Full-field Digital Mammography Research Articles

Abstract PS07-02: Benign breast disease and microcalcifications in percutaneous biopsies and breast cancer risk

Abstract Objectives: Mammographic microcalcifications (calcs) are a sentinel marker of in-situ and invasive breast cancer (BC) but most calcs reflect benign breast disease (BBD). BBD comprises a diverse set of lesions, variably associated with increased BC risk. While calc frequency data for the modern era are limited, historically, calcs were reported in 11% of BBD biopsies. Some studies suggest that calcs in BBD impact BC risks; however, the frequency and BC risks associated with calcs during the percutaneous biopsy era have not been clearly established. Accordingly, we assessed the association of calcs with specific BBD lesions and BC risk in a large contemporaneous BBD cohort including detailed pathology review. Methods: A cohort of 4,819 patients with percutaneously diagnosed BBD from 2002-2013 at Mayo Clinic, were identified. The cohort was followed from 6 months after biopsy until censoring, BC diagnosis, or December 2021. Mean follow-up was 11.3 (SD=5.1) years for BBD patients who remained cancer-free in follow-up compared with 7.4 (SD=4.3) years for cases. Histology of all biopsies were reviewed microscopically to record pathologic findings. A natural language processing algorithm (NLPA) was developed and utilized to identify the presence of calcs based on pathology reports. NLPA results were compared to 300 matched biopsy reports, taken as ground truth. We performed age-adjusted Cox proportional hazards regression to assess hazard ratios (HRs) with 95% confidence intervals (CIs) for specific BBD lesions, stratified by the presence (calc+) or absence of calcs (calcs-), with estimation of an interaction term to test for differences in risks by calc strata. Standardized incidence ratios (SIRs) estimated risks for calc+ and calc- BBD lesions versus matched strata for Iowa SEER population-based BC incidence rates. Results: The NLPA achieved sensitivity=0.993 and specificity=0.986. Overall, 42.8% of BBD biopsies were calc+, including 49.1% of biopsies preceding BC and 42.4% of biopsies not preceding BC (Chi-square p=0.02). Overall, risks of BC among women with BBD calc+ biopsies did not differ significantly from those of women with calc- BBD: HR=1.13 (95% CI: 0.90,1.41), p=0.290. SIRs were also similar for the two groups; women with BBD calc+ biopsies had an SIR =2.00 (95% CI: 1.72, 2.33) and BBD calc- biopsies yielded an SIR= 1.91 (95% CI: 1.64,2.22) (Table 1). HRs were similar for specific calc+ and calc- BBD lesions, with progressively higher risks for non-proliferative disease (NP), proliferative disease without atypia (PDWA) and atypical hyperplasia (AH) (pinteraction=0.55). Interaction terms were not significant for any specific lesion, apart from a marginally significant result for dilated ducts, wherein risks were marginally higher for calc- lesions (pInteraction =0.048), perhaps representing a chance finding. SIRs for calc+ versus calc- BBD lesions were also similar. Overall, 77.3% of AH was calc+; for AH calc+, SIR=3.76 (95%CI: 2.74-5.17) and for AH calc-, SIR=4.41 (95%CI: 2.56-7.59). Conclusion: In this recent, larger percutaneous BBD cohort, calcs were present in 42.8% of all specimens, representing a marked increase compared with historical BBD data, particularly those dominated by surgical biopsy for diagnosis and preceding implementation of full-field digital mammography. In this study, calcs in percutaneously diagnosed BBD were not associated with increased BC risk. Table 1: Comparison of standard incidence ratio of subsequent breast cancer with and without microcalcifications in benign breast disease by histologic impression (NP = non-proliferative disease, PDWA = proliferative disease without atypia, and AH = atypical hyperplasia). (1) compared to Iowa SEER population Citation Format: Sarah Schrup, Robert Vierkant, Stacey Winham, Celine Vachon, Derek Radisky, Jodi Carter, Laura Pacheco-Spann, Matthew Jensen, Amy Degnim, Mark Sherman. Benign breast disease and microcalcifications in percutaneous biopsies and breast cancer risk [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PS07-02.

Cigarette smoking and mammographic breast density in post-menopausal women from the EPIC Florence cohort.

