Malignant Microcalcifications Research Articles

Detection and diagnosis of automated breast ultrasound in patients with BI-RADS category 4 microcalcifications: a retrospective study

BackgroundAutomated Breast Ultrasound (AB US) has shown good application value and prospects in breast disease screening and diagnosis. The aim of the study was to explore the ability of AB US to detect and diagnose mammographically Breast Imaging Reporting and Data System (BI-RADS) category 4 microcalcifications.Methods575 pathologically confirmed mammographically BI-RADS category 4 microcalcifications from January 2017 to June 2021 were included. All patients also completed AB US examinations. Based on the final pathological results, analyzed and summarized the AB US image features, and compared the evaluation results with mammography, to explore the detection and diagnostic ability of AB US for these suspicious microcalcifications.Results250 were finally confirmed as malignant and 325 were benign. Mammographic findings including microcalcifications morphology (61/80 with amorphous, coarse heterogeneous and fine pleomorphic, 13/14 with fine-linear or branching), calcification distribution (189/346 with grouped, 40/67 with linear and segmental), associated features (70/96 with asymmetric shadow), higher BI-RADS category with 4B (88/120) and 4 C (73/38) showed higher incidence in malignant lesions, and were the independent factors associated with malignant microcalcifications. 477 (477/575, 83.0%) microcalcifications were detected by AB US, including 223 malignant and 254 benign, with a significantly higher detection rate for malignant lesions (x2 = 12.20, P < 0.001). Logistic regression analysis showed microcalcifications with architectural distortion (odds ratio [OR] = 0.30, P = 0.014), with amorphous, coarse heterogeneous and fine pleomorphic morphology (OR = 3.15, P = 0.037), grouped (OR = 1.90, P = 0.017), liner and segmental distribution (OR = 8.93, P = 0.004) were the independent factors which could affect the detectability of AB US for microcalcifications. In AB US, malignant calcification was more frequent in a mass (104/154) or intraductal (20/32), and with ductal changes (30/41) or architectural distortion (58/68), especially with the both (12/12). BI-RADS category results also showed that AB US had higher sensitivity to malignant calcification than mammography (64.8% vs. 46.8%).ConclusionsAB US has good detectability for mammographically BI-RADS category 4 microcalcifications, especially for malignant lesions. Malignant calcification is more common in a mass and intraductal in AB US, and tend to associated with architectural distortion or duct changes. Also, AB US has higher sensitivity than mammography to malignant microcalcification, which is expected to become an effective supplementary examination method for breast microcalcifications, especially in dense breasts.

Assessing the malignancy of suspicious breast microcalcifications: the role of contrast enhanced mammography.

To assess the role of contrast-enhanced mammography (CEM) in predicting the malignancy of breast calcifications. We retrospectively evaluated patients with suspicious calcifications (BIRADS 4) who underwent CEM and stereotactic vacuum-assisted biopsy (VAB) at our institution. We assessed the sensitivity (SE), specificity (SP), positive predictive value (PPV) and negative predictive value (NPV) of CEM in predicting malignancy of microcalcifications with a 95% confidence interval; we performed an overall analysis and a subgroup analysis stratified into group A-low risk (BIRADS 4a) and group B-medium/high risk (BIRADS 4b-4c). We then evaluated the correlation between enhancement and tumour proliferation index (Ki-67) for all malignant lesions. Data from 182 patients with 184 lesions were collected. Overall the SE of CEM in predicting the malignancy of microcalcifications was 0.70, SP was 0.85, the PPV was 0.82, the NPV was 0.76 and AUC was 0.78. SE in group A was 0.89, SP was 0.89, PPV was 0.57, NPV was 0.98 and AUC was 0.75. SE in group B was 0.68, SP was 0.80, PPV was 0.87, NPV was 0.57 and AUC was 0.75. Among malignant microcalcifications that showed enhancement (N = 52), 61.5% had Ki-67 ≥ 20% and 38.5% had low Ki-67 values. Among the lesions that did not show enhancement (N = 22), 90.9% had Ki-67 < 20% and 9.1% showed high Ki-67 values 20%. The absence of enhancement can be used as an indicative parameter for the absence of disease in cases of low-suspicious microcalcifications, but not in intermediate-high suspicious ones for which biopsy remains mandatory and can be used to distinguish indolent lesions from more aggressive neoplasms, with consequent reduction of overdiagnosis and overtreatment.

