Breast MRI Research Articles

Flamingo Search Sailfish Optimizer Based SqueezeNet for Detection of Breast Cancer Using MRI Images

Breast cancer with increased risk in women is identified with Breast Magnetic Resonance Imaging (Breast MRI) and this helps in evaluating treatment therapies. Breast MRI is time time-consuming process that involves the assessment of current imaging. This research work depends on the detection of breast cancer at the earlier stages. Among various cancers, breast cancer in women occurs in larger accounts for almost 30% of estimated cancer cases. In this research, many steps are followed for breast cancer detection like pre-processing, segmentation, augmentation, extraction of features, and cancer detection. Here, the median filter is utilized for pre-processing, as well as segmentation is followed after pre-processing, which is done by Psi-Net. Moreover, the process of augmentation like shearing, translation, and cropping are followed after segmentation. Also, the segmented image tends to process feature extraction, where features like shape features, Completed Local Binary Pattern (CLBP), Pyramid Histogram of Oriented Gradients (PHOG), and statistical features are extracted. Finally, breast cancer is detected using the DL model, SqueezeNet. Here, the newly devised Flamingo Search SailFish Optimizer (FSSFO) is used in training Psi-Net as well as SqueezeNet. Furthermore, FSSFO is the combination of both the Flamingo Search Algorithm (FSA) and SailFish Optimizer (SFO).

Discrimination Between Benign and Malignant Lesions With Restriction Spectrum Imaging MRI in an Enriched Breast Cancer Screening Cohort.

Breast cancer screening with dynamic contrast-enhanced MRI (DCE-MRI) is recommended for high-risk women but has limitations, including variable specificity and difficulty in distinguishing cancerous (CL) and high-risk benign lesions (HRBL) from average-risk benign lesions (ARBL). Complementary non-invasive imaging techniques would be useful to improve specificity. To evaluate the performance of a previously-developed breast-specific diffusion-weighted MRI (DW-MRI) model (BS-RSI3C) to improve discrimination between CL, HRBL, and ARBL in an enriched screening population. Prospective. Exactly 187 women, either with mammography screening recommending additional imaging (N = 49) or high-risk individuals undergoing routine breast MRI (N = 138), before the biopsy. Multishell DW-MRI echo planar imaging sequence with a reduced field of view at 3.0 T. A total of 72 women had at least one biopsied lesion, with 89 lesions categorized into ARBL, HRBL, CL, and combined CLs and HRBLs (CHRLs). DW-MRI data were processed to produce apparent diffusion coefficient (ADC) maps, and estimate signal contributions (C1, C2, and C3-restricted, hindered, and free diffusion, respectively) from the BS-RSI3C model. Lesion regions of interest (ROIs) were delineated on DW images based on suspicious DCE-MRI findings by two radiologists; control ROIs were drawn in the contralateral breast. One-way ANOVA and two-sided t-tests were used to assess differences in signal contributions and ADC values among groups. P-values were adjusted using the Bonferroni method for multiple testing, P = 0.05 was used for the significance level. Receiver operating characteristics (ROC) curves and intra-class correlations (ICC) were also evaluated. C1, √C1C2, and were significantly different in HRBLs compared with ARBLs (P-values < 0.05). The had the highest AUC (0.821) in differentiating CHRLs from ARBLs, performing better than ADC (0.696), especially in non-mass enhancement (0.776 vs. 0.517). This study demonstrated the BS-RSI3C could differentiate HRBLs from ARBLs in a screening population, and separate CHRLs from ARBLs better than ADC. 2.

Initial Attempted Contrast-Enhanced Mammography-Guided Biopsy for Suspicious Breast MRI Findings: A Single Institution's Experience.

Initial Attempted Contrast-Enhanced Mammography-Guided Biopsy for Suspicious Breast MRI Findings: A Single Institution's Experience.