Cigarette smoking has been recognized as a risk factor for breast cancer (BC) also if the biological mechanism remains poorly understood. High mammographic breast density (MBD) is associated with BC risk and many BC risk factors, such as genetic, anthropometric, reproductive and lifestyle factors and age, are also able to modulate MBD. The aim of the present study was to prospectively explore, in post-menopausal women, the association between smoking habits and MBD, assessed using an automated software, considering duration and intensity of smoking. The analysis was carried out in 3,774 women enrolled in the European Prospective Investigation into Cancer and Nutrition (EPIC) Florence cohort in 1993-98, participating in the 2004-06 follow up (FU) and with at least one full-field digital mammography (FFDM) performed after FU. For each woman, detailed information on smoking habits, anthropometry, lifestyle and reproductive history was collected at enrollment and at FU. Smoking information at baseline and at FU was integrated. The fully automated Volpara™ software was used to obtain total breast volume (cm3), absolute breast dense volume (DV, cm3) and volumetric percent density (VPD, %) from the first available FFDM (average 5.3 years from FU). Multivariable linear regression models were applied to evaluate the associations between smoking habits and VPD or DV. An inverse association between smoking exposure and VPD emerged (Diff% -7.96%, p <0.0001 for current smokers and -3.92%, p 0.01 for former smokers, compared with non-smokers). An inverse dose-response relationship with number of cigarettes/day, years of smoking duration and lifetime smoking exposure (pack-years) and a direct association with time since smoking cessation among former smokers emerged. Similar associations, with an attenuated effect, emerged when DV was considered as the outcome variable. This longitudinal study confirms the inverse association between active smoking, a known risk factor for BC, and MBD among post-menopausal women. The inclusion of smoking habits in the existing BC risk prediction models could be evaluated in future studies.

Performance evaluation of six digital mammography systems

The strong advance in digital mammography as a tool for breast cancer screening requires that the new systems be characterized. Quality control protocols describe the methodology to evaluate systems performance. Detective quantum efficiency (DQE) is the most suitable parameter for describing the imaging performance of an X-ray imaging device. The objective of this study was to characterize in terms of DQE six digital mammography systems, at different detector air kerma (DAK) levels for a variety of beam qualities. A Carestream EHR-M3 CR detector, a small field digital mammography system Siemens Opdima, and full field digital mammography systems Planmed Clarity, GE Essential, GE Pristina and GE Crystal Nova were characterized using the European Guidelines protocol. Modulation transfer function (MTF), normalized noise power spectrum (NNPS) and DQE were determined, for an extended detector air kerma range. Attenuated beam qualities (obtained by adding 2 mm Al to the corresponding beam qualities) used were 28 kV with anode/filter combination Mo/Mo for the EHR-M3, Opdima, Essential and Pristina systems; 28 kV W/Ag for the Clarity; 28 kV W/Rh for the Crystal Nova; 28 kV Mo/Rh for the EHR-M3; and 34 kV Rh/Ag for the Pristina. Two groups were identified in MTF analysis, and the group composed of Clarity, Opdima and Essential presented the highest MTF values. In NNPS analysis, three main groups were identified, in which the systems Crystal Nova and Essential presented lower and higher NNPS, respectively. Crystal Nova system also exhibited higher DQE values for low spatial frequencies, while Opdima and Clarity presented higher DQE values for medium to high spatial frequency. Agreement with data from literature indicates that the systems evaluated are operating under typical conditions. Evidence of improvement in detectors performance was found.

Generalisable deep learning method for mammographic density prediction across imaging techniques and self-reported race.

Breast density is an important risk factor for breast cancer complemented by a higher risk of cancers being missed during screening of dense breasts due to reduced sensitivity of mammography. Automated, deep learning-based prediction of breast density could provide subject-specific risk assessment and flag difficult cases during screening. However, there is a lack of evidence for generalisability across imaging techniques and, importantly, across race. This study used a large, racially diverse dataset with 69,697 mammographic studies comprising 451,642 individual images from 23,057 female participants. A deep learning model was developed for four-class BI-RADS density prediction. A comprehensive performance evaluation assessed the generalisability across two imaging techniques, full-field digital mammography (FFDM) and two-dimensional synthetic (2DS) mammography. A detailed subgroup performance and bias analysis assessed the generalisability across participants' race. Here we show that a model trained on FFDM-only achieves a 4-class BI-RADS classification accuracy of 80.5% (79.7-81.4) on FFDM and 79.4% (78.5-80.2) on unseen 2DS data. When trained on both FFDM and 2DS images, the performance increases to 82.3% (81.4-83.0) and 82.3% (81.3-83.1). Racial subgroup analysis shows unbiased performance across Black, White, and Asian participants, despite a separate analysis confirming that race can be predicted from the images with a high accuracy of 86.7% (86.0-87.4). Deep learning-based breast density prediction generalises across imaging techniques and race. No substantial disparities are found for any subgroup, including races that were never seen during model development, suggesting that density predictions are unbiased.

