Breast Imaging Research Articles

Automated breast density assessment for full-field digital mammography and digital breast tomosynthesis.

Mammographic density is a strong risk factor for breast cancer (BC) and is reported clinically as part of Breast Imaging Reporting and Data System (BI-RADS) results issued by radiologists. Automated assessment of density is needed that can be used for both full-field digital mammography (FFDM) and digital breast tomosynthesis (DBT) as both types of exams are acquired in standard clinical practice. We trained a deep learning model to automate the estimation of BI-RADS density from a prospective Washington University (WashU) clinic-based cohort of 9,714 women, entering into the cohort in 2013 with follow-up through, October 31, 2020. The cohort included 27% non-Hispanic Black women. The trained algorithm was assessed in an external validation cohort that included 18,360 women screened at Emory from January 1, 2013 and followed through December 31, 2020 that included 42% non-Hispanic Black women. Our model-estimated BI-RADS density demonstrated substantial agreement with the density as assessed by radiologist. In the external validation, the agreement with radiologists for category B 81% and C 77% for FFDM and B 83% and C 74% for DBT show important distinction for separation of women with dense breast. We obtained a Cohen's κ of 0.72 (95% CI, 0.71, 0.73) in FFDM and 0.71 (95% CI 0.69, 0.73) in DBT. We provided a consistent and fully automated BI-RADS estimation for both FFDM and DBT using a deep learning model. The software can be easily implemented anywhere for clinical use and risk prediction.

TECRR: a benchmark dataset of radiological reports for BI-RADS classification with machine learning, deep learning, and large language model baselines

BackgroundRecently, machine learning (ML), deep learning (DL), and natural language processing (NLP) have provided promising results in the free-form radiological reports’ classification in the respective medical domain. In order to classify radiological reports properly, a high-quality annotated and curated dataset is required. Currently, no publicly available breast imaging-based radiological dataset exists for the classification of Breast Imaging Reporting and Data System (BI-RADS) categories and breast density scores, as characterized by the American College of Radiology (ACR). To tackle this problem, we construct and annotate a breast imaging-based radiological reports dataset and its benchmark results. The dataset was originally in Spanish. Board-certified radiologists collected and annotated it according to the BI-RADS lexicon and categories at the Breast Radiology department, TecSalud Hospitals Monterrey, Mexico. Initially, it was translated into English language using Google Translate. Afterwards, it was preprocessed by removing duplicates and missing values. After preprocessing, the final dataset consists of 5046 unique reports from 5046 patients with an average age of 53 years and 100% women. Furthermore, we used word-level NLP-based embedding techniques, term frequency-inverse document frequency (TF-IDF) and word2vec to extract semantic and syntactic information. We also compared the performance of ML, DL and large language models (LLMs) classifiers for BI-RADS category classification.ResultsThe final breast imaging-based radiological reports dataset contains 5046 unique reports. We compared K-Nearest Neighbour (KNN), Support Vector Machine (SVM), Naive Bayes (NB), Random Forest (RF), Adaptive Boosting (AdaBoost), Gradient-Boosting (GB), Extreme Gradient Boosting (XGB), Long Short-Term Memory (LSTM), Bidirectional Encoder Representations from Transformers (BERT) and Biomedical Generative Pre-trained Transformer (BioGPT) classifiers. It is observed that the BioGPT classifier with preprocessed data performed 6% better with a mean sensitivity of 0.60 (95% confidence interval (CI), 0.391-0.812) compared to the second best performing classifier BERT, which achieved mean sensitivity of 0.54 (95% CI, 0.477-0.607).ConclusionIn this work, we propose a curated and annotated benchmark dataset that can be used for BI-RADS and breast density category classification. We also provide baseline results of most ML, DL and LLMs models for BI-RADS classification that can be used as a starting point for future investigation. The main objective of this investigation is to provide a repository for the investigators who wish to enter the field to push the boundaries further.

