiating the development of breast cancer

Diagnosis of microcalcifications as a factor initiating the development of breast cancer

Multiple Angulated Mammography Reconstructions in Digital Breast Tomosynthesis for the Diagnosis of Microcalcifications - Added Value to Standard Stack Reconstructions and Synthesized Mammography.

To compare ratings regarding the depiction, diagnostic accuracy and lesion characterization of conventional synthesized mammography (SM), multiple angulated mammography reconstructions (INSIGHT3D), and standard stack reconstructions in digital breast tomosynthesis for microcalcifications. This is a retrospective, multicase, multireader study. We included patients with digital breast tomosynthesis (DBT), microcalcifications and histology over a period of four months in our institution and the same number of normal cases. Three radiologists, who were blinded to patient data, independently rated the depiction, distribution, morphology and BI-RADS score of microcalcifications in SM, INSIGHT3D and standard stack reconstructions. Deidentified images were presented in random order. Reading time was measured. Friedman and post hoc Nemenyi tests, Cochrane's Q and post hoc Wilcoxon signed rank tests, Fleiss' kappa and receiver operating characteristics were used for statistical analysis. We included 41 histopathologically proven and 41normal cases. Depiction of microcalcifications was rated better in INSIGHT3D than in SM and better in stack reconstructions than in INSIGHT3D and SM (P < 0.001). The reading time was lower in SM and INSIGHT3D compared to stack reconstructions (P < 0.001). The diagnostic accuracy and inter-rater correlation were comparable between all tested modes of reconstruction. INSIGHT3D has higher ratings regarding the depiction of microcalcifications compared to SM while maintaining a short reading time. Our preliminary assessment suggests that INSIGHT3D provides added value to SM. · INSIGHT3D depicts microcalcifications better than synthesized mammography while maintaining a low reading time.. · The diagnostic accuracy and inter-rater correlation were comparable between INSIGHT3D and synthesized mammography.. · INSIGHT3D may be a potential successor to synthesized mammography.. · Neubauer J, Neubauer C, Wicklein J et al. Multiple Angulated Mammography Reconstructions in Digital Breast Tomosynthesis for the Diagnosis of Microcalcifications - Added Value to Standard Stack Reconstructions and Synthesized Mammography. Fortschr Röntgenstr 2018; DOI: 10.1055/s-0044-100726.

Computer-aided mammography techniques for detection and classification of microcalcifications in digital mammograms

Recent techniques that are developed in computer-aided mammography (CAM) produce more accurate results in detection and diagnosis of microcalcifications in its earlier state that can lead to breast cancers among women. These techniques aim at the reduction of false positive rates through which the number of biopsies and surgeries can be greatly reduced. This paper gives a detailed study of the existing techniques available in CAM for the segmentation and classification of the microcalcifications present in the di0067ital mammograms which help the radiologists to take quick and accurate diagnosis decisions.

A New Image Mining Approach for Detecting Micro-Calcification in Digital Mammograms

ABSTRACTAlthough mammography is typically the best method to detect breast cancer, it does not recognize 3–20% of the cancer cases. Mammography has established itself as the most efficient technique for detecting tiny cancerous tumor and micro-calcifications are the most difficult to detect since they are very small (0.1–1.0 mm) and they are almost contrasted against the images background. The main purpose of this paper is to provide a new method for the automatic diagnosis of micro-calcification in digital mammograms. It is based on image mining, and the results show 97.35% accuracy, which is improved than the previous works. Tests are based on the standard images data corpus, MIAS. The practical result of this research is registered as an invention in the Patents and Industrial Property Registration Organization numbered as 83119.

Quantitative comparison of clustered microcalcifications in for-presentation and for-processing mammograms in full-field digital mammography.