Prediction of early clinical response to neoadjuvant chemotherapy in Triple-negative breast cancer: Incorporating Radiomics through breast MRI

This study assessed pretreatment breast MRI coupled with machine learning for predicting early clinical responses to neoadjuvant chemotherapy (NAC) in triple-negative breast cancer (TNBC), focusing on identifying non-responders. A retrospective analysis of 135 TNBC patients (107 responders, 28 non-responders) treated with NAC from January 2015 to October 2022 was conducted. Non-responders were defined according to RECIST guidelines. Data included clinicopathologic factors and clinical MRI findings, with radiomics features from contrast-enhanced T1-weighted images, to train a stacking ensemble of 13 machine learning models. For subgroup analysis, propensity score matching was conducted to adjust for clinical disparities in NAC response. The efficacy of the models was evaluated using the area under the receiver-operating-characteristic curve (AUROC) before and after matching. The model combining clinicopathologic factors and clinical MRI findings achieved an AUROC of 0.752 (95% CI 0.644–0.860) for predicting non-responders, while radiomics-based models showed 0.749 (95% CI 0.614–0.884). An integrated model of radiomics, clinicopathologic factors, and clinical MRI findings reached an AUROC of 0.802 (95% CI 0.699–0.905). After propensity score matching, the hierarchical order of key radiomics features remained consistent. Our study demonstrated the potential of using machine learning models based on pretreatment MRI to non-invasively predict TNBC non-responders to NAC.

Evaluation of apparent diffusion coefficient (ADC) with regards to reproducibility and diagnostic accuracy as well as possible significance of pre - and post - contrast acquisition and employment of different b values

PurposeOngoing efforts are focusing on optimizing diffusion-weighted imaging (DWI) as an essential part of breast MRI protocol. Our study aimed to evaluate the effect of contrast media (CM) on the apparent diffusion coefficients (ADC) acquired following current recommendations. Patient and Methods: Patients who underwent 3 T breast MRI with a histologically verified suspicious lesion were included in this IRB-approved, single-center, cross-sectional retrospective study. Breast MRI protocol included a DWI sequence with multiple b-values, which was acquired before and after CM administration. ADC maps were calculated by in-line monoexponential fitting with b-values 0 /800 and 50/800. Two independent readers (R1, R2) reviewed the images in separate sessions for b values 0/800 and 50/800, pre- and post-CM. Bland Altmann plots as well as intraclass correlation coefficients (ICCs) for inter-reader agreement, different b-values, and pre- and post-CM were calculated. Diagnostic accuracy was evaluated and compared by calculating the area under the receiver operating characteristics curve (AUC). Results: 91 lesions in 89 patients were examined (mean age 50.7 years, standard deviation 13.9). ADC values were significantly (P<0.05) lower post-CM (mean ranging from 1.28 x10−3 mm2/s to 1.30 x10−3 mm2/s) compared to pre-CM (mean ranging from 1.32 x10−3 mm2/s to 1.37 x10−3 mm2/s) for both b-values combinations (0/800 and 50/800 s/mm2). We found an almost perfect inter-reader agreement pre-/post-CM with b values 0/800 and 50/800 (ICC ranging from 0.853 to 0.939). Bland Altman plot demonstrated no systematic difference between readers. ROC analysis revealed good diagnostic performance without significant differences (P>0.05) between b values 0/800 and 50/800 s/mm2 as well as pre- and post-CM with areas under the ROC curve between 0.834 and 0.877. Conclusion: ADC values are slightly lower when acquiring b values 0/800 and post-CM. This effect does not reduce the diagnostic performance but may be relevant in case of definite cut-offs in medical decision making.

Prediction of axillary lymph node metastasis using a magnetic resonance imaging radiomics model of invasive breast cancer primary tumor