A single-institution retrospective evaluation of noninvasive localization for non-palpable breast microcalcification

TechniqueFrom January 1, 2018, to December 31, 2021, we localized the breast microcalcification of 40 patients before the surgical excision. We measured the distance between the nipple and the center of the calcification on the CC view and the ML view, respectively. The operation proceeded around the intersection between two lines, slightly larger than the diameter of the microcalcification. We also analyze the pathological findings. ResultsAll 40 patients successfully detected calcification by mammograms preoperatively using the method mentioned above. 38 patients have the microcalcification removal within the one-time operation, while the other two underwent an extended lumpectomy. 20 of 40 calcifications (50 %) were malignant and 12(30 %) were precancerous lesions. In the group of women older than 45 years old, the percentages of malignant and atypical hyperplasias are 56.25 % (18/32) and 31.25 % (10/32) respectively. ConclusionOur non-invasive method of preoperative localization is safe and cost-effective. Furthermore, initial observations suggest that there may be a link between age and malignant microcalcification.

Interpretable Radiomic Signature for Breast Microcalcification Detection and Classification

Breast microcalcifications are observed in 80% of mammograms, and a notable proportion can lead to invasive tumors. However, diagnosing microcalcifications is a highly complicated and error-prone process due to their diverse sizes, shapes, and subtle variations. In this study, we propose a radiomic signature that effectively differentiates between healthy tissue, benign microcalcifications, and malignant microcalcifications. Radiomic features were extracted from a proprietary dataset, composed of 380 healthy tissue, 136 benign, and 242 malignant microcalcifications ROIs. Subsequently, two distinct signatures were selected to differentiate between healthy tissue and microcalcifications (detection task) and between benign and malignant microcalcifications (classification task). Machine learning models, namely Support Vector Machine, Random Forest, and XGBoost, were employed as classifiers. The shared signature selected for both tasks was then used to train a multi-class model capable of simultaneously classifying healthy, benign, and malignant ROIs. A significant overlap was discovered between the detection and classification signatures. The performance of the models was highly promising, with XGBoost exhibiting an AUC-ROC of 0.830, 0.856, and 0.876 for healthy, benign, and malignant microcalcifications classification, respectively. The intrinsic interpretability of radiomic features, and the use of the Mean Score Decrease method for model introspection, enabled models’ clinical validation. In fact, the most important features, namely GLCM Contrast, FO Minimum and FO Entropy, were compared and found important in other studies on breast cancer.

Transforming data from the image to the text domain: benign versus malignant micro-calcification classification

In this paper we present a new approach for the classification of benign and malignant micro-calcification clusters by transforming data from the image to the text domain. A string representation is extracted from binary micro-calcification segmentation images. We extracted two different features from the strings and combined different machine learning techniques towards benign versus malignant classification. We evaluated our proposed method on the DDSM database and experimental results indicates a Classification Accuracy equal to 92%.

The impact of (simulated) resolution on breast cancer diagnosis based on high-resolution 3D micro-CT microcalcification images.

Breast microcalcifications (MCs) are considered to be a robust marker of breast cancer. A machine learning model can provide breast cancer diagnosis based on properties of individual MCs - if their characteristics are captured at high resolution and in3D. The main purpose of the study was to explore the impact of image resolution (8µm, 16µm, 32µm, 64µm) when diagnosing breast cancer using radiomics features extracted from individual high resolution 3D micro-CT MCimages. Breast MCs extracted from 86 female patients were analyzed at four different spatial resolutions: 8µm (original resolution) and 16µm, 32µm, 64µm (simulated image resolutions). Radiomic features were extracted at each image resolution in an attempt, to find a compact feature signature allowing to distinguish benign and malignant MCs. Machine learning algorithms were used for classifying individual MCs and samples (i.e., patients). For sample diagnosis, a custom-based thresholding approach was used to combine individual MC results into sample results. We conducted classification experiments when using (a) the same MCs visible in 8µm, 16µm, 32µm, and 64µm resolution; (b) the same MCs visible in 8µm, 16µm, and 32µm resolution; (c) the same MCs visible in 8µm and 16µm resolution; (d) all MCs visible in 8µm, 16µm, 32µm, and 64µm resolution. Accuracy, sensitivity, specificity, AUC, and F1 score were computed for eachexperiment. The individual MC results yielded an accuracy of 77.27%, AUC of 83.83%, F1 score of 77.25%, sensitivity of 80.86%, and specificity of 72.2% at 8µm resolution. For the individual MC classifications we report for the F1 scores: a 2.29% drop when using 16µm instead of 8µm, a 4.01% drop when using 32µm instead of 8µm, a 10.69% drop when using 64µm instead of 8µm. The sample results yielded an accuracy and F1 score of 81.4%, sensitivity of 80.43%, and specificity value of 82.5% at 8µm. For the sample classifications we report for F1 score values: a 6.3% drop when using 16µm instead of 8µm, a 4.91% drop when using 32µm instead of 8µm, and a 6.3% drop when using 64µm instead of 8µm. The highest classification results are obtained at the highest resolution (8µm). If breast MCs characteristics could be visualized/captured in 3D at a higher resolution compared to what is used nowadays in digital mammograms (approximately 70µm), breast cancer diagnosis will beimproved.