Mammograms acquired with full-field digital mammography (FFDM) systems are provided in both "for-processing'' and "for-presentation'' image formats. For-presentation images are traditionally intended for visual assessment by the radiologists. In this study, we investigate the feasibility of using for-presentation images in computerized analysis and diagnosis of microcalcification (MC) lesions. We make use of a set of 188 matched mammogram image pairs of MC lesions from 95 cases (biopsy proven), in which both for-presentation and for-processing images are provided for each lesion. We then analyze and characterize the MC lesions from for-presentation images and compare them with their counterparts in for-processing images. Specifically, we consider three important aspects in computer-aided diagnosis (CAD) of MC lesions. First, we quantify each MC lesion with a set of 10 image features of clustered MCs and 12 textural features of the lesion area. Second, we assess the detectability of individual MCs in each lesion from the for-presentation images by a commonly used difference-of-Gaussians (DoG) detector. Finally, we study the diagnostic accuracy in discriminating between benign and malignant MC lesions from the for-presentation images by a pretrained support vector machine (SVM) classifier. To accommodate the underlying background suppression and image enhancement in for-presentation images, a normalization procedure is applied. The quantitative image features of MC lesions from for-presentation images are highly consistent with that from for-processing images. The values of Pearson's correlation coefficient between features from the two formats range from 0.824 to 0.961 for the 10 MC image features, and from 0.871 to 0.963 for the 12 textural features. In detection of individual MCs, the FROC curve from for-presentation is similar to that from for-processing. In particular, at sensitivity level of 80%, the average number of false-positives (FPs) per image region is 9.55 for both for-presentation and for-processing images. Finally, for classifying MC lesions as malignant or benign, the area under the ROC curve is 0.769 in for-presentation, compared to 0.761 in for-processing (P = 0.436). The quantitative results demonstrate that MC lesions in for-presentation images are highly consistent with that in for-processing images in terms of image features, detectability of individual MCs, and classification accuracy between malignant and benign lesions. These results indicate that for-presentation images can be compatible with for-processing images for use in CAD algorithms for MC lesions.

The Sonogaphy is a Valuable Tool for Diagnosis of Microcalcification in Screening Mammography

The purpose of our study was to investigate whether sonography an adjunctive imaging for determining benign or malignancy lesions in breast microcalcification after screening mammography. According to BI-RADS assessment categories systems, category 4 or 5 needed further tissue proof. This retrospective study enrolled patients in St. Paul hospital who underwent tissue proof between May 1, 2011 to March 31, 2017. All patients with microcalcification in screening mammography were divided into two subgroups: the group of BI-RADS 0 initially then turn into BI-RADS 4 or 5 after magnified mammography (group A) and the other group of BI-RADS 4 or 5 (group B). We excluded patients with incomplete data including no tissue proof or no sonography report in our hospital. We evaluate the correlation between the pathologic results and the sonographic findings. A total of 133 patients were reviewed, 105 (78.9%) patients were group A. Among 105 specimens in the group A, 23 (21.9%) were proved malignancy. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of sonography were 52%, 84.1%, 48%, 86.3%, and 77.1%, respectively. Sixteen (57.1%) out of 28 patients in the group B were malignant. The findings of sonogrpahy showed high sensitivity, specificity, PPV, NPV, and accuracy for malignancy (87.5%, 75%, 82.4%, 81.8%, and 82.1%, respectively). Sonography could provide good specificity in undetermined microcalfication. A biopsy may be avoided if microcalcifications in mammography appear absolutely benign on sonography and those patients can be followed-up with interval serial exam.