BackgroundThis study investigated the clinical value of breast magnetic resonance imaging (MRI) radiomics for predicting axillary lymph node metastasis (ALNM) and to compare the discriminative abilities of different combinations of MRI sequences.MethodsThis study included 141 patients diagnosed with invasive breast cancer from two centers (center 1: n = 101, center 2: n = 40). Patients from center 1 were randomly divided into training set and test set 1. Patients from center 2 were assigned to the test set 2. All participants underwent preoperative MRI, and four distinct MRI sequences were obtained. The volume of interest (VOI) of the breast tumor was delineated on the dynamic contrast-enhanced (DCE) postcontrast phase 2 sequence, and the VOIs of other sequences were adjusted when required. Subsequently, radiomics features were extracted from the VOIs using an open-source package. Both single- and multisequence radiomics models were constructed using the logistic regression method in the training set. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and precision of the radiomics model for the test set 1 and test set 2 were calculated. Finally, the diagnostic performance of each model was compared with the diagnostic level of junior and senior radiologists.ResultsThe single-sequence ALNM classifier derived from DCE postcontrast phase 1 had the best performance for both test set 1 (AUC = 0.891) and test set 2 (AUC = 0.619). The best-performing multisequence ALNM classifiers for both test set 1 (AUC = 0.910) and test set 2 (AUC = 0.717) were generated from DCE postcontrast phase 1, T2-weighted imaging, and diffusion-weighted imaging single-sequence ALNM classifiers. Both had a higher diagnostic level than the junior and senior radiologists.ConclusionsThe combination of DCE postcontrast phase 1, T2-weighted imaging, and diffusion-weighted imaging radiomics features had the best performance in predicting ALNM from breast cancer. Our study presents a well-performing and noninvasive tool for ALNM prediction in patients with breast cancer.

Dedicated Breast CT: Getting Ready for Prime Time.

Dedicated breast CT is an imaging modality that provides true 3D imaging of the breast with many advantages over current conventional breast imaging modalities. The addition of intravascular contrast increases the sensitivity of breast CT substantially. As such, there are immediate potential applications in the clinical workflow. These include using breast CT to replace much of the traditional diagnostic workup when faced with indeterminate breast lesions. Contrast-enhanced breast CT may be appropriate as a supplemental screening tool for women at high risk of breast cancer, similar to breast MRI. In addition, emerging studies are demonstrating the utility of breast CT in neoadjuvant chemotherapy tumor response monitoring as well as planning for surgical treatment options. While short exam times and fully 3D imaging in a noncompressed position are advantages of this modality, limited coverage of chest wall/axilla due to prone positioning and use of ionizing radiation are drawbacks. To date, several studies have reported on the performance characteristics of this promising modality.

Beyond the Needle: Understanding Tissue Marker Migration in Breast MRI-Guided Biopsies.

To evaluate the frequency and factors associated with clip migration in MRI-guided breast biopsies. This study was approved by our Institutional Review Board and was compliant with HIPAA. We retrospectively evaluated all MRI-guided biopsies performed between January 2013 and December 2020 in our institution for clip migration. Only patients with follow-up breast MRI showing the clip were included in the study. Migration was defined as movement of the clip of 10mm or more from the target lesion. Migration frequency and directions were recorded. Factors associated with clip migration were analyzed using statistical tests as appropriate. A total of 291 biopsies in 268 women were included in the study with 31 migration events recorded (11%; 95% CI, 7%-15%). All migrations occurred along the biopsy tract; 97% (30/31) of them displaced distal to the needle entry site. More than 50% regional fat (around the target lesion) was the strongest factor associated with migration, seen in 21/141 women (15%), compared to 10/150 (7%) with 50% or less local fat (P = .023). Global fatty breast was more loosely associated with migration, showing borderline significance (P = .06). Other factors did not correlate with clip migration, including lesion size, depth, or location; pathology result; breast thickness; or biopsy approach. Although clip migration after breast MRI-guided biopsy is an uncommon event, it occurs more often when the target lesion is surrounded by fat, with the clip usually displaced away from the needle entry site.

Unusual Pattern of Spread of High-Grade Serous Fallopian Tubal Carcinoma in a Woman with BRCA1 Gene Mutation

A 40-year-old woman presented with chronic watery vaginal discharge for one-month and right pelvic pain radiating to the right flank for 2 weeks. Physical and pelvic examination revealed a right pelvic mass. Computerized tomography and magnetic resonance of whole abdomen revealed a 6-cm of heterogeneous mass at the right adnexa and a larger mass of 8-cm with internal cystic portions compressing on the inferior vena cava. Her serum cancer antigen (CA) 125 elevated to 540 U/ml. Surgical intervention revealed a right fallopian tube mass with an intact serosal surface, several enlarged pelvic and para-aortic nodes, and a bulky precaval node. No gross peritoneal nor other organ invasion was found. Complete surgical staging was performed by gynecologic oncologists and a surgeon, resulting in optimal surgery. Pathology revealed high-grade serous carcinoma of the right fallopian tube with metastasis to all resected nodes and a positive peritoneal cytology. Subsequent blood testing showed BReast CAncer (BRCA) 1 gene mutation. Adjuvant therapy with paclitaxel/carboplatin/bevacizumab was given for six cycles. Maintenance therapy with bevacizumab/olaparib, and periodic surveillance for other cancers, including breast magnetic resonance imaging were planned. This case presented an unusual pattern fallopian tubal cancer spread to a large precaval lymph node which was bulkier than the primary tumor. A thorough pre-operative evaluation and a surgical team specialized in cancer surgery are crucial for successful surgical management. Appropriate adjuvant treatment and follow-up for a woman with BRCA mutation were also to be emphasized.

