Patients' Perceptions and Attitudes to the Use of Artificial Intelligence in Breast Cancer Diagnosis: A Narrative Review.

Breast cancer remains the most prevalent cancer among women worldwide, necessitating advancements in diagnostic methods. The integration of artificial intelligence (AI) into mammography has shown promise in enhancing diagnostic accuracy. However, understanding patient perspectives, particularly considering the psychological impact of breast cancer diagnoses, is crucial. This narrative review synthesizes literature from 2000 to 2023 to examine breast cancer patients' attitudes towards AI in breast imaging, focusing on trust, acceptance, and demographic influences on these views. Methodologically, we employed a systematic literature search across databases such as PubMed, Embase, Medline, and Scopus, selecting studies that provided insights into patients' perceptions of AI in diagnostics. Our review included a sample of seven key studies after rigorous screening, reflecting varied patient trust and acceptance levels towards AI. Overall, we found a clear preference among patients for AI to augment rather than replace the diagnostic process, emphasizing the necessity of radiologists' expertise in conjunction with AI to enhance decision-making accuracy. This paper highlights the importance of aligning AI implementation in clinical settings with patient needs and expectations, emphasizing the need for human interaction in healthcare. Our findings advocate for a model where AI augments the diagnostic process, underlining the necessity for educational efforts to mitigate concerns and enhance patient trust in AI-enhanced diagnostics.

Non-contrast MRI and post-mastectomy silicone breast implant rupture: preventing false positive diagnoses.

BACKGROUND: Breast implants are not lifelong, with implant rupture being the third leading cause of revisional surgery in augmented women. Noncontrast MRI is a reliable tool to assess implant integrity; however, false positive and false negative diagnoses have been reported due to an incorrect interpretation of MRI signs. This study aims to investigate the incidence of these misleading results, comparing MRI findings with intraoperative surgical observations and exploring signs of nonunivocal interpretation. MATERIALS AND METHODS: Between March 2019 and October 2022, our hospital, a referral center for breast cancer care, conducted 139 breast MRI examinations to evaluate implant integrity. Surgical intervention was deemed necessary for patients diagnosed with suspected or confirmed implant rupture at MRI. Those patients who did not undergo any surgical procedure (63 cases) or had surgery at different institutes (11 cases) were excluded. RESULTS: Among the 65 patients who underwent preoperative MRI and subsequent surgery at our institute, surgical findings confirmed the preoperative MRI diagnosis in 48 women. Notably, 17 women exhibited a discordance between MRI and surgical findings: three false negatives, 11 false positives and three possible ruptures not confirmed. Signs of nonunivocal or misleading interpretation were assessed on a patient-by-patient basis. The importance of obtaining detailed information about a patient's breast implant, including fill materials, number of lumens, manufacturer and shape, proved immensely beneficial for interpreting MRI signs accurately. CONCLUSION: Pre-MRI knowledge of implant details and a meticulous evaluation of non-univocal signs can aid radiologists in accurately assessing implant integrity, reducing the risk of unnecessary revisional surgeries, and potentially averting allegations of medical malpractice.

CDH1 Genotype Exploration in Women With Hereditary Lobular Breast Cancer Phenotype.