The Utility of Second-Look US to Evaluate Abnormal Molecular Breast Imaging Findings: A Retrospective Study.

The purpose of this study was to evaluate the utility of US for identifying and characterizing lesions detected on molecular breast imaging (MBI). A retrospective single-institution review was performed of patients with MBI studies with subsequent US for abnormal MBI findings between January 1, 2015, and September 30, 2021. Medical records, imaging, and histopathology were reviewed. The reference standard was histopathology and/or imaging follow-up. Associations among MBI findings, the presence of an US correlate, and histopathology were evaluated by Fisher exact tests. The 32 lesions detected on MBI in 25 patients were evaluated by US, and 19 lesions had an US correlate (19/32, 59%). Mass uptake was more likely to have an US correlate (11/13, 85%; P = .02) than nonmass uptake (7/19, 37%), and mass uptake was more likely to be malignant (5/13, 38%; P = .01). Of the 13 lesions without an US correlate, 5 were evaluated and subsequently biopsied by MRI (2 high-risk lesions and 3 benign lesions). Follow-up MBIs demonstrated stability/resolution for 5 lesions in 4 patients at 6 months or longer. Three patients had no further imaging. Mass lesions identified on MBI were more likely to have an US correlate and were more likely to be malignant than nonmass lesions.

Predictors of breast cancer HER2-receptor positivity by MRI intuitive imaging features

BackgroundToday, breast cancer is the most diagnosed cancer worldwide. There are many different clinical presentations, radiological characteristics, and histological types of breast cancer. HER2 is overexpressed in a significant number of breast cancer cases reaching 20% of all breast cancers, and its overexpression is seen directly proportionate with a poor outcome and prognosis.MethodsWe started this cross-sectional research from January 2022–December 2023 on 202 breast cancer patients who had 220 lesions. The molecular subtypes of the different lesions were determined in all the included cases. Magnetic resonance imaging (MRI) studies were conducted in all included cases. The MRI parameters included conventional MRI, diffusion-weighted analysis, and dynamic post-contrast T1-weighted imaging.ResultsThe prevalence of irregular margins (P < 0.001), linear and segmental distribution (P = 0.044), heterogeneous pattern (P < 0.001), and type 2 curve was statistically significantly higher in the HER2-positive lesions. Nipple infiltration incidence showed statistically significant elevation in the HER2-positive lesions (P = 0.017). The lesions’ ADC and perilesional ADC in the HER2-positive lesions were also statistically significantly elevated. The best cutoff point of ADC to detect lesions with positive HER2 expression was > 0.885 × 10–3 mm2/s, with 65.7% sensitivity and 60% specificity, with a statistically significant value (p = 0.005).ConclusionsMagnetic resonance imaging of breast imaging is a promising noninvasive method for identifying breast tumors with the HER2 molecular subtype. Combining various radiological features by MRI may provide a conclusion for recognizing positive HER2 lesions.

ALK-Positive Histiocytosis and its Distinctive Manifestation in the Breast

Abstract Introduction/Objective ALK-positive histiocytosis (APH) is a rare histiocytic proliferation disease that harbors ALK rearrangements, often involving fusion with KIF5B. Primary cases in the unilateral breast are exceptionally uncommon, with only a few reported cases globally, characterizing it as a unique histiocytic proliferation disorder. Methods/Case Report In our study, we report a case of unilateral multifocal breast involvement of ALK-positive histiocytosis following bilateral breast core biopsies in a 56-year-old Hispanic woman who presented with bilateral breast masses. Right breast imaging demonstrated multiple nodular densities, further characterized on ultrasound as a hypoechoic region of 8 cm with increased vascularity. On right breast biopsy, prominent proliferation of histiocytes (lacking high-grade cytologic atypia) with chronic inflammation, few giant cells, and focal cholesterol clefts were identified. On immunohistochemical studies, the lesional cells were variably positive for histiocytic markers CD68, CD163, and PU.1 and were negative for S100 and pancytokeratin. ALK1 showed multifocal staining in the lesional cells as confirmed on repeat study; however, ALK (D5F3), GMS and acid fast studies were negative. The presence of focal cholesterol clefts, scattered giant cells, and chronic inflammation lead us to consider aberrant ALK expression in a reactive process. However, APH was definitively diagnosed through confirmation of clonal histiocyte proliferation, observed findings on morphology, immunophenotyping, and the presence of KIF5B-ALK gene fusion as detected by comprehensive solid tumor fusion panel testing. Results (if a Case Study enter NA) NA Conclusion It is noteworthy that ALK-positive histiocytosis can occasionally present alongside features of a reactive process in the breast. Therefore, considering any history of prior surgery or trauma at the lesion site is crucial. However, we recommend a comprehensive approach in most cases, which includes morphological, immunohistochemical, and molecular analysis on all suspected histiocytosis cases. This approach aims to increase awareness and detection of this rarely described entity and to precisely distinguish it from other diseases for prognostic and therapeutic purposes.