Morphological and Distribution Pattern of Calcifications on Full Field Digital Mammography versus Digital Breast Tomosynthesis and Comparison of Diagnostic Abilities of the Two Modalities: A Retrospective Study

Introduction: Microcalcification (MC) is an effective and sometimes the only indicator of breast cancer. Early detection and characterisation of malignant MC can facilitate early diagnosis and timely treatment of breast cancer. However, due to the small size and low contrast as compared to the background parenchyma, it is difficult and time-consuming for radiologists to accurately evaluate MC. Aim: To compare the diagnostic abilities of Full Field Digital Mammography (FFDM) and Digital Breast Tomosynthesis (DBT) in the detection and characterisation of breast calcifications. Materials and Methods: This retrospective descriptive study was conducted in the year 2022 at the breast imaging unit of Dr. Ram Manohar Lohia Institute of Medical Sciences, Lucknow, Uttar Pradesh, India and data of patients who had undergone FFDM and DBT between March 2019- September 2020 was collected. Mammograms of 702 women with 1217 breasts were evaluated and MC was detected in 622 breasts. Based on the morphology and distribution pattern, Breast Imaging Reporting and Data System (BI-RADS) assessment Category was assigned from 2 to 5. Cases with BI-RADS 2 and 3 were followed-up by repeat Mammograms at 6-month to 1-year intervals. Cases with BI-RADS 4 and 5 were biopsied under stereotactic or ultrasound guidance. Histopathology findings and the stability of the calcifications on sequential mammograms were considered the gold standard for final BI-RADS categorisation. The Chi-square test was applied for the comparison of FFDM and DBT. Results: Typically benign morphology MC was noted in 508 (81.67%) of breasts on FFDM and 505 (80.67%) on DBT. Suspicious morphology MC was noted in 114 (18.33%) of breasts on FFDM and 121 (19.33%) on DBT. Vascular calcification was the most common benign MC seen in 233 cases (37.45%) on FFDM and 244 cases (38.9%) on DBT. Similarly, fine pleomorphic was the most common suspicious morphology MC on FFDM and DBT both seen in 47 cases (7.5%) and 44 cases (7.02%), respectively. The most common distribution pattern was diffuse seen in 582 cases (93.56%) on FFDM and 583 cases (93.13%) on DBT, respectively. No significant difference was observed (p=0.283) in the rate of detection or characterisation of MC by FFDM or DBT. The sensitivity of both modalities were almost similar (97.7% and 97.9%) without any significant difference (p=0.278). Similarly, there was no difference in the specificity (94.9% and 94.4%, respectively, p=0.289). Conclusion: The performance of FFDM and DBT for the detection and characterisation of MC is not significantly different.