유방 미세석회화 조직검사에서 X선 유도 하 조직검사와 초음파 유도 하 조직검사의 유용성

ABSTRACT Social interest in breast cancer has increased. The most basic exams for diagnosis include breast X-ray and breast ultrasound. In particular, breast microcalcification requires histological diagnosis, and breast microcalcification biopsy is commonly performed. Therefore, this study aimed to analyze and assess X-ray guided biopsy (needle localized open biopsy) and ultrasound guided biopsy (sono guided core needle biopsy), which are basics in diagnosis of microcalcification.Targeting 241 cases in which magnification mammography was performed for patients who visited the hospital due to breast microcalcification, age distribution and the location of lesions were analyzed in X-ray guided biopsy and ultrasound guided biopsy. By classifying exams performed after magnification mammography, the frequencies of X-ray guided biopsy and ultrasound guided biopsy were analyzed, and malignant and benign results were confirmed. The results showed that 64 cases(26.6%) were X-ray guided biopsy, which was 5.4 times higher than 12 cases(4.9%) of ultrasound guided biopsy.Due to development of ultrasound equipments, stereotactic vacuum-assisted biopsy, etc. the methods of histological diagnosis of microcalcification have become diverse, but when considering characteristics and limitations of each exam, X-ray guided biopsy is thought to be most accurate and useful.

Stereotactic vacuum-assisted breast biopsy under lateral decubitus position.

PurposeStereotactic vacuum-assisted breast biopsy (VAB) has been established as a standard method for histological diagnosis of microcalcification or nonpalpable breast lesions on mammography. Generally, the procedure has been done under the prone position or upright sitting position. We herein attempt to evaluate clinical utility of Stereotactic VAB under lateral decubitus position.MethodsOne hundred six women (mean age, 51.2 years) with mammographically detected microcalcification underwent lateral decubitus positioning VAB using the 8G probe. In all cases, we obtained mammography specimens for identification of microcalcification and postprocedure mammography. We reviewed mean procedure time, pieces of specimen, pathology and follow-up mammography.ResultsThe procedure took approximately 20 minutes (range, 15-24 minutes). Average number of obtained specimens was 8.5 pieces (range, 6-12 pieces). Microcalcifications were confirmed in both specimen mammography and microscopic slides. Of 106 cases, 10 cases were diagnosed as ductal carcinoma in situ. Additional surgical management was performed. Atypical ductal hyperplasias were found in 8 cases, and fibrocystic changes in 88 cases.ConclusionStereotactic VAB using the 8G probe under lateral decubitus position does not need a dedicated table, and is easier to maintain the position. Also, this procedure is accurate and safe. Thus, stereotactic VAB using the 8G probe under lateral decubitus position will be a useful method for diagnosis of microcalcification or nonpalpable breast lesions on mammography.

PB.28: Is second-time vacuum-assisted biopsy effective in improving preoperative diagnosis rate of screen-detected DCIS?

The NHSBSP standards for non-operative diagnosis are a target of 95% for invasive cancers (minimum 90%) and 90% for non-invasive cancer (minimum 85%). The lower target for non-invasive cancers reflects the difficulty in achieving definitive diagnosis of DCIS. Our unit has routinely used vacuum biopsies (VAB) for non-operative diagnosis of microcalcifications. Following an audit in 2009, repeat VAB were extended to B3 cases selected in MDT in order to improve non-operative diagnosis of DCIS.

Impact of digital mammography in the detection and management of microcalcifications

ObjectiveTo determine whether the introduction of digital mammography in breast cancer screening has resulted in changes in the detection and management of microcalcifications. Material and methodsWe retrospectively studied the performance indicators of our breast cancer screening program that are related to the diagnosis of microcalcifications (rates of recall and recommendation of intermediate follow-up after screening, rate of indication of invasive procedures for microcalcifications and their positive predictive value, detection rate for microcalcifications, and number of ductal carcinomas in situ (DCIS) diagnosed). We compared the results obtained using direct digital mammography (September 2008–August 2009) with those obtained using analog mammography (September 2006–August 2007). Statistical analysisChi-square test and measures of association. ResultsWe found that using digital mammography led to significant increases in the recall rate (from 50.8 to 64‰), in the rate of intermediate follow-up after screening (from 9.41 to 18.7‰), in the rate of indication for invasive procedures (from 1.88 to 3.01‰), in the cancers detected through microcalcifications (from 0.86 to 1.36‰), and in the number of DCIS diagnosed. ConclusionDirect digital mammography has improved the detection of microcalcifications, increasing the number of DCIS diagnosed without decreasing the positive predictive value of the invasive procedures indicated for microcalcifications. However, direct digital mammography has had a negative effect by increasing the recall rate and indication for short-term follow-up, possibly due to the difficulty of comparing the findings with those of earlier analog mammograms.