A comparative study between the diagnostic performance of contrast-enhanced digital mammography and dynamic contrast-enhanced MRI in invasive lobular carcinoma of the breast

BackgroundInvasive lobular carcinoma is the second most prevalent histological subtype of breast cancer after invasive duct carcinoma, with a reported increased incidence in the last two decades. It often presents with challenging imaging characteristics that lower the sensitivity of mammography in their detection and delineation of their extent. Moreover, an increased risk of having synchronous lesions in the same or opposite breast was reported in cases with invasive lobular carcinoma. This obviates the need for other imaging modalities, specifically contrast-enhanced imaging modalities, to improve early detection as well as allow precise determination of the extent of the disease. Our aim in this study was to compare the diagnostic performance of contrast-enhanced digital mammography and dynamic contrast-enhanced magnetic resonance imaging (MRI) in the local staging of invasive lobular carcinoma regarding the size, extensions, multiplicity and bilaterality.MethodsThis study included 46 female patients with pathologically proven invasive lobular carcinoma. They underwent full-field digital mammography with a complementary ultrasound examination, contrast-enhanced digital mammography, and dynamic contrast-enhanced MRI. The findings encountered by the three imaging modalities were evaluated independently, and the results were compared with final histopathology.ResultsIn the current study, dynamic contrast-enhanced MRI study was the most sensitive modality in the detection of the index lesion, synchronous ipsilateral and contralateral lesions and achieved a sensitivity of 100% in each analysis as compared to contrast-enhanced digital mammography, which achieved a sensitivity of 97.8%, 85.7% and 80%, respectively. Regarding the assessment of the lesion extent to the surroundings, there was a tendency to overestimation by MRI examination.ConclusionsAlthough dynamic contrast-enhanced MRI is the most sensitive imaging modality for detecting the index lesion, multiplicity and bilaterality, contrast-enhanced digital mammography achieved comparable overall accuracy. Regarding the locoregional staging of invasive lobular carcinoma, there was a tendency for relative overestimation by MRI examination.

Abstract B078: Artificial-intelligence-driven breast density assessment in the transition from full-field digital mammograms to digital breast tomosynthesis

Abstract Introduction: To enhance reproducibility and robustness in mammographic density assessment, various artificial intelligence (AI) models have been proposed to automatically classify mammographic images into BI-RADS density categories. Despite their promising performances, so far density AI models have been assessed primarily in traditional full-field digital mammography (FFDM) images. Our study aims to assess the potential of AI in breast density assessment in FFDM versus the newer synthetic mammography (SM) images acquired with digital breast tomosynthesis. Methods: We retrospectively analyzed negative (BI-RADS 1 or 2) routine mammographic screening exams (Selenia or Selenia Dimensions; Hologic) acquired at sites within the Barnes-Jewish/Christian (BJC) Healthcare network in St. Louis, MO from 2015 to 2018. BI-RADS breast density assessments of radiologists were obtained from BJC’s mammography reporting software (Magview 7.1). For each mammographic imaging modality, a balanced dataset of 4,000 women was selected so there were equal numbers of women in each of the four BI-RADS density categories, and each woman had at least one mediolateral oblique (MLO) and one craniocaudal (CC) view per breast in that mammographic imaging modality. Previously validated pre-processing steps were applied to all FFDM and SM images to standardize image orientation and intensity. Images were then split into training, validation, and test sets at ratios of 80%, 10%, and 10%, respectively, while maintaining the distribution of breast density categories and ensuring that all images of the same woman appear only in one set. Our AI model was based on the widely used ResNet50 architecture and was designed to accept as an input a mammographic image and predict the BI-RADS breast density category that the image belongs to. Our AI model was optimized, trained, and evaluated separately for each mammographic imaging modality. We report on the AI model’s predictive accuracy on the test set for each mammographic imaging modality, for both views as well as separately for CC and MLO; accuracy differences in FFDM versus SM were assessed via bootstrapping. Results: A batch size of 32, learning rate of e-6, and Adam optimizer were chosen as the optimal hyperparameters for our AI model. Using the same hyperparameters, the AI model demonstrated substantially higher accuracy on the test set for FFDM than for SM (FFDM: accuracy = 71% ± 4.5% versus SM: accuracy = 66% ± 4.2%; p-value&amp;lt;0.001 for comparison). Similar conclusion held when CC and MLO views were evaluated separately (accuracy = 72% ± 4.6% versus 66% ± 4.3% for CC; accuracy = 69% ± 4.5% versus 62% ± 4.3% for MLO; p-value&amp;lt;0.001 for both comparisons). Conclusions: AI performance in BI-RADS breast density assessment was significantly higher on FFDM versus SM, even under the same AI model design, dataset size and training process. Our preliminary findings suggest that further AI optimizations and adaptations may be needed as we translate AI models from FFDM to the newer SM format acquired with digital breast tomosynthesis. Citation Format: Krisha Anant, Juanita Hernandez Lopez, Debbie Bennett, Aimilia Gastounioti. Artificial-intelligence-driven breast density assessment in the transition from full-field digital mammograms to digital breast tomosynthesis [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Advances in Breast Cancer Research; 2023 Oct 19-22; San Diego, California. Philadelphia (PA): AACR; Cancer Res 2024;84(3 Suppl_1):Abstract nr B078.