Dual energy-based quantification method for determination of breast microcalcification types

The purpose of this study is to distinguish and characterize breast microcalcification types (benign and malignant) non-invasively using photon-counting spectral mammography. In this study, a photon-counting spectral mammography system was simulated using Geant4 application for tomographic emission (GATE) tool. Based on the photon-counting detector, dual-energy images were obtained using two energy bins. Calcium oxalate and calcium hydroxyapatite were used for benign and malignant microcalcifications, respectively. As a quantitative characteristic evaluation for two types of microcalcification related to etiology, an analytical model was implemented for the determination of the calcium/phosphorus mass ratio (mCa/mP) based on the dual-energy method. In the chemical composition of each microcalcification, the calcium hydroxyapatite has a phosphate substance, and calcium oxalate has an oxalate substance. The thicknesses of the calcium oxalate corresponding to calcium hydroxyapatite were calculated to preserve equal photon beam attenuation. The results indicate a higher mass ratio value in the case of malignant microcalcifications when compared with that in the case of benign ones. Even when the breast thickness increased up to 5 cm, the difference in the mass ratio exhibited a constant tendency. By excluding the effect on x-ray attenuation properties, we confirmed that malignant and benign microcalcifications were quantitatively distinguished based only on the mineral properties of the chemical composition. In conclusion, this study provides quantitative and objective indicators, a non-invasive discrimination method of two types of microcalcifications associated with pathology. We also expect to reduce the frequency of biopsies by improving the accuracy of early diagnosis in mammography.

Una forma factible y precisa de ubicar las microcalcificaciones de mama: dando una oportunidad a la técnica SNOLL

ObjectivesTo evaluate the feasibility and accuracy of the ROLL technique to localize malignant mammary microcalcifications and the risk of local recurrence, we performed a multicentre prospective observational study to assess the application of the technique and progress of patients with a 10year follow-up. Materials and methodsBetween 2007 and 2010, 64 patients were recruited. All the patients had been diagnosed with breast neoplasm due to microcalcifications on mammography and were treated with conservative surgery and sentinel lymph node biopsy. A technetium-99m injection was performed preoperatively, with a single or several punctures (> 3.5 cm lesions), guided by mammography or by ultrasound. In all cases, we performed a preoperative lymphoscintigraphy, to assess contrast migration, and intraoperative mammogram to assess correct removal of the lesion. ResultsIn the 64 patients, contrast injection could be confirmed, and lymphoscintigraphy proved correct migration of the contrast to the sentinel node, allowing excision of the mammary lesion and of the sentinel lymph node in 100%.The intraoperative mammogram showed complete lesion excision in 100% cases. The pathology showed radicality in the first surgery of 84.4% and showed a disease-free survival of 84% at 10 years. ConclusiónThe SNOLL technique (ROLL + SNB) is a feasible and accurate technique for the localization and surgical treatment of malignant microcalcifications with disease-free survival and a relapse rate comparable to the rest of the techniques. Likewise, we propose systematic cavity shave to reduce the need for reinterventions.

Radiomic Applications on Digital Breast Tomosynthesis of BI-RADS Category 4 Calcifications Sent for Vacuum-Assisted Breast Biopsy.

Background: A fair amount of microcalcifications sent for biopsy are false positives. The study investigates whether quantitative radiomic features extracted from digital breast tomosynthesis (DBT) can be an additional and useful tool to discriminate between benign and malignant BI-RADS category 4 microcalcification. Methods: This retrospective study included 252 female patients with BI-RADS category 4 microcalcifications. The patients were divided into two groups according to micro-histopathology: 126 patients with benign lesions and 126 patients with certain or possible malignancies. A total of 91 radiomic features were extracted for each patient, and the 12 most representative features were selected by using the agglomerative hierarchical clustering method. The binary classification task of the two groups was carried out by using four different machine-learning algorithms (i.e., linear support vector machine (SVM), radial basis function (RBF) SVM, logistic regression (LR), and random forest (RF)). Accuracy, sensitivity, sensibility, and the area under the curve (AUC) were calculated for each of them. Results: The best performance was achieved using the RF classifier (AUC = 0.59, 95% confidence interval 0.57–0.60; sensitivity = 0.56, 95% CI 0.54–0.58; specificity = 0.61, 95% CI 0.59–0.63; accuracy = 0.58, 95% CI 0.57–0.59). Conclusions: DBT-based radiomic analysis seems to have only limited potential in discriminating benign from malignant microcalcifications.