99mTc-thymine scintigraphy may be a promising method in the diagnosis of breast cancer

OBJECTIVE:Mammography has been established as the gold standard for the detection of breast cancer, and imaging techniques such as ultrasonography, magnetic resonance imaging, scintigraphy and positron emission tomography may be useful to improve its sensitivity and specificity. The objective of this study with breast scintigraphy was to evaluate the uptake of 99mTc-thymine in mammary lesions.METHODS:A total of 45 patients were included in this study. Thirty-three patients (73%) were subjected to surgery or percutaneous biopsy, providing histopathological data. The other 12 patients who remained under surveillance received clinical examinations and biannual mammography with a normal follow-up of at least three years, the data from which were used for comparison with the scintimammography results.RESULTS:The majority of patients (64.4%) had clinically impalpable lesions with a mammogram diagnosis of microcalcifications, impalpable nodules, or focal asymmetry. Of the studied lesions, 87% were smaller or equal to 20 mm in diameter, and 22% had malignant histopathological findings. Scintigraphy with 99mTc-thymine had a sensitivity of 70%, a specificity of 85.7%, positive and negative predictive values of 58.3% and 90.9%, respectively, and an accuracy of 82.2%.CONCLUSIONS:The results of this study are consistent with those previously reported by other authors. The good specificity and high negative predictive value of this technique and the absence of uptake in the heart indicate that it may be a promising complementary method in clinical practice and that it may contribute to reducing unnecessary benign biopsies.

P5-08-01: Quantitative Analysis of Strain Ratio of Microcalcification Lesions with Surgical Specimen Mammography.

Abstract Measurement of the strain induced by compression can be useful in the diagnosis of breast tumors. Microcalcification (MC) detected by mammography could be the only symptom of early breast cancers. The purpose of this study was to develop a quantitative method for a differential diagnosis of MC lesions based on the strain ratio (SR) obtained by applying different breast compression pressure during mammography. Methods: This prospective study was conducted with institutional review board approval and the written informed consent was obtained. Twenty-five mastectomy specimens (24 for treatment of breast cancer and 1 from contralateral prophylactic mastectomy) with MCs were examined by digital mammography. There were 24 malignant MCs (mean size of 18.8 mm) detected in the 24 separate specimens, including 14 lesions of invasive carcinoma and 10 lesions of carcinoma in situ. Five benign MCs (mean size of 21.6 mm) were detected, including four lesions which coexisted with malignant MCs in the four separate specimens, and one was discovered in the prophylactic mastectomy specimen. Each specimen experienced four different magnitudes of compression force and the corresponding images were acquired for further analysis. Images in Digital Imaging and Communications in Medicine format (DICOM) were exported into custom software, written in Matlab, to contour the region of interest. Stress was defined as the force divided by the whole specimen area, and the square root of MC area was calculated to represent strain deformation. The SR was the slope of the best-fit line through the four points of each lesion. Histology of the MC was correlated with SR. Receiver operating characteristic (ROC) curve analysis was performed to evaluate the diagnostic performance of SR for discrimination between benign and malignant MC. Results: The SRs were higher in the malignant MC group (139.10 a.u.) than in the benign MC group (34.09 a.u.; p = 0.024). The SR between invasive carcinoma and carcinoma in situ showed no statistic significance (127.03 a.u. vs. 156.00 a.u.; p = 0.642). The area under the ROC curve for the diagnosis of benign and malignant MC was 0.825 (95% CI, 0.667 to 0.982). Conclusion: This study demonstrated that the SR detected by mammography showed potential for distinguishing benign from malignant MCs. Further in vivo investigations of larger cohorts are necessary to validate these results. Citation Information: Cancer Res 2011;71(24 Suppl):Abstract nr P5-08-01.