Understanding the risk of ionizing radiation in breast imaging: Concepts and quantities, clinical importance, and future directions

BackgroundConventional mammography remains the primary imaging modality for state-of-the-art breast imaging practice and its benefit (both on diagnostic and screening) was largely reported. In mammography, the typical Mean Glandular Dose (MGD) from X-ray radiation to the breast spans, on average, from 1 to 10 mGy, depending on breast thicknesses, percentage of fibroglandular tissue, and on the examination purpose. MethodsThe aim of this narrative review is to describe the extent of radiation risk in X-ray breast imaging and discuss the main steps and parameters (e.g. MGD, screening frequency and number of examination views) that may have an influence on the radiation risk assessment. ResultsEven though the radiation doses used with these examinations are very low, as compared to other medical or natural radiation exposures, there is a non-negligible associated risk of radiation-induced cancer. Accurate radiation risk assessment permits to better balance the overall estimation of the benefit-to-risk ratio in X-ray breast imaging. ConclusionsIt is expected that a better knowledge about radiation-induced cancer risk among population could improve the communications skills between patients and clinicians and could help to increase the awareness in women about radiation risk perception for a transparent and proper informed choice of imaging exam.

Resistant inflammatory breast lesions: can AI exclude malignancy?

BackgroundNumerous underlying causes can lead to inflammatory breast disorders. A wide range of non-specific symptoms may be presenting symptoms, which could cause a delay in diagnosis and thus improper therapy. Studies on artificial intelligence (AI) are rapidly developing and offer a wide range of possible uses in breast imaging. Artificial intelligence-based computer-assisted diagnosis (AI-CAD) holds promise in the field of mammography. It demonstrated diagnostic performances that are equivalent to or even better than those achieved by stand-alone methods. The current work aimed to identify whether AI can improve the performance of mammography in diagnosing inflammatory breast diseases and excluding the underlying malignancy in cases resistant to treatment that may reduce the need for interventional procedures such as biopsy. MethodsOur study was a retrograde one done on 34 patients with pathologically proven inflammatory breast lesions.ResultsSuppurative breast lesions gave high false positive results. This was also the case with granulomatous mastitis; while simple inflammatory lesions gave true negative results on AI interrogation.ConclusionsArtificial intelligence can be of great value in diagnosing simple inflammatory breast lesions thus following up on such lesions can usually be sufficient without asking for unneeded biopsies. On the other hand, our study showed that AI had high false positive results in suppurative lesions and granulomatous mastitis. Consequently, ultrasonography can be more reliable in their diagnosis.

Ultrasound strain elastography to improve diagnostic performance of breast lesions by reclassifying BI-RADS 3 and 4a lesions: a multicenter diagnostic study.