Abstract P3-18-08: Feasibility and safety of breast-conserving surgery in early-stage breast cancers during the first trimester of pregnancy

Abstract Background: Breast cancer is the most common malignancy occurring during gestation and should be managed with the same protocols as for young non-pregnant women. In early-stage breast cancer during pregnancy (PrBC), breast-conserving surgery (BCS) with delayed radiation therapy (RT) is a reasonable alternative to radical mastectomy. Regrettably, no specific and widely adopted guidelines on the surgical management of these patients are available. In this study, we investigated the feasibility and safety of BCS during the first trimester of pregnancy in women with early-stage PrBC. Method: The first trimester was defined as 12 weeks and 6 days after the first day of the last menstruation. As for internal protocols, the surgical strategy for PrBC followed the same conservative-oriented schemes applied for nonpregnant patients. Only women with early-stage PrBC treated with BCS during pregnancy followed by planned RT to the whole breast after delivery were included. Exclusion criteria were i) clinical diagnosis or suspicion of inflammatory breast cancer; ii) multicentric disease; iii) diffuse malignant microcalcifications on mammography; iv) previous; v) connective tissue disease, and vi) syndromic breast cancers. All cases underwent central pathological review at the Pathology Department of the European Institute of Oncology. The primary outcome was the isolated local recurrence (ILR). Results: Among 168 PrBC patients, 67 (39.9%) were diagnosed during the first trimester of gestation. Of these, 30 patients (age range, 23-43 years; median=36 years; gestational age, 2-12 weeks; median=7 weeks; median follow-up time=6.5 years) met the inclusion criteria. None of the patients included in this study experienced perioperative surgical complications. No ILR was observed within three months (n=30), 1 year (n=27), and 5 years (n=18) after surgery. The 5-year overall survival rate for all patients was 97% (n=29/30). Four patients experienced ILR or new carcinomas after 6-13 years. These patients are still alive and disease-free after 14-17 years of follow-up. Discussion: In our study, both adjuvant endocrine therapy and anti-HER2 treatment were postponed after delivery. Local recurrences/second primary tumors were observed in 4 out of 30 patients treated with BCS. Given that patient #4 did not receive postoperative RT, but an after-delivery mastectomy for preoperative diagnostic underestimation during pregnancy, this case does not represent a post-BCS recurrence. On the other hand, cases #1-3 could be considered real relapses. Two of these tumors occurred in patients that underwent CT during pregnancy, in which the interval between the end of systemic therapies and the onset of RT was not influenced by the pregnancy. In a single patient (not eligible for systemic treatment in pregnancy), the RT was performed with a longer interval than the usual one of the non-pregnant patients. Survival was not affected by local relapse, underlining the efficacy of salvage treatment.Conclusion: The findings of this study suggest that BCS in the first trimester of pregnancy can be considered reasonably safe for both mother and the child. Mammography should be mandatory in all patients for whom conservative surgery is recommended. Given that the availability of data concerning PrBC and its treatment is scarce and heterogeneous, multicentric studies are warranted. Citation Format: Nicola Fusco, Concetta Blundo, Massimo Giroda, Elham Sajjadi, Konstantinos Venetis, M. Cristina Leonardi, Elisa Vicini, Luca Despini, Claudia F. Rossi, Letterio Runza, Eugenia Di Loreto, Giovanna Scarfone, Elena Guerini-Rocco, Giuseppe Viale, Paolo Veronesi, Barbara Buonomo, Fedro A. Peccatori, Viviana E. Galimberti. Feasibility and safety of breast-conserving surgery in early-stage breast cancers during the first trimester of pregnancy [abstract]. In: Proceedings of the 2021 San Antonio Breast Cancer Symposium; 2021 Dec 7-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2022;82(4 Suppl):Abstract nr P3-18-08.

Evaluation of the Extension of Benign and Malignant Microcalcifications by Breast Magnetic Resonance Imaging, Mammography, and Ultrasonography

Evaluation of the Extension of Benign and Malignant Microcalcifications by Breast Magnetic Resonance Imaging, Mammography, and Ultrasonography

Classification of Breast Cancer in Mammograms with Deep Learning Adding a Fifth Class