Importance: Pathogenic or likely pathogenic (P/LP) germline CDH1 variants are associated with risk for diffuse gastric cancer and lobular breast cancer (LBC) in the so-called hereditary diffuse gastric cancer (HDGC) syndrome. However, in some circumstances, LBC can be the first manifestation of this syndrome in the absence of diffuse gastric cancer manifestation. Objectives: To evaluate the frequency of germline CDH1 variants in women with the hereditary LBC (HLBC) phenotype, somatic CDH1 gene inactivation in germline CDH1 variant carriers' tumor samples, and the association of genetic profiles with clinical-pathological data and survival. Design, Setting, and Participants: This single-center, longitudinal, prospective cohort study was conducted from January 1, 1997, to December 31, 2021, with follow-up until January 31, 2023. Women with LBC seen at the European Institute of Oncology were included. Testing for germline CDH1, BRCA1, and BRCA2 genes was performed. Somatic profiling was assessed for germline CDH1 carriers. Main Outcomes and Measures: Accurate estimates of prevalence of germline CDH1 variants among patients with HLBC and the association of somatic sequence alteration with HLBC syndrome. The Kaplan-Meier method and a multivariable Cox proportional hazards regression model were applied for overall and disease-free survival analysis. Results: Of 5429 cases of primary LBC, familial LBC phenotype accounted for 1867 (34.4%). A total of 394 women with LBC were tested, among whom 15 germline CDH1 variants in 15 unrelated families were identified. Among these variants, 6 (40.0%) were P/LP, with an overall frequency of 1.5% (6 of 394). Of the 6 probands with P/LP CDH1 LBC, 5 (83.3%) had a positive family history of BC and only 1 (16.7%) had sporadic juvenile early-onset LBC. No germline BRCA1 and BRCA2 variants were identified in CDH1 carriers. An inactivating CDH1 mechanism (second hit) was identified in 4 of 6 explored matched tumor samples (66.7%) in P/LP germline carriers. The P/LP CDH1 LBC variant carriers had a significantly lower age at diagnosis compared with the group carrying CDH1 variants of unknown significance or likely benign (42.5 [IQR, 38.3-43.0] vs 51.0 [IQR, 45.0-53.0] years; P = .03). Conclusions and Relevance: In this cohort study, P/LP germline CDH1 variants were identified in individuals not fulfilling the classic clinical criteria for HDGC screening, suggesting that identification of these variants may provide a novel method to test women with LBC with early age at diagnosis and/or positive family history of BC.

Comparison of long-term outcome between clinically high risk lobular versus ductal breast cancer: a propensity score matched study.

Background: Abemaciclib is currently approved for the adjuvant treatment of high-risk, lymph node (LN)-positive, hormone receptor (HR)-positive breast cancer (BC). In a real-world setting the clinicopathologic features of patients potentially eligible for adjuvant abemaciclib remain to be defined. There are conflicting data regarding the biological behavior and long-term outcomes across invasive lobular carcinoma (ILC) and invasive ductal carcinoma (IDC). In our study we retrospectively assessed the real-world data and long-term outcome of selected high-risk features ILC compared to IDC, according to the MonarchE trial inclusion criteria. Methods: We identified 15,071 patients who got surgery at the European Institute of Oncology for a first primary, non-metastatic, HR-positive, HER2-negative BC from 2000 to 2008. 11,981 (79.5%) patients had an IDC and 1524 (10.1%) an ILC. The remaining 1566 patients (10.4%) had either combined ductal and lobular breast cancer or another histological breast cancer subtype. According to the eligibility criteria of the MonarchE study, we identified two high-risk groups, based on high number of positive lymph nodes, large tumor size, or a high cellular proliferation as measured by tumor grade or biomarkers. Patients were matched by propensity score. Findings: A total of 2872 (21.3%) patients were selected as clinically high-risk, including 361/1524 ILC (23.7%) and 2511/11,981 IDC (21%). 322 high-risk ILC were matched with similar high-risk IDC. The median follow-up was 13.2 years for survival. In the matched set, invasive disease-free survival (IDFS) (log-rank P = 0.09) and overall survival (OS) (log-rank P = 0.48) were not statistically significantly different between the two histological groups. For IDC patients, the 5-year and 10-year IDFS rates (95% CI) were 77.7% (72.9-82.2) and 57.3% (51.7-63.1) respectively, compared to the 5-year and 10-year IDFS rates of ILC patients that were 75.5% (70.6-80.2) and 50.7% (45.0-56.6). The 5-year and 10-year distant relapse free survival (DRFS) rates were 80% (75.3-84.2) and 65.3% (59.8-70.7) in IDC cohort, compared to the 5-year and the 10-year DRFS rates of 78.7% (74.0-83.1) and 61.5% (55.9-67.1) in the ILC cohort. Such data match the recent outcomes efficacy results of the MonarchE control arm. More patients in the ILC (n = 17) than in the IDC group (n = 10) developed axillary recurrence. At multivariable analysis, stratified for specific clinical features, age <35 years, pT2-3, axillary involvement with more than 10 positive axillary nodes were found to be predictors of unfavorable IDFS and OS in the overall matched high-risk population. Interpretation: Findings from this matched cohort study reported similar IDFS and DRFS rates for high risk HR positive early BC when compared to the control arm overall IDFS and DRFS rates reported from the MonarchE trial. Our study demonstrated rates of concordant long-term outcome status beyond histologic subtype. These data support an escalation strategy for these two different histological entities when diagnosed with high-risk features. In our dataset approximately 21% rate of high-risk HR positive early BC patients are potentially eligible for adjuvant abemaciclib treatment. Funding: Umberto Veronesi Foundation.