To investigate the added value of strain elastography (SE) by recategorizing ultrasound (US) Breast Imaging Reporting and Data System (BI-RADS) 3 and 4a lesions. A total of 4371 patients underwent US and SE with BI-RADS 2-5 categories solid breast lesions were included from thirty-two hospitals. We evaluated the elastographic images according to elasticity scores (ES) and strain ratios (SR). Three combined methods (BI-RADS+ES, BI-RADS+SR, BI-RADS+ES+SR) and two reclassified methods were used (method one: upgrading BI-RADS 3 and downgrading BI-RADS 4a, method two: downgrading BI-RADS 4a alone). The diagnostic performance and the potential reduction of unnecessary biopsies were evaluated. Combining BI-RADS with SE had a higher area under the curve (AUC) than BI-RADS alone (0.822-0.898 vs. 0.794, P<0.01). For reclassified method one, the sensitivity, specificity, and accuracy were 99.36%, 66.70%, 78.36% for BI-RADS+ES and 98.01%, 66.45%, 77.72% for BI-RADS+SR, and 99.42%, 66.70%, 78.38% for BI-RADS+ES+SR, respectively. For reclassified method two, the sensitivity, specificity, and accuracy were 99.17%, 70.72%, 80.87% for BI-RADS+ES and 97.76%, 81.75%, 87.46% for BI-RADS+SR, and 99.23%, 69.83%, 80.32% for BI-RADS+ES+SR, respectively. Downgrading BI-RADS 4a alone had higher AUC, specificity, and accuracy (P<0.01) and similar sensitivity (P>0.05) to upgrading BI-RADS 3 and downgrading BI-RADS 4a. Combining SE with BI-RADS could help reduce unnecessary biopsies by 17.64%-55.20%. Combining BI-RADS with SE improved the diagnostic performance in distinguishing benign from malignant lesions and could decrease false-positive breast biopsy rates. Downgrading BI-RADS 4a lesions alone might be sufficient for achieving good diagnostic performance. Downgrading BI-RADS category 4a lesions alone had higher AUC, specificity, and accuracy, and similar sensitivity to upgrading or downgrading BI-RADS category 3 and 4a lesions.

Advanced breast diffusion-weighted imaging: what are the next steps? A proposal from the EUSOBI International Breast Diffusion-weighted Imaging working group.

This study by the EUSOBI International Breast Diffusion-weighted Imaging (DWI) working group aimed to evaluate the current and future applications of advanced DWI in breast imaging. A literature search and a comprehensive survey of EUSOBI members to explore the clinical use and potential of advanced DWI techniques and a literature search were involved. Advanced DWI approaches such as intravoxel incoherent motion (IVIM), diffusion kurtosis imaging (DKI), and diffusion tensor imaging (DTI) were assessed for their current status and challenges in clinical implementation. Although a literature search revealed an increasing number of publications and growing academic interest in advanced DWI, the survey revealed limited adoption of advanced DWI techniques among EUSOBI members, with 32% using IVIM models, 17% using non-Gaussian diffusion techniques for kurtosis analysis, and only 8% using DTI. A variety of DWI techniques are used, with IVIM being the most popular, but less than half use it, suggesting that the study identified a gap between the potential benefits of advanced DWI and its actual use in clinical practice. The findings highlight the need for further research, standardization and simplification to transition advanced DWI from a research tool to regular practice in breast imaging. The study concludes with guidelines and recommendations for future research directions and clinical implementation, emphasizing the importance of interdisciplinary collaboration in this field to improve breast cancer diagnosis and treatment. Advanced DWI in breast imaging, while currently in limited clinical use, offers promising improvements in diagnosis, staging, and treatment monitoring, highlighting the need for standardized protocols, accessible software, and collaborative approaches to promote its broader integration into routine clinical practice. Increasing number of publications on advanced DWI over the last decade indicates growing research interest. EUSOBI survey shows that advanced DWI is used primarily in research, not extensively in clinical practice. More research and standardization are needed to integrate advanced DWI into routine breast imaging practice.