The Role of Magnetic Resonance Imaging in the Preoperative Staging and Treatment of Invasive Lobular Carcinoma

IntroductionInvasive lobular carcinoma (ILC) is known for its diffuse growth pattern and its associated challenges in diagnosing. Magnetic resonance imaging (MRI) is the most accurate imaging modality and might aid in improving preoperative staging compared to full field digital mammography (FFDM) and ultrasound (US), however current literature is inconsistent. The aim of this paper is to evaluate the accuracy of MRI staging compared to FFDM/US and pathology results. MethodsIn this single-centre retrospective study, all patients diagnosed with ILC between 2014 and 2019 who underwent preoperative MRI were included. Specific parameters studied were: (1) the need for second-look targeted biopsies, (2) detection of new tumors (ie, contralateral or multifocal), (3) changes in cTNM-classification, and (4) impact on final treatment plan. Bland-Altman plots were used to compare the tumor sizes measured on MRI and FFDM/US with actual pathological tumor sizes. ResultsNinety-nine patients were included. After performing preoperative MRI, 9 (9.1%) multifocal tumors were diagnosed after additional biopsies. Contralateral tumors were detected twice (2.0%) and cN classification was upgraded in 7 cases (7.1%). Surgical treatment or neoadjuvant treatment plans were changed in 16 patients (16.1%). Compared to histopathological results, FFDM/US underestimated tumor size with a mean of 0.4 cm (Limit of agreement (LoA): -2.8 cm to 2.0 cm) whereas MRI overestimated tumor size with a mean of 0.6 cm (LoA: -1.9 cm to 3.0 cm). ConclusionsIn our study, mean differences in tumor size measurements using FFDM/US and MRI were comparable, with similar random errors. MRI correctly diagnosed multifocal and contralateral tumors more often and provided a better cN staging.

Radiation doses received in the UK breast screening programmes 2019-2023.

To report the latest UK mammography dose survey results and to compare radiation doses from digital breast tomosynthesis (DBT) and full-field digital mammography (FFDM) in UK breast screening. Anonymized exposure factors were collected for 111 152 screening cases and 5113 assessment cases from 405 x-ray sets across the United Kingdom using an online submission system linked to a national database of mammography quality control data. Output and beam quality measurements from each set were combined with exposure data to estimate mean glandular doses (MGD). FFDM doses increased by ∼10% compared to the 2016-2019 national survey but compressed breast thicknesses (CBT) remained similar. DBT doses were 34%-40% higher than FFDM overall and 34% higher than FFDM for breasts 50-60mm thick. We found a possible overestimation of PMMA breast equivalent thicknesses at low CBTs, but the evidence was not conclusive. Recent changes to the mix of x-ray models in use in UK breast screening have resulted in higher FFDM breast doses. DBT doses in the NHSBSP are on average higher than FFDM by ∼34%-40%. This is the first national study to report DBT and FFDM MGDs in UK breast screening.

YOLO-based CAD framework with ViT transformer for breast mass detection and classification in CESM and FFDM images

Breast cancer detection is considered a challenging task for the average experienced radiologist due to the variation of the lesions’ size and shape, especially with the existence of high fibro-glandular tissues. The revolution of deep learning and computer vision contributes recently in introducing systems that can provide an automated diagnosis for breast cancer that can act as a second opinion for doctors/radiologists. The most of previously proposed deep learning-based Computer-Aided Diagnosis (CAD) systems mainly utilized Convolutional Neural Networks (CNN) that focuses on local features. Recently, vision transformers (ViT) have shown great potential in image classification tasks due to its ability in learning the local and global spatial features. This paper proposes a fully automated CAD framework based on YOLOv4 network and ViT transformers for mass detection and classification of Contrast Enhanced Spectral Mammography (CESM) images. CESM is an evolution type of Full Field Digital Mammography (FFDM) images that provides enhanced visualization for breast tissues. Different experiments were conducted to evaluate the proposed framework on two different datasets that are INbreast and CDD-CESM that provides both FFDM and CESM images. The model achieved at mass detection a mean Average Precision (mAP) score of 98.69%, 81.52%, and 71.65% and mass classification accuracy of 95.65%, 97.61%, and 80% for INbreast, CE-CESM, and DM-CESM, respectively. The proposed framework showed competitive results regarding the state-of-the-art models in INbreast. It outperformed the previous work in the literature in terms of the F1-score by almost 5% for mass detection in CESM. Moreover, the experiments showed that the CESM could provide more morphological features that can be more informative, especially with the highly dense breast tissues.