Atypical Ductal Hyperplasia and Lobular In Situ Neoplasm: High-Risk Lesions Challenging Breast Cancer Prevention.

This retrospective study investigates the histopathological outcomes, upgrade rates, and disease-free survival (DFS) of high-risk breast lesions, including atypical ductal hyperplasia (ADH or DIN1b) and lobular in situ neoplasms (LIN), following Vacuum-Assisted Breast Biopsy (VABB) and surgical excision. The study addresses the challenge posed by these lesions due to their association with synchronous or adjacent Breast Cancer (BC) and increased future BC risk. The research, comprising 320 patients who underwent stereotactic VABB, focuses on 246 individuals with a diagnosis of ADH (120) or LIN (126) observed at follow-up. Pathological assessments, categorized by the UK B-coding system, were conducted, and biopsy samples were compared with corresponding excision specimens to determine upgrade rates for in situ or invasive carcinoma. Surgical excision was consistently performed for diagnosed ADH or LIN. Finally, patient follow-ups were assessed and compared between LIN and ADH groups to identify recurrence signs, defined as histologically confirmed breast lesions on either the same or opposite side. The results reveal that 176 (71.5%) patients showed no upgrade post-surgery, with ADH exhibiting a higher upgrade rate to in situ pathology than LIN1 (Atypical Lobular Hyperplasia, ALH)/LIN2 (Low-Grade Lobular in situ Carcinoma, LCIS) (38% vs. 20%, respectively, p-value = 0.002). Considering only patients without upgrade, DFS at 10 years was 77%, 64%, and 72% for ADH, LIN1, and LIN2 patients, respectively (p-value = 0.92). The study underscores the importance of a multidisciplinary approach, recognizing the evolving role of VABB. It emphasizes the need for careful follow-up, particularly for lobular lesions, offering valuable insights for clinicians navigating the complex landscape of high-risk breast lesions. The findings advocate for heightened awareness and vigilance in managing these lesions, contributing to the ongoing refinement of clinical strategies in BC care.

Contrast-enhanced mammography BI-RADS: a case-based approach to radiology reporting.

Contrast-enhanced mammography (CEM) is a relatively recent diagnostic technique increasingly being utilized in clinical practice. Until recently, there was a lack of standardized reporting for CEM findings. However, this has changed with the publication of a supplement in the Breast Imaging Reporting and Data System (BI-RADS). A comprehensive understanding of CEM is essential for further enhancing its role in both screening and managing patients with breast malignancies. CEM can also be beneficial for problem-solving, improving the management of uncertain breast findings. Practitioners in this field should become more cognizant of how and when to employ this technique and interpret the various CEM findings. This paper aims to outline the key findings in the updated version of the BI-RADS specifically dedicated to CEM. Additionally, it will present some clinical cases commonly encountered in clinical practice.Critical relevance statement Standardized reporting and a thorough understanding of CEM findings are pivotal for advancing the role of CEM in screening and managing breast cancer patients. This standardization contributes significantly to integrating CEM as an essential component of daily clinical practice.Key points • A complete knowledge and understanding of the findings outlined in the new BI-RADS CEM are necessary for accurate reporting.• BI-RADS CEM supplement is intuitive and practical to use.• Standardization of the CEM findings enables more accurate patient management.

Evolving paradigms in breast cancer screening: Balancing efficacy, personalization, and equity.