Evaluation of guided reporting: quality and reading time of automatically generated radiology report in breast magnetic resonance imaging using a dedicated software solution.

Unstructured, free-text dictation (FT), the current standard in breast magnetic resonance imaging (MRI) reporting, is considered time-consuming and prone to error. The purpose of this study is to assess the usability and performance of a novel, software-based guided reporting (GR) strategy in breast MRI. Eighty examinations previously evaluated for a clinical indication (e.g., mass and focus/non-mass enhancement) with FT were reevaluated by three specialized radiologists using GR. Each radiologist had a different number of cases (R1, n = 24; R2, n = 20; R3, n = 36). Usability was assessed by subjective feedback, and quality was assessed by comparing the completeness of automatically generated GR reports with that of their FT counterparts. Errors in GR were categorized and analyzed for debugging with a final software version. Combined reading and reporting times and learning curves were analyzed. Usability was rated high by all readers. No non-sense, omission/commission, or translational errors were detected with the GR method. Spelling and grammar errors were observed in 3/80 patient reports (3.8%) with GR (exclusively in the discussion section) and in 36/80 patient reports (45%) with FT. Between FT and GR, 41 patient reports revealed no content differences, 33 revealed minor differences, and 6 revealed major differences that resulted in changes in treatment. The errors in all patient reports with major content differences were categorized as content omission errors caused by improper software operation (n = 2) or by missing content in software v. 0.8 displayable with v. 1.7 (n = 4). The mean combined reading and reporting time was 576 s (standard deviation: 327 s; min: 155 s; max: 1,517 s). The mean times for each reader were 485, 557, and 754 s, and the respective learning curves evaluated by regression models revealed statistically significant slopes (P = 0.002; P = 0.0002; P < 0.0001). Overall times were shorter compared with external references that used FT. The mean combined reading and reporting time of MRI examinations using FT was 1,043 s and decreased by 44.8% with GR. GR allows for complete reporting with minimized error rates and reduced combined reading and reporting times. The streamlining of the process (evidenced by lower reading times) for the readers in this study proves that GR can be learned quickly. Reducing reporting errors leads to fewer therapeutic faults and lawsuits against radiologists. It is known that delays in radiology reporting hinder early treatment and lead to poorer patient outcomes. While the number of scans and images per examination is continuously rising, staff shortages create a bottleneck in radiology departments. The IT-based GR method can be a major boon, improving radiologist efficiency, report quality, and the quality of simultaneously generated data.

Assessment of the contribution of the ADC value to the Kaiser score in the differential diagnosis of breast lesions with non-mass enhancement morphology on MRI

PurposeTo investigate the effectiveness of diffusion-weighted imaging (DWI) as a supplementary tool to the Kaiser score (KS) in diagnosing breast cancer in non-mass enhancement (NME) lesions using breast magnetic resonance imaging (MRI). MethodsThis single-center, retrospective study analyzed 360 cases with NME on MRI images. Two breast radiologists independently evaluated each lesion using the Kaiser score (KS) and apparent diffusion coefficient (ADC) values, without knowledge of the pathological outcomes. NME lesions with a KS above 4 and an ADC value below 1.3 × 10-3mm2/s were classified as malignant. Inter-rater reliability was determined using Cohen’s Kappa (κ) statistics. The diagnostic performance of KS, DWI, and their combination was assessed by calculating sensitivity, specificity, and the area under the curve (AUC), and the results were compared across the benign and malignant groups. ResultsThe diagnostic performance of KS surpassed that of DWI in predicting the malignancy of NMEs (p = 0.003). The sensitivity of KS alone was 93 %; however, when ADC data was incorporated, the sensitivity decreased to 86 %, with no significant difference observed (p = 0.060). The specificity of the combined KS and ADC (94 %) was significantly higher than that of KS alone (89 %) and DWI alone (73 %) (p < 0.001). ConclusionOur findings indicated that although the combination of KS and ADC increased specificity and reduced unnecessary biopsies, the resulting decrease in sensitivity was unacceptable. Therefore, KS alone is superior to the KS-ADC combination in detecting malignancy in NME lesions.