Impact of AI on radiology: a EuroAIM/EuSoMII 2024 survey among members of the European Society of Radiology

In order to assess the perceptions and expectations of the radiology staff about artificial intelligence (AI), we conducted an online survey among ESR members (January–March 2024). It was designed considering that conducted in 2018, updated according to recent advancements and emerging topics, consisting of seven questions regarding demographics and professional background and 28 AI questions. Of 28,000 members contacted, 572 (2%) completed the survey. AI impact was predominantly expected on breast and oncologic imaging, primarily involving CT, mammography, and MRI, and in the detection of abnormalities in asymptomatic subjects. About half of responders did not foresee an impact of AI on job opportunities. For 273/572 respondents (48%), AI-only reports would not be accepted by patients; and 242/572 respondents (42%) think that the use of AI systems will not change the relationship between the radiological team and the patient. According to 255/572 respondents (45%), radiologists will take responsibility for any AI output that may influence clinical decision-making. Of 572 respondents, 274 (48%) are currently using AI, 153 (27%) are not, and 145 (25%) are planning to do so. In conclusion, ESR members declare familiarity with AI technologies, as well as recognition of their potential benefits and challenges. Compared to the 2018 survey, the perception of AI's impact on job opportunities is in general slightly less optimistic (more positive from AI users/researchers), while the radiologist’s responsibility for AI outputs is confirmed. The use of large language models is declared not only limited to research, highlighting the need for education in AI and its regulations.Critical relevance statementThis study critically evaluates the current impact of AI on radiology, revealing significant usage patterns and clinical implications, thereby guiding future integration strategies to enhance efficiency and patient care in clinical radiology.Key PointsThe survey examines ESR member's views about the impact of AI on radiology practice.AI use is relevant in CT and MRI, with varying impacts on job roles.AI tools enhance clinical efficiency but require radiologist oversight for patient acceptance.Graphical

Diagnosis and management of Rosai–Dorfman disease of the breast: Case report and literature review

AbstractRosai–Dorfman disease (RDD) is a rare subtype of non–Langerhans cell histiocytosis. It is a benign disease with variable presentations, with breast involvement being an uncommon manifestation. In this paper, we present a case of breast RDD in a 59‐year‐old Chinese woman who presented with a painless, enlarging mass in her right breast, accompanied by skin changes and no palpable axillary lymph node. A mammogram and breast ultrasonography revealed a progressively enlarging lesion with a suspicious axillary lymph node, leading to an upgrade from Breast Imaging Reporting and Data System (BIRADS) score of 3 to 4A on interval imaging. Core biopsy of the breast mass and cytology of the right axillary lymph node confirmed extranodal RDD. After a 5‐year period of observation, excision was performed due to persistent symptoms. Local recurrence of RDD, with skin discolouration and thickening, was confirmed by skin biopsy 1 year and 9 months after the operation. To the best of our knowledge, this is the first reported case of breast RDD in Hong Kong.

Australian healthcare workers’ views on artificial intelligence in BreastScreen: Results of a mixed method survey study

IntroductionThe evolving role of Artificial Intelligence (AI) in medicine, particularly in radiology and population-based breast cancer screening programs, offers potential accuracy gains and efficiency improvements. However, successful implementation requires understanding of healthcare workers’ views on AI, which this study aims to explore within the Australian BreastScreen program. MethodsAn online survey was distributed to clinical staff involved in breast imaging, collecting responses from November 2022 to April 2023. The survey encompassed demographic information, opinions, and experiences with AI in medical imaging, with questions covering various scenarios of AI integration in BreastScreen ResultsOut of an estimated 350 professionals contacted, 95 responded, with 84.2 % (80/95) being radiologists. Less than half of respondents (44.9 %, 40/89) had worked with artificial intelligence for image classification previously. The majority of radiologists 74.2 % (46/62) thought that the use of AI in reading mammograms for BreastScreen would improve workflow. However, radiologists thought they would behave with increasing caution with scenarios where AI was more autonomous, with the majority of radiologists (63.3 %, 38/60) uncomfortable with holding accountability when the AI was used to triage and remove cases from the workflow. Notably, 60 % of radiologists (36/60) expressed concerns about accountability. DiscussionThe findings suggest an optimistic attitude towards AI among Australian healthcare workers, although when given hypothetical scenarios for the way AI could be integrated into BreastScreen, there was increasing caution with scenarios where AI was more autonomous. This study highlights understanding and concerns of healthcare professionals working in population screening which are important to address when implementing AI into the healthcare system.