Breast cancer remains a significant global health challenge, with projections indicating a troubling increase in incidence. Breast cancer screening programs have long been hailed as life-saving initiatives, yet their true impact on mortality rates is a subject of ongoing debate. Screening poses the risk of false positives and the detection of indolent tumors, potentially leading to overtreatment. Bias factors, including lead time, length time, and selection biases, further complicate the assessment of screening efficacy. Recent studies suggest that AI-driven image analysis may revolutionize breast cancer screening, maintaining diagnostic accuracy while reducing radiologists' workload. However, the generalizability of these findings to diverse populations is a critical consideration. Personalized screening approaches and equitable access to advanced technologies are essential to mitigate disparities. In conclusion, the breast cancer screening landscape is evolving, emphasizing the need for risk stratification, appropriate imaging modalities, and a personalized approach to reduce overdiagnosis and focus on cancers with the potential to impact lives while prioritizing patient-centered care.

Radiological Features of Male Breast Neoplasms: How to Improve the Management of a Rare Disease.

The primary aim of our study was to assess the main mammographic and ultrasonographic features of invasive male breast malignancies. The secondary aim was to evaluate whether a specific radiological presentation would be associated with a worse receptor profile. Radiological images (mammography and/or ultrasound) of all patients who underwent surgery for male invasive breast cancer in our institution between 2008 and 2023 were retrospectively analyzed by two breast radiologists in consensus. All significant features of radiological presentation known in the literature were re-evaluated. Fifty-six patients were selected. The mean age at surgery of patients was 69 years (range: 35-81); in 82% of cases (46 patients), the histologic outcome was invasive ductal carcinoma. A total of 28 out of 56 (50%) patients had preoperative mammography; in 9/28 cases (32%), we found a mass with microcalcifications on mammography. The mass presented high density in 25 out of 28 patients (89%); the mass showed irregular margins in 15/28 (54%) cases. A total of 46 out of 56 patients had preoperative ultrasounds. The lesion showed a solid mass in 41/46 (89%) cases. In 5/46 patients (11%), the lesion was a mass with a mixed (partly liquid-partly solid) structure. We did not find any statistically significant correlation between major types of radiological presentation and tumor receptor arrangement. Knowledge of the main radiologic presentation patterns of malignant male breast neoplasm can help better manage this type of disease, which is rare but whose incidence is increasing.

Contrast-Enhanced Mammography (CEM) compared to Breast Magnetic Resonance (MRI) in the evaluation of breast lobular neoplasia.

PURPOSE: To compare the diagnostic performance (detection, assessment of correct disease extent and multifocality/centricity) of Contrast-Enhanced Mammography (CEM) Versus Breast Magnetic Resonance (MRI) in the study of lobular neoplasms. METHODS: We retrospectively selected all the patients who underwent surgery for a lobular breast neoplasm, either an in situ or an invasive tumor, and had undergone both breast CEM and MRI examinations during the pre-surgical planning. Wilcoxon Signed Rank test was performed to assess the differences between size measurements using the different methods and the post-surgical pathological measurements, considered the gold standard. The agreement in identifying multifocality/multicentricity among the different methods and the pathology was assessed using the Kappa statistics. RESULTS: We selected 19 patients, of which one presented a bilateral neoplasm. Then, the images of these 19 patients were analyzed, for a total of 52 malignant breast lesions. We found no significant differences between the post-surgical pathological size of the lesions and the calculated size with CEM and MRI (p-value of the difference respectively 0.71 and 0.47). In all 20 cases, neoplasm detection was possible both with CEM and MRI. CEM and MRI showed an excellent ability to identify multifocal and multicentric cases (K statistic equal to 0.93 for both the procedures), while K statistic was 0.11 and 0.59 for FFDM and US, respectively. CONCLUSION: The findings of this study suggest that CEM is a reliable imaging technique in the preoperative setting of patients with lobular neoplasm, with comparable results to breast MRI.

Advances in breast cancer risk modeling: integrating clinics, imaging, pathology and artificial intelligence for personalized risk assessment.