Presurgical Upgrade Prediction of DCIS to Invasive Ductal Carcinoma Using Time-dependent Deep Learning Models with DCE MRI.

Purpose To determine whether time-dependent deep learning models can outperform single time point models in predicting preoperative upgrade of ductal carcinoma in situ (DCIS) to invasive malignancy at dynamic contrast-enhanced (DCE) breast MRI without a lesion segmentation prerequisite. Materials and Methods In this exploratory study, 154 cases of biopsy-proven DCIS (25 upgraded at surgery and 129 not upgraded) were selected consecutively from a retrospective cohort of preoperative DCE MRI in women with a mean age of 59 years at time of diagnosis from 2012 to 2022. Binary classification was implemented with convolutional neural network (CNN)-long short-term memory (LSTM) architectures benchmarked against traditional CNNs without manual segmentation of the lesions. Combinatorial performance analysis of ResNet50 versus VGG16-based models was performed with each contrast phase. Binary classification area under the receiver operating characteristic curve (AUC) was reported. Results VGG16-based models consistently provided better holdout test AUCs than did ResNet50 in CNN and CNN-LSTM studies (multiphase test AUC, 0.67 vs 0.59, respectively, for CNN models [P = .04] and 0.73 vs 0.62 for CNN-LSTM models [P = .008]). The time-dependent model (CNN-LSTM) provided a better multiphase test AUC over single time point (CNN) models (0.73 vs 0.67; P = .04). Conclusion Compared with single time point architectures, sequential deep learning algorithms using preoperative DCE MRI improved prediction of DCIS lesions upgraded to invasive malignancy without the need for lesion segmentation. Keywords: MRI, Dynamic Contrast-enhanced, Breast, Convolutional Neural Network (CNN) Supplemental material is available for this article. © RSNA, 2024.

Maximizing Breast Cancer Detection Through Screening: A Comparative Analysis of Imaging-Based Approaches

Introduction/BackgroundThis study estimates the percentage of detectable breast cancers in the screening population that could be found with primary and supplemental screening, and provides cost estimates for population wide supplemental screening in the U.S. Materials and MethodsPublished estimates on cancer detection rates of 2D mammography, tomosynthesis (DBT), whole breast ultrasound (US), molecular breast imaging (MBI), contrast-enhanced mammography (CEM), and MRI, the number of mammograms conducted in the United States in 2023, and the proportion of dense breast tissue, were utilized. The maximum number of detectable cancers was projected from incremental cancer detection rates of the most sensitive supplemental screening method. The proportion of cancers detectable for each modality was calculated. In 2023, Medicare reimbursement rates were used to estimate supplemental screening costs. ResultsOut of 469,437 detectable cancers, 2D mammography could detect 190,531 (41%), leaving 278,906 undetected. Adding supplemental screening could detect a combined 220,165 cancers (47%) with DBT, 237,596 (51%) with US, 331,727 (71%) with MBI, 377,049 (80%) with CEM and 469,437 (100%) with MRI. The imaging cost in US dollars to provide supplemental screening to all individuals with dense breasts in 2023 was $933M for tomosynthesis, $1.84B for US, $3.87B for CEM, $4.16B for MBI, and $6.36B for MRI. ConclusionThe study highlights potential benefits from supplemental breast cancer screening, suggesting the combination of mammography and breast MRI offers the most effective detection method though at the highest imaging cost. These findings provide valuable insights to guide future research and inform decision-making in supplemental breast cancer screening strategies.

Preoperative breast MR imaging influences surgical management in patients with invasive lobular carcinoma.