Estudio comparativo de la dosis de radiación de la mamografía espectral con contraste (CEM), mamografía digital y tomosíntesis mamaria

IntroductionThe use of contrast-enhanced spectral mammography (CESM) has increased in recent years, as has awareness of radiation dose safety among professionals and patients. The principal aim of this study was to compare radiation exposure measured using the entrance surface dose (ESD) and the average glandular dose (AGD) in CESM, full-field digital mammography (FFDM) and digital breast tomosynthesis (DBT). Our second objective was to evaluate differences caused by compressed breast thickness, compression force and patient age. Material and methodsA retrospective observational study included all patients who had undergone a CESM between May 2021 and May 2022. Data was collected on ESD and AGD from the different CESM studies, and breast density and volume were determined by 2expert radiologists. The comparative analysis focused on the dose of radiation received during the craniocaudal (CC) projection of the right breast in CESM studies and FFDM or DBT, performed within a 12-month period. Lastly, a statistical analysis was performed to determine the influence of breast compression thickness, compression force and patient age. ResultsSeventy-seven patients participated in the comparative study and forty-four in the dosimetric study. Differences in radiation dose (ESD/AGD) were found among the 3breast imaging techniques. The dose in CESM (1.70/5.39 mGy) was lower than in DBT (2.19/6.79 mGy) and higher than in FFDM (1.26/4.06 mGy) for an average breast compression thickness of 59.64mm. A positive correlation was observed between the dose received in CESM and breast compression thickness (ρ=0.55), and a negative correlation was observed with patient age (ρ= –0.27). No differences in dosimetric variables were observed for different compression forces. ConclusionsThe ESD and AGD in the CC projection of the right breast in CESM are higher than in FFDM but lower than in DBT. The dose had a positive correlation with breast compression thickness and a negative correlation with patient age.

Discrepancy between Tumor Size Assessed by Full-Field Digital Mammography or Ultrasonography (cT) and Pathology (pT) in a Multicenter Series of Breast Metaplastic Carcinoma Patients.

A retrospective cohort study was conducted on databases encompassing records of BC patients (2012-2022) at the National Research Institutes of Oncology (Warsaw, Gliwice and Krakow Branches). Inclusion criteria comprised confirmed diagnosis in postsurgical pathology reports with tumor size details (pT) and availability of tumor size from preoperative US and/or FFDM. Patients subjected to neoadjuvant systemic treatment were excluded. Demographics and clinicopathological data were gathered. Forty-five females were included. A total of 86.7% were triple-negative. The median age was 66 years (range: 33-89). The median pT was 41.63 mm (6-130), and eight patients were N-positive. Median tumor size assessed by US and FFDM was 31.81 mm (9-100) and 34.14 mm (0-120), respectively. Neither technique demonstrated superiority (p > 0.05), but they both underestimated the tumor size (p = 0.002 for US and p = 0.018 for FFDM). Smaller tumors (pT1-2) were statistically more accurately assessed by any technique (p < 0.001). Only pT correlated with overall survival. The risk of underestimation in tumor size assessment with US and FFDM has to be taken into consideration while planning surgical procedures for BC-Mp.

A Comparative Study of Breast Mass Detection Using YOLOv8 Deep Learning Model in Various Data Scenarios on Multi-View Digital Mammograms

Breast cancer is one of the most common types of cancer among women worldwide. It typically begins with abnormal cell growth in the breast glands or milk ducts and can spread to other tissues. Many breast cancer cases start with the presence of a mass and should be carefully examined. Masses can be monitored using X-ray-based digital mammography images, including right craniocaudal, left craniocaudal, right mediolateral oblique, and left mediolateral oblique views. In this study, automatic mass detection and localization were performed on mammography images taken from the full-field digital mammography VinDr-Mammo dataset using the YOLOv8 deep learning model. Three different scenarios were tested: raw data, data with preprocessing to crop breast regions, and data with only mass regions cropped to a 1.2x ratio. The data were divided into 80% for training and 10% each for validation and testing. The results were evaluated using performance metrics such as precision, recall, F1-score, mAP, and training graphs. At the end of the study, it is demonstrated that the YOLOv8 deep learning model provides successful results in mass detection and localization, indicating its potential use as a computer-based decision support system.