Breast cancer risk models represent the likelihood of developing breast cancer based on risk factors. They enable personalized interventions to improve screening programs. Radiologists identify mammographic density as a significant risk factor and test new imaging techniques. Pathologists provide data for risk assessment. Clinicians conduct individual risk assessments and adopt prevention strategies for high-risk subjects. Tumor genetic testing guides personalized screening and treatment decisions. Artificial intelligence in mammography integrates imaging, clinical, genetic and pathological data to develop risk models. Emerging imaging technologies, genetic testing and molecular profiling improve risk model accuracy. The complexity of the disease, limited data availability and model inputs are discussed. A multidisciplinary approach is essential for earlier detection and improved outcomes.

Updates on Breast Cancer.

This collection of 18 articles, comprising 12 original studies, 1 systematic review, and 5 reviews, is a collaborative effort by distinguished experts in breast cancer research, and it has been edited by Dr [...].

A Pictorial Exploration of Mammary Paget Disease: Insights and Perspectives.

Mammary Paget disease (MPD) is a rare condition primarily affecting adult women, characterized by unilateral skin changes in the nipple-areolar complex (NAC) and frequently associated with underlying breast carcinoma. Histologically, MPD is identified by large intraepidermal epithelial cells (Paget cells) with distinct characteristics. Immunohistochemical profiles aid in distinguishing MPD from other skin conditions. Clinical evaluation and imaging techniques, including magnetic resonance imaging (MRI), are recommended if MPD is suspected, although definitive diagnosis always requires histological examination. This review delves into the historical context, epidemiology, pathogenesis, clinical manifestations, and diagnosis of MPD, emphasizing the need for early detection. The classification of MPD based on pathogenesis is explored, shedding light on its varied presentations. Treatment options, including mastectomy and breast-conserving surgery, are discussed with clear guidelines for different scenarios. Adjuvant therapies are considered, particularly in cases with underlying breast cancer. Prognostic factors are outlined, underlining the importance of early intervention. Looking to the future, emerging techniques, like liquid biopsy, new immunohistochemical and molecular markers, and artificial intelligence-based image analysis, hold the potential to transform MPD diagnosis and treatment. These innovations offer hope for early detection and improved patient care, though validation through large-scale clinical trials is needed.

Deep learning performance for detection and classification of microcalcifications on mammography.

BACKGROUND: Breast cancer screening through mammography is crucial for early detection, yet the demand for mammography services surpasses the capacity of radiologists. Artificial intelligence (AI) can assist in evaluating microcalcifications on mammography. We developed and tested an AI model for localizing and characterizing microcalcifications. METHODS: Three expert radiologists annotated a dataset of mammograms using histology-based ground truth. The dataset was partitioned for training, validation, and testing. Three neural networks (AlexNet, ResNet18, and ResNet34) were trained and evaluated using specific metrics including receiver operating characteristics area under the curve (AUC), sensitivity, and specificity. The reported metrics were computed on the test set (10% of the whole dataset). RESULTS: The dataset included 1,000 patients aged 21-73 years and 1,986 mammograms (180 density A, 220 density B, 380 density C, and 220 density D), with 389 malignant and 611 benign groups of microcalcifications. AlexNet achieved the best performance with 0.98 sensitivity, 0.89 specificity of, and 0.98 AUC for microcalcifications detection and 0.85 sensitivity, 0.89 specificity, and 0.94 AUC of for microcalcifications classification. For microcalcifications detection, ResNet18 and ResNet34 achieved 0.96 and 0.97 sensitivity, 0.91 and 0.90 specificity and 0.98 and 0.98 AUC, retrospectively. For microcalcifications classification, ResNet18 and ResNet34 exhibited 0.75 and 0.84 sensitivity, 0.85 and 0.84 specificity, and 0.88 and 0.92 AUC, respectively. CONCLUSIONS: The developed AI models accurately detect and characterize microcalcifications on mammography. RELEVANCE STATEMENT: AI-based systems have the potential to assist radiologists in interpreting microcalcifications on mammograms. The study highlights the importance of developing reliable deep learning models possibly applied to breast cancer screening. KEY POINTS: • A novel AI tool was developed and tested to aid radiologists in the interpretation of mammography by accurately detecting and characterizing microcalcifications. • Three neural networks (AlexNet, ResNet18, and ResNet34) were trained, validated, and tested using an annotated dataset of 1,000 patients and 1,986 mammograms. • The AI tool demonstrated high accuracy in detecting/localizing and characterizing microcalcifications on mammography, highlighting the potential of AI-based systems to assist radiologists in the interpretation of mammograms.