The purpose of the study is to assess the role of preoperative magnetic resonance (MR) imaging on the surgical management of invasive lobular carcinoma (ILC) and to evaluate whether breast density and background parenchymal enhancement (BPE) influence surgical treatment. This retrospective study was conducted on 56 patients who were diagnosed with ILC between 2014 and 2020. All patients had mammogram and ultrasound. Preoperative MRI was available in 34 patients. Age, menopausal status, breast density, BPE, multifocality/multicentricity and surgical treatment were collected. Mean pathological tumour size was 36.4 mm (range 5-140 mm). Dense breasts had larger tumours compared to non-dense breasts (P = 0.072). Of the 34 patients with MRI, 6 opted for mastectomy. Of the remaining 28 cases, MRI findings upgraded surgery to mastectomy in 54% (15/28) because mammogram/ultrasound underestimated tumour extent in 25% (7/28), or multifocal/multicentric disease was identified in 29% (8/28). Tumour size was underestimated by MRI in 7% (2/28). In the non-MRI subgroup, 64% (14/22) of patients underwent breast-conserving surgery, but 29% of them (4/14) required a second-stage mastectomy due to extensive margin involvement. There was no difference in mastectomy rate between patients with MRI (62%) and without MRI (55%) (P = 0.061). Tumour size correlation between MRI and histopathology demonstrated an excellent intraclass correlation coefficient (P < 0.001). Surgical treatment recommendation was not significantly impacted by breast density or BPE. Breast MRI improves surgical management of patients with ILC in providing additional diagnostic information often missed with standard imaging modalities, and without increasing mastectomy rate. Surgical treatment is not impacted by breast density or BPE.

The potential role of breast MRI in evaluation of triple-negative breast cancer and fibroadenoma of less than 3 cm.

The majority of small-sized (<3 cm) triple-negative breast cancer (TNBC) exhibit smooth margins upon palpation and are often oval or rounded masses. Distinguishing these masses preoperatively from fibroadenomas (FAs) would be very meaningful for clinical practice. The aim of our study was to evaluate the magnetic resonance imaging (MRI) appearance of TNBC and differentiate it from FAs. In this retrospective single-center study, we included 37 patients with TNBCs and 36 patients with FAs who underwent breast MRI. We employed the χ2 test and t-test to compare the differences in morphological features, dynamic contrast-enhanced MRI (DCE-MRI) parameters, and apparent diffusion coefficient (ADC) values between the two groups. Additionally, we constructed non-parametric receiver operating characteristic (ROC) curves using ADC values, with pathological results serving as the gold standard. A total of 37 TNBC lesions and 39 FA lesions were included in the final analysis. TNBCs exhibited more frequent irregular shape, irregular margins, peritumoral edema, fast enhancement in the initial phase, rim enhancement, and time-signal intensity curve (TIC) type III compared to FAs (all P<0.05). Conversely, low-signal segregation in T2-weighted imaging (T2WI) and TIC type I were commonly found in FAs. The mean ADC value of TNBCs was significantly lower than that of FAs [(1.104±0.13)×10-3 vs. (1.613±0.16)×10-3 mm2/s, P<0.05]. The cutoff ADC for differentiating TNBCs from FAs was 1.239×10-3 mm2/s, yielding an area under the curve (AUC) of 0.997, a sensitivity of 94.6%, and a specificity of 100%. The morphological presentation of MRI, internal enhancement features of the mass, TIC curves, and ADC values provide valuable differential diagnostic information for TNBC and FA masses with a maximum diameter of less than 3 cm.

Imaging evaluation focused on microstructural tissue changes using tensor-valued diffusion encoding in breast cancers after neoadjuvant chemotherapy: is it a promising way forward?