Breast cancer is one of the diseases of most profound concern, with the most prevalence worldwide, where early detections and diagnoses play the leading role against this disease achieved through imaging techniques such as mammography. Radiologists tend to have a high false positive rate for mammography diagnoses and an accuracy of around 82%. Currently, deep learning (DL) techniques have shown promising results in the early detection of breast cancer by generating computer-aided diagnosis (CAD) systems implementing convolutional neural networks (CNNs). This work focuses on applying, evaluating, and comparing the architectures: AlexNet, GoogLeNet, Resnet50, and Vgg19 to classify breast lesions after using transfer learning with fine-tuning and training the CNN with regions extracted from the MIAS and INbreast databases. We analyzed 14 classifiers, involving 4 classes as several researches have done it before, corresponding to benign and malignant microcalcifications and masses, and as our main contribution, we also added a 5th class for the normal tissue of the mammary parenchyma increasing the correct detection; in order to evaluate the architectures with a statistical analysis based on the received operational characteristics (ROC), the area under the curve (AUC), F1 Score, accuracy, precision, sensitivity, and specificity. We generate the best results with the CNN GoogLeNet trained with five classes on a balanced database with an AUC of 99.29%, F1 Score of 91.92%, the accuracy of 91.92%, precision of 92.15%, sensitivity of 91.70%, and specificity of 97.66%, concluding that GoogLeNet is optimal as a classifier in a CAD system to deal with breast cancer.

Comparison of Microcalcifications Detection and Characterization in Digital Breast Tomosynthesis (DBT) With Synthesized 2D Mammography (SM) versus DBT with Full-Field Digital Mammography (FFDM)

Background: Synthesized 2D mammography (SM) has been invented to help lower the radiation dose by circumventing the need for acquiring full-field digital mammography (FFDM) when digital breast tomosynthesis (DBT) is performed. Prior studies have compared microcalcifications detection and characterization in FFDM with SM or with DBT alone. Only few studies have compared DBT plus SM and DBT plus FFDM. Objective: To determine the performance of DBT with SM versus DBT with FFDM in detection and characterization of microcalcifications. Materials and Methods: Three hundred three paired examinations of 2D plus DBT images in the same session were performed. Fifty-five biopsyproven malignancy, 198 biopsy-proven benign microcalcifications, and 50 randomly selected negative screening studies were retrospectively reviewed by two radiologists. Comparison of sensitivity and specificity between the two modalities were performed. Results: From the 55 malignant microcalcifications, three cases were missed by DBT with FFDM but detected and correctly categorized as malignant by DBT with SM. Only one case of malignant microcalcifications was not detected by DBT with SM, and the present case was also miscategorized as benign by DBT with FFDM. There were no statistically significant differences in both detections (p=0.42), and characterization (p=0.65) of microcalcification between both modalities. In DBT with SM, the sensitivity was higher, and the specificity was lower for both detection and characterization of microcalcification when compared to DBT with FFDM. Conclusion: DBT in combination with SM is comparable to DBT in combination with FFDM for detection and characterization of microcalcifications. Keywords: Synthesized 2D mammography; Full-field digital mammography; Digital breast tomosynthesis; Microcalcifications detection and characterization

Comparison of diagnostic performances in the evaluation of breast microcalcifications: synthetic mammography versus full-field digital mammography.

Although several studies proved that SM could substitute for FFDM, the efficacy of SM in microcalcification evaluation remains controversial. To investigate the diagnostic performance of synthetic mammography (SM) in the evaluation of microcalcifications in comparison with full-field digital mammography (FFDM). In this retrospective study, 76 mammograms of 76 patients who underwent FFDM and digital breast tomosynthesis (DBT) acquisitions concomitantly between 2018 and 2019 and whose final mammography interpretation revealed microcalcifications (28 malignant microcalcifications and 48 benign microcalcifications) were included. All mammograms were reviewed independently by three radiologists with different levels of breast imaging experience. Readers were blinded to patient outcomes and interpreted each case in two separate reading sessions (first FFDM, second SM + DBT), according to the BI-RADS lexicon. The area under the receiver operating characteristic (ROC) curve (AUC) was calculated using ROC analysis in all cases for FFDM and SM + DBT sessions. The readers also assigned conspicuity scores to mammograms. The interobserver agreement was calculated using intraclass correlation coefficients (ICC). The overall AUCs for malignant microcalcifications were 0.80 (95% CI: 0.75-0.85) in FFDM and 0.85 (95% CI: 0.80-0.89) in SM, and no significant difference was found between the groups (p = 0.0603). The sensitivity of the readers increased slightly with experience. The ICC values of BI-RADS categorization between readers were 0.93 (95% CI: 0.90-0.95) and 0.94 (95% CI: 0.91-0.96) for FFDM and SM, respectively. SM had similar diagnostic performance in the evaluation of breast microcalcifications in comparison with FFDM, regardless of reader experience levels.