Defining the Need for Services for Patients at High Risk of Breast Cancer at a Safety-Net Hospital: An Approach to Narrowing the Disparities Gap.

The National Accreditation Program for Breast Cancer (NAPBC) standards were recently revised to promote breast cancer (BC) risk assessment and subsequent referral for high-risk services. This project sought to estimate the proportion of patients at high risk for BC in the authors' safety-net hospital system, gauge patient interest in high-risk services, and define resources for program development. Women presenting for breast imaging during 2 weeks in 2023 were surveyed. Thirty-five patients with a history or diagnosis of BC were excluded. The Tyrer-Cuzick (TC) model version 8 was used to calculate BC risk. High/intermediate risk was defined as a 10-year risk of 5% or more, a lifetime risk of 15% or more, or both. The criteria for genetic counseling and testing referral were based on National Comprehensive Cancer Network guidelines. A total of 257 patients had a TC risk assessment showing 14.8% (n = 38) with a 10-year BC risk of 5% or more (consideration of endocrine therapy), 6.2% (n = 16) with a lifetime BC risk of 20% or more (qualifying for annual screening MRI), and 10.5% (n = 27) with a lifetime BC risk of 15% or more (consideration of high-risk screening). The criteria for genetic counseling/testing were met by 61 (23.7%) of the 257 patients. Overall, 31.5% (n = 81) qualified for high/intermediate-risk screening, risk reduction, and/or genetic assessment/testing, 92.8% of whom were interested in referrals for additional information and care. In the authors' community, almost one third of patients undergoing breast imaging qualify for BC high-risk assessment and services. The majority of the patients expressed interest in pursuing such services. These data will be used in financial planning and resource allocation to develop a high-risk program at the authors' institution in line with NAPBC guidelines. They are hopeful that these efforts will improve oncologic outcomes and survival from BC in their community.

Positive predictive value of malignancy for additional calcifications found during evaluation of a synchronous breast cancer

PurposeTo evaluate the positive predictive value and factors predictive of malignancy of additional calcifications in the pre-therapeutic work-up of a synchronous breast cancer. Materials and methodsInstitutional review board approval was obtained for this retrospective study and informed consent was waved. Consecutive patients referred to our center between January 1st 2018 and December 31st 2022 for a breast cancer and who presented additional calcifications detected during the pretreatment work-up were eligible for inclusion in this study. Morphology, distribution and BI-RADS category of the calcifications were assessed in consensus by 3 radiologists specialized in breast imaging. Side and distance from the cancer were collected. The predictive value of malignancy of the calcifications was calculated for each BI-RADS category. Factors associated with malignancy were evaluated by logistic non-conditional regression on univariate and multivariate analysis. ResultsOne hundred and thirteen clusters of calcifications in 103 patients were included. Among the groups of calcifications 41 % were malignant, 31 % benign and 28 % were atypia on biopsy. After exclusion of the non-operated atypia, 50.5 % of additional calcifications were ultimately malignant and 49.5 % were benign. The predictive value of malignancy was 20.7 %; 40.7 %; 63 %; 85.7 % and 100 % for category BI-RADS 3, 4a, 4B, 4c and 5 respectively. On multivariate analysis, multifocality or centricity of the index tumour (P = 0.01), BI-RADS classifications (P = 0.0001) and location ipsilateral less than 35 mm to the index cancer (P = 0.008) of the additional calcifications were found to be independent predictors of malignancy. Sixty percent of calcifications were not described on the initial out-center diagnostic work-up. ConclusionAdditional calcifications detected during the pretreatment work-up of a breast cancer are associated with a higher probability of malignancy than in a screening population and require biopsy even when demonstrating probably benign (BI-RADS 3) features.