Imaging characteristics of interval cancers detected on Full Field Digital Mammography (FFDM) versus Digital Breast Tomosynthesis (DBT)

ObjectiveTo compare imaging features of interval cancers detected in patients screened with full field digital mammography (FFDM) versus digital breast tomosynthesis (DBT). Materials/MethodsThis retrospective observational study consisted of female patients undergoing screening DM or FFDM at an academic medical center and two outpatient imaging facilities between January 2012 and June 2017. A natural language processing algorithm queried breast imaging reports for breast density and BI-RADS category. This was cross-referenced to an institutional breast cancer registry to identify interval cancers. Retrospective consensus review of the cases was done to categorize imaging features of interval cancers on FFDM vs DBT. ResultsThe rate of interval cancers was comparable in patients screened with FFDM (30/39793) and DBT (29/32180) (p = 0.58). There was no significant difference in the rate, histopathology, or imaging features of interval cancers in patients screened with FFDM versus DBT. The most common mammographic features on diagnostic imaging across both groups was the presence of a mass (13/47). Almost equally common was negative diagnostic mammogram with mass detected only on ultrasound (11/47). The rate of interval cancers detected by high-risk surveillance breast MRI was increased in patients who previously had screening with DBT relative to those who had screening with FFDM (p = 0.0419). ConclusionThere is no significant difference in rate of detection, histopathology, or imaging features of interval cancers in patients screened with FFDM versus DBT. However, across both cohorts, the most common features on diagnostic mammogram were either the presence of a mass or a negative mammogram.

LAMIS-DMDB: A new full field digital mammography database for breast cancer AI-CAD researches

The current state of machine learning (ML) and deep learning (DL) shows that they are powerful tools that can be used to glean knowledge from a huge amount of data. While a great deal of research in this area has centered around improving the accuracy and efficiency of training and inference algorithms, there has been relatively little attention paid to the equally important problem of monitoring the quality of data. To tackle this challenge, we have created a cutting-edge breast database capable of employing ML and DL algorithms to detect and classify breast cancer. It is noteworthy that compared to other digital mammogram databases (DMDB), the Laboratory of Mathematics, Informatics and System (LAMIS) images have better resolution and are in full-field digital mammography (FFDM) format. Furthermore, the images can be accessed according to their abnormality (normal, benign, malignant), lesions classification (mass, calcification, architectural distortion, multiple finding), American College of Radiology (ACR) density classification (ACR1, ACR2, ACR3, ACR4) and Breast Imaging Reporting and Data System (BI-RADS). Specifically, the database is designed to provide a variety of metadata as well as clinical data in simple comma separated values (CSV) format that can be really beneficial to the breast cancer research community and to the development of computer-aided diagnosis (CADx) tools that rely on artificial intelligence (AI) algorithms, such as those based on DL models.

Comparative Analysis of Diagnostic Performance of Automatic Breast Ultrasound, Full-Field Digital Mammography and Contrast-Enhanced Mammography in Relation to Breast Composition.

This single center study includes a comparative analysis of the diagnostic performance of full-field digital mammography (FFDM), contrast-enhanced mammography (CEM) and automatic breast ultrasound (ABUS) in the group of patients with breast American College of Radiology (ACR) categories C and D as well as A and B with FFDM. The study involved 297 patients who underwent ABUS and FFDM. Breast types C and D were determined in 40% of patients with FFDM and low- energy CEM. CEM was performed on 76 patients. Focal lesions were found in 131 patients, of which 115 were histopathologically verified. The number of lesions detected in patients with multiple lesions were 40 from 48 with ABUS, 13 with FFDM and 21 with CEM. Compliance in determining the number of foci was 82% for FFDM and 91% for both CEM and ABUS. In breast types C and D, 72% of all lesions were found with ABUS, 56% with CEM and 29% with FFDM (p = 0.008, p = 0.000); all invasive cancers were diagnosed with ABUS, 83% with CEM and 59% with FFDM (p = 0.000, p = 0.023); 100% DCIS were diagnosed with ABUS, 93% with CEM and 59% with FFDM. The size of lesions from histopathology in breast ACR categories A and B was 14-26 mm, while in breast categories C and D was 11-37 mm. In breast categories C and D, sensitivity of ABUS, FFDM and CEM was, respectively, 78.05, 85.37, 92.68; specificity: 40, 13.33, 8.33; PPV (positive predictive value): 78.05, 72.92, 77.55; NPV (negative predictive value): 40, 25, 25, accuracy: 67.86, 66.07, 73.58. In breast categories A and B, sensitivity of ABUS, FFDM and CEM was, respectively, 81.25, 93.75, 93.48; specificity: 18.18, 18.18, 16.67; PPV: 81.25, 83.33, 89.58; NPV: 18.18, 40, 25; accuracy: 69.49, 79.66, 84.62. The sensitivity of the combination of FFDM and ABUS was 100 for all types of breast categories; the accuracy was 75 in breast types C and D and 81.36 in breast types A and B. The study confirms the predominance of C and D breast anatomy types and the low diagnostic performance of FFDM within that group and indicates ABUS and CEM as potential additive methods in breast cancer diagnostics.