Influencia de la mamografía digital en la detección y manejo de microcalcificaciones

ObjectiveTo determine whether the introduction of digital mammography in breast cancer screening has resulted in changes in the detection and management of microcalcifications. Material and methodsWe retrospectively studied the performance indicators of our breast cancer screening program that are related to the diagnosis of microcalcifications (rates of recall and recommendation of intermediate follow-up after screening, rate of indication of invasive procedures for microcalcifications and their positive predictive value, detection rate for microcalcifications, and number of ductal carcinomas in situ (DCIS) diagnosed). We compared the results obtained using direct digital mammography (september 2008-august 2009) with those obtained using analog mammography (september 2006-august 2007). Statistical analysisChi-square test and measures of association. ResultsWe found that using digital mammography led to significant increases in the recall rate (from 50.8 to 64‰), in the rate of intermediate follow-up after screening (from 9.41 to 18.7‰), in the rate of indication for invasive procedures (from 1.88 to 3.01‰), in the cancers detected through microcalcifications (from 0.86 to 1.36‰), and in the number of DCIS diagnosed. ConclusionDirect digital mammography has improved the detection of microcalcifications, increasing the number of DCIS diagnosed without decreasing the positive predictive value of the invasive procedures indicated for microcalcifications. However, direct digital mammography has had a negative effect by increasing the recall rate and indication for short-term follow-up, possibly due to the difficulty of comparing the findings with those of earlier analog mammograms.

Screen-detected ductal carcinoma in situ - fine needle aspiration versus core biopsy

Our current practice in the investigation of micro-calcification is to perform fine needle aspiration (FNA), with immediate results, and vacuum-assisted core biopsy (VACB), which was introduced in April 2007. The British Association Of Surgical Oncology 2006/2007 audit reported fewer centres using cytology alone for diagnosis of screen-detected cancer. We assessed the contribution of FNA to non-operative diagnosis of microcalcification, and the benefit to women in having immediate FNA results. We also investigated the effect of introducing VACB, rather than core biopsy for sampling microcalcification, on the number of repeat cores, and on the non-operative diagnosis of microcalcification.

Zooming method (× 2.0) of digital mammographyvsdigital magnification view (× 1.8) in full-field digital mammography for the diagnosis of microcalcifications

The purpose of this study was to determine whether the interpretation of microcalcifications assessed on images zoomed (x 2.0) from digital mammograms is at least equivalent to that from digital magnification mammography (x 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 (A(z) 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 (A(z) = 0.8680 for ZOOM; A(z) = 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.

In patients with DCIS: is it sufficient to histologically examine only those tissue specimens that contain microcalcifications?

The purpose was to investigate in patients with histologically proven DCIS to what extent there is agreement between radiographically proven microcalcifications of specimens obtained by vacuum-assisted biopsy and the histologic diagnosis of microcalcifications and DCIS, and second, to assess the accuracy of biopsy in relation to the number of specimens obtained in patients with high-grade and low-grade DCIS. Four hundred twenty specimens from 35 patients who were diagnosed with DCIS were examined radiographically and histologically for the presence of microcalcifications. The results were analyzed using the McNemar-test. In addition, the average numbers of biopsy specimens necessary for diagnosing low-grade DCIS and high-grade DCIS were compared using the t-test. Specimen radiography had a PPV of 0.50 and a NPV of 0.85 for the demonstration of DCIS. Differences in localization between radiographically proven microcalcifications and DCIS were statistically significant (p<0.01). The difference between the mean numbers of specimens required per patient for correctly diagnosing high-grade or low-grade DCIS was statistically significant (p<0.01). Specimen radiography is very limited in identifying those specimens that are crucial for diagnosing DCIS. The rate of underestimation is expected to be higher for low-grade than for high-grade DCIS. The findings suggest that all samples obtained by vacuum-assisted breast biopsy should be histologically examined.