Single diffusion encoding is a widely used, noninvasive technique for probing the tissue microstructure in breast tumors. However, it does not provide detailed information about the microenvironmental complexity. This study investigated the clinical utility of tensor-valued diffusion encoding for evaluating microstructural changes in breast cancer after neoadjuvant chemotherapy (NAC). We retrospectively included patients underwent chemotherapy for histologically proven invasive breast cancer between July 2020 and June 2023 and monitored the tumor response with breast magnetic resonance imaging (MRI), including tensor-valued diffusion encoding. We reviewed pre- and post-NAC MRIs regarding chemotherapy in 23 breast cancers. Q-space trajectory imaging (QTI) parameters were estimated at each time-point, and were compared with histopathological parameters. The mean total mean kurtosis (MKT), anisotropic mean kurtosis (MKA), and microscopic fractional anisotropy (µFA) were significantly decreased on post-NAC MRI compared with pre-NAC MRI, with the large effect size (ES) in MKA and µFA (0.81±0.41 vs. 0.99±0.33, ES: 0.48, P=0.03; 0.48±0.30 vs. 0.73±0.27, ES: 0.88, P<0.001; 0.58±0.14 vs. 0.68±0.11, ES: 0.79, P=0.003; respectively). Regarding prognostic factors, tumors with high Ki-67 expression showed significantly lower pre-NAC mean diffusivity (MD) and higher pre-NAC µFA compared to tumors with low Ki-67 expression (0.98±0.09 vs. 1.25±0.20, P=0.002; and 0.72±0.07 vs. 0.57±0.10, P=0.005; respectively). And negative progesterone receptor (PR) group revealed significantly lower MKT, MKA, and isotropic mean kurtosis than positive PR group on the post-NAC MRI (0.60±0.31 vs. 1.03±0.40, P=0.008; 0.36±0.21 vs. 0.61±0.33, P=0.04; and 0.23±0.17 vs. 0.42±0.25, P=0.046; respectively). QTI parameters reflected the microstructural changes in breast cancer treated with NAC and can be used as noninvasive imaging biomarkers correlated with prognostic factors.

Barriers and facilitators to breast cancer screening among high-risk women: a qualitative study.

Women with greater than 20-25% lifetime breast cancer risk are recommended to have breast cancer screening with annual mammogram and supplemental breast MRI. However, few women follow these screening recommendations. The objective of this study was to identify barriers and facilitators of screening among women at high risk for breast cancer, guided by the Health Services Utilization Model (HSUM). Unaffected high-risk women (N=63) completed semi-structured qualitative interviews exploring their experiences with breast cancer screening. Interviews were audio recorded, transcribed verbatim, and analyzed using a combined deductive and inductive approach. Most participants (84%) had received a screening mammogram; fewer (33%) had received a screening breast MRI. Only 14% had received neither screening. In line with the HSUM, qualitative analysis identified predisposing factors, enabling factors, and need factors associated with receipt of breast cancer screening. Enabling factors - including financial burden, logistic barriers, social support, and care coordination - were most frequently discussed. Predisposing factors included knowledge, health beliefs, and self-advocacy. Need factors included healthcare provider recommendation, family history of breast cancer, and personal medical history. Although HSUM themes were consistent for both mammography and breast MRI, participants did highlight several important differences in barriers and facilitators between the two screening modalities. Barriers and enabling factors associated with supplemental screening for high-risk women represent possible intervention targets. Future research is needed to develop and test multilevel interventions targeting these factors, with the ultimate goal of increasing access to supplemental screening for high-risk women.

Breast Cancer Screening Using Mammography, Digital Breast Tomosynthesis, and Magnetic Resonance Imaging by Breast Density

Information on long-term benefits and harms of screening with digital breast tomosynthesis (DBT) with or without supplemental breast magnetic resonance imaging (MRI) is needed for clinical and policy discussions, particularly for patients with dense breasts. To project long-term population-based outcomes for breast cancer mammography screening strategies (DBT or digital mammography) with or without supplemental MRI by breast density. Collaborative modeling using 3 Cancer Intervention and Surveillance Modeling Network (CISNET) breast cancer simulation models informed by US Breast Cancer Surveillance Consortium data. Simulated women born in 1980 with average breast cancer risk were included. Modeling analyses were conducted from January 2020 to December 2023. Annual or biennial mammography screening with or without supplemental MRI by breast density starting at ages 40, 45, or 50 years through age 74 years. Lifetime breast cancer deaths averted, false-positive recall and false-positive biopsy recommendations per 1000 simulated women followed-up from age 40 years to death summarized as means and ranges across models. Biennial DBT screening for all simulated women started at age 50 vs 40 years averted 7.4 vs 8.5 breast cancer deaths, respectively, and led to 884 vs 1392 false-positive recalls and 151 vs 221 false-positive biopsy recommendations, respectively. Biennial digital mammography had similar deaths averted and slightly more false-positive test results than DBT screening. Adding MRI for women with extremely dense breasts to biennial DBT screening for women aged 50 to 74 years increased deaths averted (7.6 vs 7.4), false-positive recalls (919 vs 884), and false-positive biopsy recommendations (180 vs 151). Extending supplemental MRI to women with heterogeneously or extremely dense breasts further increased deaths averted (8.0 vs 7.4), false-positive recalls (1088 vs 884), and false-positive biopsy recommendations (343 vs 151). The same strategy for women aged 40 to 74 years averted 9.5 deaths but led to 1850 false-positive recalls and 628 false-positive biopsy recommendations. Annual screening modestly increased estimated deaths averted but markedly increased estimated false-positive results. In this model-based comparative effectiveness analysis, supplemental MRI for women with dense breasts added to DBT screening led to greater benefits and increased harms. The balance of this trade-off for supplemental MRI use was more favorable when MRI was targeted to women with extremely dense breasts who comprise approximately 10% of the population.