Automated 3D Ultrasound as an Adjunct to Screening Mammography Programs in Dense Breast: Literature Review and Metanalysis.

Purpose: The purpose of this meta-analysis is to investigate the effectiveness of supplementing screening mammography with three-dimensional automated breast ultrasonography (3D ABUS) in improving breast cancer detection rates in asymptomatic women with dense breasts. Materials and Methods: We conducted a thorough review of scientific publications comparing 3D ABUS and mammography. Articles for inclusion were sourced from peer-reviewed journal databases, namely MEDLINE (PubMed) and Scopus, based on an initial screening of their titles and abstracts. To ensure a sufficient sample size for meaningful analysis, only studies evaluating a minimum of 20 patients were retained. Eligibility for evaluation was further limited to articles written in English. Additionally, selected studies were required to have participants aged 18 or above at the time of the study. We analyzed 25 studies published between 2000 and 2021, which included a total of 31,549 women with dense breasts. Among these women, 229 underwent mammography alone, while 347 underwent mammography in combination with 3D ABUS. The average age of the women was 50.86 years (±10 years standard deviation), with a range of 40-56 years. In our efforts to address and reduce bias, we applied a range of statistical analyses. These included assessing study variation through heterogeneity assessment, accounting for potential study variability using a random-effects model, exploring sources of bias via meta-regression analysis, and checking for publication bias through funnel plots and the Egger test. These methods ensured the reliability of our study findings. Results: According to the 25 studies included in this metanalysis, out of the total number of women, 27,495 were diagnosed with breast cancer. Of these, 211 were diagnosed through mammography alone, while an additional 329 women were diagnosed through the combination of full-field digital mammography (FFDSM) and 3D ABUS. This represents an increase of 51.5%. The rate of cancers detected per 1000 women screened was 23.25‱ (95% confidence interval [CI]: 21.20, 25.60; p < 0.001) with mammography alone. In contrast, the addition of 3D ABUS to mammography increased the number of tumors detected to 20.95‱ (95% confidence interval [CI]: 18.50, 23; p < 0.001) per 1000 women screened. Discussion: Even though variability in study results, lack of long-term outcomes, and selection bias may be present, this systematic review and meta-analysis confirms that supplementing mammography with 3D ABUS increases the accuracy of breast cancer detection in women with ACR3 to ACR4 breasts. Our findings suggest that the combination of mammography and 3D ABUS should be considered for screening women with dense breasts. Conclusions: Our research confirms that adding 3D automated breast ultrasound to mammography-only screening in patients with dense breasts (ACR3 and ACR4) significantly (p < 0.05) increases the cancer detection rate.

Eye radiation dose from breast cancer screening using full field digital mammography and digital breast tomosynthesis: A phantom study

IntroductionThe eye lens is recently classified as one of the most radiosensitive tissues by the International Commission on Radiological Protection (ICRP), and it has been suggested that the eye lens receives radiation dose during mammography due to scatter radiation. The aim of this study was to investigate the radiation dose received by the lens of the clients’ eye from Full Field Digital Mammography (FFDM) and Digital Breast Tomosynthesis (DBT) screening. MethodsThe eye radiation dose received by ATOM dosimetry phantom was estimated with thermo-luminescent dosemeters (TLDs). One TLD was utilised for each eye. A breast phantom was exposed for four-view screening mammography using 16 FFDM machines and one DBT machine. The breast phantom was exposed three times for each mammographic position and an average TLD dose reading was considered to minimise random error. ResultsFor four-view FFDM screening, the phantom eye radiation dose ranges from 0.013 mGy to 0.029 mGy with a mean±sd of 0.019 ± 0.005 mGy. A higher eye radiation dose of 0.041 mGy was recorded from four-view DBT screening. The statistical analysis demonstrated that the eye lens radiation dose is strongly and significantly correlated to breast organ dose and X-ray tube voltage. ConclusionThe phantom eye lens was exposed to scatter radiation from FFDM and DBT screening. The measured dose via the four-view DBT screening was higher than the four-view FFDM screening, but sits below the internationally acceptable ranges. If the findings of our paper hold true in practice, then the risk to the lens of the eyes for women attending breast screening is acceptable. Implications for practiceThe new lens radiation dose levels recommended by the ICRP necessitate the reevaluation of eye radiation dose from different radiographic examinations, especially those used for screening purpose where healthy individuals involved.