Future Directions in the Assessment of Axillary Lymph Nodes in Patients with Breast Cancer.

Background and Objectives: Breast cancer (BC) is a leading cause of morbidity and mortality worldwide, and accurate assessment of axillary lymph nodes (ALNs) is crucial for patient management and outcomes. We aim to summarize the current state of ALN assessment techniques in BC and provide insights into future directions. Materials and Methods: This review discusses various imaging techniques used for ALN evaluation, including ultrasound, computed tomography, magnetic resonance imaging, and positron emission tomography. It highlights advancements in these techniques and their potential to improve diagnostic accuracy. The review also examines landmark clinical trials that have influenced axillary management, such as the Z0011 trial and the IBCSG 23-01 trial. The role of artificial intelligence (AI), specifically deep learning algorithms, in improving ALN assessment is examined. Results: The review outlines the key findings of these trials, which demonstrated the feasibility of avoiding axillary lymph node dissection (ALND) in certain patient populations with low sentinel lymph node (SLN) burden. It also discusses ongoing trials, including the SOUND trial, which investigates the use of axillary ultrasound to identify patients who can safely avoid sentinel lymph node biopsy (SLNB). Furthermore, the potential of emerging techniques and the integration of AI in enhancing ALN assessment accuracy are presented. Conclusions: The review concludes that advancements in ALN assessment techniques have the potential to improve patient outcomes by reducing surgical complications while maintaining accurate disease staging. However, challenges such as standardization of imaging protocols and interpretation criteria need to be addressed. Future research should focus on large-scale clinical trials to validate emerging techniques and establish their efficacy and cost-effectiveness. Over-all, this review provides valuable insights into the current status and future directions of ALN assessment in BC, highlighting opportunities for improving patient care.

Advancements in Standardizing Radiological Reports: A Comprehensive Review.

Standardized radiological reports stimulate debate in the medical imaging field. This review paper explores the advantages and challenges of standardized reporting. Standardized reporting can offer improved clarity and efficiency of communication among radiologists and the multidisciplinary team. However, challenges include limited flexibility, initially increased time and effort, and potential user experience issues. The efforts toward standardization are examined, encompassing the establishment of reporting templates, use of common imaging lexicons, and integration of clinical decision support tools. Recent technological advancements, including multimedia-enhanced reporting and AI-driven solutions, are discussed for their potential to improve the standardization process. Organizations such as the ACR, ESUR, RSNA, and ESR have developed standardized reporting systems, templates, and platforms to promote uniformity and collaboration. However, challenges remain in terms of workflow adjustments, language and format variability, and the need for validation. The review concludes by presenting a set of ten essential rules for creating standardized radiology reports, emphasizing clarity, consistency, and adherence to structured formats.

Inter-reader agreement of breast magnetic resonance imaging and contrast-enhanced mammography in breast cancer diagnosis: a multi-reader retrospective study.

OBJECTIVE: Breast magnetic resonance imaging (MRI) and contrast-enhanced mammography (CEM) are nowadays used in breast imaging but studies about their inter-reader agreement are lacking. Therefore, we compared the inter-reader agreement of CEM and MRI in breast cancer diagnosis in the same patients. METHODS: Breast MRI and CEM exams performed in a single center (09/2020-09/2021) for an IRB-approved study were retrospectively and independently evaluated by four radiologists of two different centers with different levels of experience who were blinded to the clinical and other imaging data. The reference standard was the histological diagnosis or at least 1-year negative imaging follow-up. Inter-reader agreement was examined using Cohen's and Fleiss' kappa (κ) statistics and compared with the Wald test. RESULTS: Of the 750 patients, 395 met inclusion criteria (44.5 ± 14 years old), with 752 breasts available for CEM and MRI. Overall agreement was moderate (κ = 0.60) for MRI and substantial (κ = 0.74) for CEM. For expert readers, the agreement was substantial (κ = 0.77) for MRI and almost perfect (κ = 0.82) for CEM; for non-expert readers was fair (κ = 0.39); and for MRI and moderate (κ = 0.57) for CEM. Pairwise agreement between expert readers and non-expert readers was moderate (κ = 0.50) for breast MRI and substantial (κ = 0.74) for CEM and it showed a statistically superior agreement of the expert over the non-expert readers only for MRI (p = 0.011) and not for CEM (p = 0.062). CONCLUSIONS: The agreement of CEM was superior to that of MRI (p = 0.012), including for both expert (p = 0.031) and non-expert readers (p = 0.005).