Deep Learning Based Automatic Fibroglandular Tissue Segmentation in Breast Magnetic Resonance Imaging Screening.

In light of the global increase in breast cancer cases and the crucial importance of the density of fibroglandular tissue (FGT) in assessing risk and predicting the course of the disease, the accurate measurement of FGT emerges as a significant challenge in diagnostic imaging. The current study focuses on the automatic segmentation of breast glandular tissue in MRI scans using a deep learning model. The aim is to establish a solid foundation for the development of methods for the precise quantification of fibroglandular tissue. For this purpose, the publicly available 'Duke Breast Cancer MRI' dataset was systematically processed to train a deep neural network model utilizing the nnU-Net ('no-new-Net') framework, which was then subjected to a quantitative evaluation. The results show the following macro-averaged metrics with standard deviation: Dice Similarity Coefficient 0.827 ± 0.152, accuracy 0.997 ± 0.003, sensitivity 0.825 ± 0.158, and specificity 0.999 ± 0.001. The effectiveness of our model in segmenting FGT is underscored by the high values of the Dice coefficient, Accuracy, Sensitivity, and Specificity, which reflect the precision and reliability of our results. The findings of this study lay a solid foundation for developing automated methods to quantify FGT. Our research efforts, especially driven by clinical studies at the University Hospital Augsburg, are focused on further exploring and validating these potentials.

Longitudinal registration of T1-weighted breast MRI: A registration algorithm (FLIRE) and clinical application

PurposeMRI is commonly used to aid breast cancer diagnosis and treatment evaluation. For patients with breast cancer, neoadjuvant chemotherapy aims to reduce the tumor size and extent of surgery necessary. The current clinical standard to measure breast tumor response on MRI uses the longest tumor diameter. Radiologists also account for other tissue properties including tumor contrast or pharmacokinetics in their assessment. Accurate longitudinal image registration of breast tissue is critical to properly compare response to treatment at different timepoints. MethodsIn this study, a deformable Fast Longitudinal Image Registration (FLIRE) algorithm was optimized for breast tissue. FLIRE was then compared to the publicly available software packages with high accuracy (DRAMMS) and fast runtime (Elastix). Patients included in the study received longitudinal T1-weighted MRI without fat saturation at two to six timepoints as part of asymptomatic screening (n = 27) or throughout neoadjuvant chemotherapy treatment (n = 32). T1-weighted images were registered to the first timepoint with each algorithm. ResultsAlignment and runtime performance were compared using two-way repeated measure ANOVAs (P < 0.05). Across all patients, Pearson's correlation coefficient across the entire image volume was slightly higher with statistical significance and had less variance for FLIRE (0.98 ± 0.01 stdev) compared to DRAMMS (0.97 ± 0.03 stdev) and Elastix (0.95 ± 0.03 stdev). Additionally, FLIRE runtime (10.0 mins) was 9.0 times faster than DRAMMS (89.6 mins) and 1.5 times faster than Elastix (14.5 mins) on a Linux workstation. ConclusionFLIRE demonstrates promise for time-sensitive clinical applications due to its accuracy, robustness across patients and timepoints, and speed.