Threshold in breast compression reduction for full-field digital mammography and digital breast tomosynthesis

IntroductionBreast compression is essential in mammography to improve image quality and reduce radiation dose. However, it can cause discomfort or even pain in women which could discourage them from attending future mammography examinations. Therefore, this study aims to explore the maximum reduction in breast compression in full-field digital mammography (FFDM) and digital breast tomosynthesis (DBT) that is achievable without impacting on image quality and dose. MethodsTen compression force (CF) levels (20N–110N, with 10N intervals) were assessed on Siemens MAMMOMAT Inspiration with Nuclear Associates 18–228 phantom. Imaging was carried out in craniocaudal projection using Automatic Exposure Control at 28 kVp with a Tungsten/Rhodium anode/filter combination, and at 50° sweep angle for DBT. Using ImageJ software, image quality of the acquired mammograms and central tomosynthesis slices were examined based on mass conspicuity (MC) and microcalcification conspicuity (MicroC). Entrance skin dose (ESD) and mean glandular dose (MGD) were recorded from Digital Imaging and Communication in Medicine image header. Linear regression was performed to examine the relationship between CF with ESD, MGD, MC and MicroC. Differences in image quality and radiation dose were assessed with one-way analysis of variance and Kruskal-Wallis H test. ResultsSignificant correlations were noted between CF with ESD and MicroC for FFDM and DBT, with DBT also demonstrating associations with MGD and MC. No significant differences were observed for ESD, MGD, MC and MicroC when CF was reduced to 40N and 80N in FFDM and DBT respectively. ConclusionThis study demonstrated that CF can be reduced as low as 40N and 80N in FFDM and DBT respectively, without significant impact on image quality and radiation dose. Implications for practiceReduced mammographic compression may reduce discomfort or pain in women, which may improve attendance rate in breast screening programmes. Findings from this study will provide reference for future work examining breast compression in mammography.

MLN-net: A multi-source medical image segmentation method for clustered microcalcifications using multiple layer normalization

The accurate segmentation of clustered microcalcifications in mammography is crucial for the diagnosis and treatment of breast cancer. Despite exhibiting expert-level accuracy, recent deep learning advancements in medical image segmentation provide insufficient contribution to practical applications, due to the domain shift resulting from differences in patient postures, individual gland density, and imaging modalities, etc. In this paper, a novel framework named MLN-net is proposed for clustered microcalcification segmentation. It can segment multi-source images using only single source images. Specifically, to rich domain distribution information, we introduce a source domain image augmentation for generating multi-source images. A structure of multiple layer normalization (LN) layers is then used to construct the segmentation network, which can be found efficient for clustered microcalcification segmentation in different domains. Additionally, a branch selection strategy is designed for measuring the similarity of the source domain data and the target domain data. To validate the proposed MLN-net, extensive analyses including ablation experiments are performed, comparison of 12 baseline methods. MLN-net enhances segmentation quality of full-field digital mammography (FFDM) and digital breast tomosynthe (DBT) images from the FFDM-DBT dataset, achieving the average Dice similarity coefficient (DSC) of 86.52% and the average Hausdorff distance (HD) of 20.49 mm on the source domain DBT. And it outperforms the baseline models for the task in FFDM images from both the CBIS-DDSM and the FFDM-DBT dataset, achieving the average DSC of 50.78% and the average HD of 35.12 mm on the source domain CBIS-DDSM. Extensive experiments validate the effectiveness of MLN-net in segmenting clustered microcalcifications from different domains and its segmentation accuracy surpasses state-of-the-art methods. Code will be available at https://github.com/yezanting/MLN-NET-VERSON1.

Deep learning, radiomics and radiogenomics applications in the digital breast tomosynthesis: a systematic review

BackgroundRecent advancements in computing power and state-of-the-art algorithms have helped in more accessible and accurate diagnosis of numerous diseases. In addition, the development of de novo areas in imaging science, such as radiomics and radiogenomics, have been adding more to personalize healthcare to stratify patients better. These techniques associate imaging phenotypes with the related disease genes. Various imaging modalities have been used for years to diagnose breast cancer. Nonetheless, digital breast tomosynthesis (DBT), a state-of-the-art technique, has produced promising results comparatively. DBT, a 3D mammography, is replacing conventional 2D mammography rapidly. This technological advancement is key to AI algorithms for accurately interpreting medical images.Objective and methodsThis paper presents a comprehensive review of deep learning (DL), radiomics and radiogenomics in breast image analysis. This review focuses on DBT, its extracted synthetic mammography (SM), and full-field digital mammography (FFDM). Furthermore, this survey provides systematic knowledge about DL, radiomics, and radiogenomics for beginners and advanced-level researchers.ResultsA total of 500 articles were identified, with 30 studies included as the set criteria. Parallel benchmarking of radiomics, radiogenomics, and DL models applied to the DBT images could allow clinicians and researchers alike to have greater awareness as they consider clinical deployment or development of new models. This review provides a comprehensive guide to understanding the current state of early breast cancer detection using DBT images.ConclusionUsing this survey, investigators with various backgrounds can easily seek interdisciplinary science and new DL, radiomics, and radiogenomics directions towards DBT.