Racial Disparities and Strategies for Improving Equity in Diagnostic Follow-Up for Abnormal Screening Mammograms.

Black and White women undergo screening mammography at similar rates, but racial disparities in breast cancer outcomes persist. To assess potential contributors, we investigated delays in follow-up after abnormal imaging by race/ethnicity. Women who underwent screening mammography at our urban academic center from January 2015 to February 2018 and received a Breast Imaging Reporting and Data System 0 assessment were included. Kaplan-Meier estimates described distributions of time between diagnostic events from (1) screening to diagnostic imaging and (2) diagnostic imaging to biopsy. Multivariable logistic regression models estimated the associations between race/ethnicity and receipt of follow-up within 15 and 30 days. Two thousand five hundred and fifty-four women were included (48.6% non-Hispanic [NH] Black, 38.2% NH White, 13.1% other/unknown). Median time between screening and diagnostic imaging varied by race/ethnicity (White: 7 days [IQR, 2-14]; Black: 12 days [IQR, 7-23]; other/unknown: 9 days [IQR, 5-21]). There were similar disparities in days between diagnostic imaging and biopsy (White: 12 [IQR, 7-24]; Black: 21 [IQR, 13-37]; other/unknown: 16 [IQR, 9-30]) and between screening and biopsy (White: 20 [IQR, 11-41]; Black: 35 [IQR, 22-63]; other/unknown: 27.5 [IQR, 17-42]). After adjustment, odds of diagnostic imaging follow-up within 15 days of screening were lower for Black versus White women (odds ratio, 0.59 [95% CI, 0.44 to 0.80]; P < .001). In this diverse cohort, disparities in timely diagnostic follow-up after abnormal breast screening were observed, with Black women waiting 1.75 times as long as White women to obtain a tissue diagnosis. National guidelines for time to diagnostic follow-up may facilitate more timely breast cancer care and potentially affect outcomes.

Predictive Analysis of Breast Cancer from Full-Field Digital Mammography Images using Residual Network

Breast cancer has been a significant contributor to cancer-related mortality, but advancements in early detection through regular mammography and improvements in treatment modalities have contributed to declining mortality rates in several regions. This study presents a novel approach to cancer diagnosis utilizing Full-Field Digital Mammography images through predictive analysis methods. By using predictive analytic techniques and mammography images, this study offers a novel way to cancer detection. The research involves the application of deep learning techniques to extract valuable insights from cancer images captured by mammography devices. The CBIS-DDSM (Curated Breast Imaging Subset of Digital Database for Screening Mammography) dataset including images from patients with varying types and stages of cancer, is collected and pre-processed to ensure uniformity and quality. Relevant features, including color, texture, and shape characteristics, are extracted, and a rigorous feature selection process is employed to identify discriminative markers. The Residual Network (ResNet) model is selected and trained on the dataset, with a focus on classification accuracy and robust predictive performance. Validation metrics, such as accuracy, IoU (Intersection over Union) score, dice score, and ROC (Receiver Operating Characteristic) curve are employed to evaluate the model’s efficiency. After analysis, the proposed method had the best degree of mass lesion detection accuracy, at 99.24%. This research contributes to the advancement of non-invasive and efficient diagnostic tools, potentially enhancing early detection and intervention in cancer patients. The proposed method not only demonstrates promising results in terms of diagnostic accuracy but also emphasizes interpretability, seamless integration into clinical workflows, and adherence to ethical standards.

Reply to “Enhancing breast imaging strategies: The role of ChatGPT in optimizing screening pathways”

Reply to “Enhancing breast imaging strategies: The role of ChatGPT in optimizing screening pathways”

Diagnostic Accuracy of Screening Contrast-enhanced Mammography for Women with Extremely Dense Breasts at Increased Risk of Breast Cancer.