Biological features of ductal carcinoma in situ: clinical role and basis for treatment individualization

Ductal carcinoma in situ (DCIS) is an extremely heterogeneous disease in terms of clinical manifestations, morphological changes, and expression of biomarkers, which determine the risk of subsequent development of an invasive breast cancer (BC). Diagnosis and treatment of DCIS prevents the development of invasive tumors (which reduces the potential risk of death from BC); however, the prognostic value of local treatment depends on the biological characteristics of its. The tumor grade, presence of comedonecrosis and expression of estrogen receptors are the key prognostic factors in DCIS for the treatment tactics and prognosis. The clinical symptoms of DCIS are very scarce, the most of tumors is diagnosed by screening mammography; the typical sign of DCIS is malignant microcalcifications or changes of breast architectonic. The sensitivity of mammography, ultrasound and MRI directly depend on the biological characteristics of DCIS. Surgical treatment (breast-conserving surgery or mastectomy) significantly reduces the risk of BC death in women with DCIS G2/G3, and radiotherapy after breast-conserving surgery reduce the risk of local recurrence of non-invasive and invasive BC. The choice of the local treatment (breast-conserving surgery radiation therapy vs mastectomy) depend on such factors as: tumor size, localization, clear margins, and biological characteristics of DCIS. In contrast to invasive cancers, the negative margin in DCIS is more than 2 mm from the tumor. Regional lymph node involvement in DCIS occurs in less than 1% of cases; however, microinvasion is found in analyze the surgical specimen in 15% of patients, which raises the question about regional staging. Risk factors for microinvasion in DCIS are age less than 55 years, tumor lesion size more than 4.0 cm, DCIS grade G3, and tumor palpability. Adjuvant endocrine therapy with tamoxifen significantly reduces the 10-year risk of invasive recurrence by 51%, the risk of contralateral BC by 50% and the risk of death by 40%, but only for hormone-positive DCIS. HER2 overexpression is found in DCIS significantly often (up to 40% of cases) than in invasive BC, HER2+ status correlates with DCIS high grade G3, the presence of comedonecrosis and with increased risk of relapse (both non-invasive and invasive) but is not a reason for anti-HER2 therapy. DCIS low risk and DCIS high risk have not only different morphological characteristics, but also different models of biological behavior, which must be considered in the different choice of treatment tactics.

Classification of microcalcification clusters in digital breast tomosynthesis using ensemble convolutional neural network

BackgroundThe classification of benign and malignant microcalcification clusters (MCs) is an important task for computer-aided diagnosis (CAD) of digital breast tomosynthesis (DBT) images. Influenced by imaging method, DBT has the characteristic of anisotropic resolution, in which the resolution of intra-slice and inter-slice is quite different. In addition, the sharpness of MCs in different slices of DBT is quite different, among which the clearest slice is called focus slice. These characteristics limit the performance of CAD algorithms based on standard 3D convolution neural network (CNN).MethodsTo make full use of the characteristics of the DBT, we proposed a new ensemble CNN, which consists of the 2D ResNet34 and the anisotropic 3D ResNet to extract the 2D focus slice features and 3D contextual features of MCs, respectively. Moreover, the anisotropic 3D convolution is used to build 3D ResNet to avoid the influence of DBT anisotropy.ResultsThe proposed method was evaluated on 495 MCs in DBT images of 275 patients, which are collected from our collaborative hospital. The area under the curve (AUC) of receiver operating characteristic (ROC) and accuracy of classifying benign and malignant MCs using decision-level ensemble strategy were 0.8837 and 82.00%, which were significantly higher than the experimental results of 2D ResNet34 (AUC: 0.8264, ACC: 76.00%) and anisotropic 3D ResNet (AUC: 0.8455, ACC: 76.00%). Compared with the results of 3D features classification in the radiomics, the AUC of the deep learning method with decision-level ensemble strategy was improved by 0.0435, and the F1 score was improved from 79.37 to 85.71%. More importantly, the sensitivity increased from 78.13 to 84.38%, and the specificity increased from 66.67 to 77.78%, which effectively reduced the false positives of diagnosisConclusionThe results fully prove that the ensemble CNN can effectively integrate 2D features and 3D features, improve the classification performance of benign and malignant MCs in DBT, and reduce the false positives.