Texture analysis of tissue surrounding microcalcifications on mammograms for breast cancer diagnosis

Diagnosis of microcalcifications (MCs) is challenged by the presence of dense breast parenchyma, resulting in low specificity values and thus in unnecessary biopsies. The current study investigates whether texture properties of the tissue surrounding MCs can contribute to breast cancer diagnosis. A case sample of 100 biopsy-proved MC clusters (46 benign, 54 malignant) from 85 dense mammographic images, included in the Digital Database for Screening Mammography, was analysed. Regions of interest (ROIs) containing the MCs were pre-processed using a wavelet-based contrast enhancement method, followed by local thresholding to segment MCs; the segmented MCs were excluded from original image ROIs, and the remaining area (surrounding tissue) was subjected to texture analysis. Four categories of textural features (first order statistics, co-occurrence matrices features, run length matrices features and Laws' texture energy measures) were extracted from the surrounding tissue. The ability of each feature category in discriminating malignant from benign tissue was investigated using a k-nearest neighbour (kNN) classifier. An additional classification scheme was performed by combining classification outputs of three textural feature categories (the most discriminating ones) with a majority voting rule. Receiver operating characteristic (ROC) analysis was conducted for classifier performance evaluation of the individual textural feature categories and of the combined classification scheme. The best performance was achieved by the combined classification scheme yielding an area under the ROC curve (A(z)) of 0.96 (sensitivity 94.4%, specificity 80.0%). Texture analysis of tissue surrounding MCs shows promising results in computer-aided diagnosis of breast cancer and may contribute to the reduction of unnecessary biopsies.

Voir les microcalcifications mammaires en échographie: luxe ou nécessite ?: À propos de 50 cas

Purpose Determine the value of ultrasound for the diagnosis of isolated breast microcalcifications. Material and Methods Fifty clusters of microcalcifications, including 25 smaller than 10 mm, were examined by ultrasound (5-13 MHz) prior to stereotactic aspiration macrobiopsy (30 benign lesions, three borderline lesions, and 17 malignant lesions, including ten in situ lesions and seven invasive lesions). Mammography had placed 13 of these cases in BI-RADS 3, 24 in BI-RADS 4, and 13 in BI-RADS 5. The BI-RADS classification was also used for ultrasound assessment. Results Six of the 18 microcalcifications that were not seen by ultrasound were malignant (two invasive ductal cancers [IDC] and four ductal carcinomas in situ [DCIS]). Two of the four cases with no sonographically visible tissue mass proved to be malignant (one IDC, one DCIS); these two lesions had been classified BI-RADS 4 and 5 by mammography and were larger than 10 mm. Ultrasound visualized 16 masses classed BI-RADS 3, ten masses classed BI-RADS 4, and two masses classed BI-RADS 5. One of the lesions classified as BI-RADS 3 by mammography was an IDC that was classed BI-RADS3 by ultrasound. Four of the lesions classed BI-RADS 4 by mammography were malignant (three were classified BI-RADS3 by ultrasound while one was classed BI-RADS4). One benign lesion was classified BI-RADS 5 by ultrasound. Four cancers were mammographically classed BI-RADS 5; ultrasound was in agreement in one case but classed three of the cases as BI-RADS 4. In one case, ultrasound gave a diagnosis of benignity (BI-RADS 3 classification). Conclusion Ultrasound is unsuited for the diagnosis of microcalcifications because it fails to visualize a mass in one-third of cancers and the existence of a mass is correlated with malignancy in one-third of cases. Furthermore, US does not correct the false-negative errors of mammography, and it underestimates the rate of malignancy by ascribing a benign appearance to 50% of cancers, which mammography correctly classifies BI-RADS 4 or 5.