History of Mammography: Analysis of Breast Imaging Diagnostic Achievements over the Last Century.

Breast cancer is the most common forms of cancer and a leading cause of mortality in women. Early and correct diagnosis is, therefore, essential to save lives. The development of diagnostic imaging applied to the breast has been impressive in recent years and the most used diagnostic test in the world is mammography, a low-dose X-ray technique used for imaging the breast. In the first half of the 20th century, the diagnosis was in practice only clinical, with consequent diagnostic delay and an unfavorable prognosis in the short term. The rise of organized mammography screening has led to a remarkable reduction in mortality through the early detection of breast malignancies. This historical review aims to offer a complete panorama of the development of mammography and breast imaging during the last century. Through this study, we want to understand the foundations of the pillar of radiology applied to the breast through to the most modern applications such as contrast-enhanced mammography (CEM), artificial intelligence, and radiomics. Understanding the history of the development of diagnostic imaging applied to the breast can help us understand how to better direct our efforts toward an increasingly personalized and effective diagnostic approach. The ultimate goal of imaging applied to the detection of breast malignancies should be to reduce mortality from this type of disease as much as possible. With this paper, we want to provide detailed documentation of the main steps in the evolution of breast imaging for the diagnosis of breast neoplasms; we also want to open up new scenarios where the possible current and future applications of imaging are aimed at being more precise and personalized.

An Unenhanced Breast MRI Protocol Based on Diffusion-Weighted Imaging: A Retrospective Single-Center Study on High-Risk Population for Breast Cancer.

PURPOSE: This study aimed to investigate the use of contrast-free magnetic resonance imaging (MRI) as an innovative screening method for detecting breast cancer in high-risk asymptomatic women. Specifically, the researchers evaluated the diagnostic performance of diffusion-weighted imaging (DWI) in this population. METHODS: MR images from asymptomatic women, carriers of a germline mutation in either the BRCA1 or BRCA2 gene, collected in a single center from January 2019 to December 2021 were retrospectively evaluated. A radiologist with experience in breast imaging (R1) and a radiology resident (R2) independently evaluated DWI/ADC maps and, in case of doubts, T2-WI. The standard of reference was the pathological diagnosis through biopsy or surgery, or ≥1 year of clinical and radiological follow-up. Diagnostic performances were calculated for both readers with a 95% confidence interval (CI). The agreement was assessed using Cohen's kappa (κ) statistics. RESULTS: Out of 313 women, 145 women were included (49.5 ± 12 years), totaling 344 breast MRIs with DWI/ADC maps. The per-exam cancer prevalence was 11/344 (3.2%). The sensitivity was 8/11 (73%; 95% CI: 46-99%) for R1 and 7/11 (64%; 95% CI: 35-92%) for R2. The specificity was 301/333 (90%; 95% CI: 87-94%) for both readers. The diagnostic accuracy was 90% for both readers. R1 recalled 40/344 exams (11.6%) and R2 recalled 39/344 exams (11.3%). Inter-reader reproducibility between readers was in moderate agreement (κ = 0.43). CONCLUSIONS: In female carriers of a BRCA1/2 mutation, breast DWI supplemented with T2-WI allowed breast cancer detection with high sensitivity and specificity by a radiologist with extensive experience in breast imaging, which is comparable to other screening tests. The findings suggest that DWI and T2-WI have the potential to serve as a stand-alone method for unenhanced breast MRI screening in a selected population, opening up new perspectives for prospective trials.