Background Mammogram interpretation is challenging in female patients with extremely dense breasts (Breast Imaging Reporting and Data System [BI-RADS] category D), who have a higher breast cancer risk. Contrast-enhanced mammography (CEM) has recently emerged as a potential alternative; however, data regarding CEM utility in this subpopulation are limited. Purpose To evaluate the diagnostic performance of CEM for breast cancer screening in female patients with extremely dense breasts. Materials and Methods This retrospective single-institution study included consecutive CEM examinations in asymptomatic female patients with extremely dense breasts performed from December 2012 to March 2022. From CEM examinations, low-energy (LE) images were the equivalent of a two-dimensional full-field digital mammogram. Recombined images highlighting areas of contrast enhancement were constructed using a postprocessing algorithm. The sensitivity and specificity of LE images and CEM images (ie, including both LE and recombined images) were calculated and compared using the McNemar test. Results This study included 1299 screening CEM examinations (609 female patients; mean age, 50 years ± 9 [SD]). Sixteen screen-detected cancers were diagnosed, and two interval cancers occured. Five cancers were depicted at LE imaging and an additional 11 cancers were depicted at CEM (incremental cancer detection rate, 8.7 cancers per 1000 examinations). CEM sensitivity was 88.9% (16 of 18; 95% CI: 65.3, 98.6), which was higher than the LE examination sensitivity of 27.8% (five of 18; 95% CI: 9.7, 53.5) (P = .003). However, there was decreased CEM specificity (88.9%; 1108 of 1246; 95% CI: 87.0, 90.6) compared with LE imaging (specificity, 96.2%; 1199 of 1246; 95% CI: 95.0, 97.2) (P < .001). Compared with specificity at baseline, CEM specificity at follow-up improved to 90.7% (705 of 777; 95% CI: 88.5, 92.7; P = .01). Conclusion Compared with LE imaging, CEM showed higher sensitivity but lower specificity in female patients with extremely dense breasts, although specificity improved at follow-up. © RSNA, 2024 See also the editorial by Lobbes in this issue.

Post-operative breast imaging: a management dilemma. Can mammographic artificial intelligence help?

BackgroundImaging of the postoperative breast is a challenging issue for the interpreting physician with many variable findings that may require additional assessment through targeted ultrasound, more mammography views, or other investigations. Artificial intelligence (AI) is a fast-developing field with various applications in the breast imaging including the detection and classification of lesions, the prediction of therapy response, and the prediction of breast cancer risk. This study aimed to identify whether Artificial Intelligence improves the mammographic detection and diagnosis of breast post-operative changes and hence improves follow-up and diagnostic workflow and reduces the need for additional exposure to extra radiation or contrast material doses as in Contrast Enhanced Mammography, and the need for interventional procedures as biopsy.MethodsThis cross-sectional analytic study included 66 female patients following breast-conserving surgeries coming with breast complaints or for follow-up, with mammographically diagnosed changes.ResultsMammography had a sensitivity of 91.7%, a specificity of 94.4%, a positive predictive value (PPV) of 78.6%, a negative predictive value (NPV) of 98.1%, and an accuracy of 93.9%, while the AI method indices were sensitivity 91.7%, specificity 92.6%, (PPV) 73.3%, (NPV) 98%, and accuracy 92.4%. The calculated cut-off point for the quantitative AI (probability of malignancy “POM” score) was 51.5%. There was a statistically significantly higher average in the percentage of POM in malignant cases (76.5 ± 27.3%) compared to benign cases (27.1 ± 19.7%). However, the final indices for the combined use of mammography and (AI) were sensitivity 100%, specificity 88.9%, (PPV) 66.7%, (NPV) 100%, and accuracy 90.9%.ConclusionApplying the AI algorithm on mammograms showed positive impacts on the sensitivity of the post-operative breast assessment, with an excellent reduction of the mammographic missed cancers.

Future of breast imaging

Future of breast imaging