Breast MRI in the setting of breast carcinoma with suspected microcalcifications and his predictive value in breast cancer management: An interesting case report

The Breast Imaging Reporting and Data System (BI-RADS®) is a standardized system of reporting breast pathology used also for Magnetic Resonance Imaging (MRI). It facilitates clear communication between the radiologist and other physicians as surgeons involved in senology, by providing a lexicon that compares breast gland structures to assessment categories in the management recommendations for the onco-surgical choices. In 30% of all clinical cases in women, breast cancer is correlated to micro-calcifications [1] or occulted lesion as non-palpable nodule and this diagnostic management is not easy, especially if you haven’t an easy access to all the equipment of interventional methods as stereotactic biopsy or radio-pharmacological detection’s method (for example R.O.L.L., Radioguided Occult Breast Lesion Location), and if you cannot know the real distribution of suspected or malignant microcalcifications in mammography. MRI is more accurate than mammography for prediction of residual malignancy after excisional biopsy for breast cancer with suspicious micro-calcifications [2,3]. MRI’s report often influences the surgical performance. MRI can be useful to correlate malignant microcalcifications with pathological tumor size and to allow the pre-operative drawing in onco-plastic surgery for breast cancer. MRI might be more reliable for predicting residual tumor size after an onco-plastic surgical procedure or a conservative mastectomy, with significant influence on surgical outcomes and disease free survival and risk of relapse [4,5]. Keywords: Breast cancer; Breast MRI; Microcalcifications; Multidisciplinary consultation; Breast conservative surgery.

Medical display application for degraded image sharpness restoration based on the modulation transfer function: initial assessment for a five-megapixel mammography display monitor.

An image-display application for medical liquid-crystal display (LCD) monitors called the sharpness recovery (SR) function has been developed to compensate for image sharpness as a function of deficiencies in the modulation transfer function (MTF) of a monitor. We investigated the effects of the SR function for a five-megapixel (MP) mammography LCD monitor on the resolution and noise properties of the displayed images by measuring the MTF and overall noise power spectrum (NPS), respectively. Furthermore, the effectiveness of the SR function for the 5-MP monitor in displaying subtle microcalcifications on digital mammograms was verified using a two-alternative-forced-choice sensitivity measurement as an initial application for medical image interpretation. Four radiologists compared the visibility of 45 regions of interest with a malignant microcalcification cluster shown on SR-processed and unprocessed mammograms. SR processing improved the MTF of the displayed images by approximately 40% at the Nyquist frequency of the 5-MP monitor, whereas it slightly increased the overall NPS values. All observers indicated that the fraction of cases considered to have better visibility of microcalcifications with the SR processing was significantly greater than that without the processing (averaging 82%, with the 95% confidence interval ranging from 70 to 93%). The SR processing for the 5-MP monitor yielded a significant improvement in the resolution properties of the displayed images, with a certain increase in the image noise. The SR function has the potential to improve the observer performance of radiologists, particularly when reading subtle microcalcifications reproduced on 5-MP monitors.

Exploring CNN potential in discriminating benign and malignant calcifications in conventional and dual-energy FFDM: simulations and experimental observations.

Purpose: Deep convolutional neural networks (CNN) have demonstrated impressive success in various image classification tasks. We investigated the use of CNNs to distinguish between benign and malignant microcalcifications, using either conventional or dual-energy mammography x-ray images. The two kinds of calcifications, known as type-I (calcium oxalate crystals) and type-II (calcium phosphate aggregations), have different attenuation properties in the mammographic energy range. However, variations in microcalcification shape, size, and density as well as compressed breast thickness and breast tissue background make this a challenging discrimination task for the human visual system. Approach: Simulations (conventional and dual-energy mammography) and phantom experiments (conventional mammography only) were conducted using the range of breast thicknesses and randomly shaped microcalcifications. The off-the-shelf Resnet-18 CNN was trained on the regions of interest with calcification clusters of the two kinds. Results: Both Monte Carlo simulations and experimental phantom data suggest that deep neural networks can be trained to separate the two classes of calcifications with high accuracy, using dual-energy mammograms. Conclusions: Our work shows the encouraging results of using the CNNs for non-invasive testing for type-I and type-II microcalcifications and may stimulate further research in this area with expanding presence of the novel breast imaging modalities like dual-energy mammography or systems using photon-counting detectors.