Deep Learning for Distinguishing Mucinous Breast Carcinoma From Fibroadenoma on Ultrasound

PURPOSE

Mucinous breast carcinoma (MBC) tends to be misdiagnosed as fibroadenomas (FA) due to its benign imaging characteristics. We aimed to develop a deep learning (DL) model to differentiate MBC and FA based on ultrasound (US) images. The model could contribute to the diagnosis of MBC for radiologists.

METHODS

In this retrospective study, 884 eligible patients (700 FA patients and 184 MBC patients) with 2257 US images were enrolled. The images were randomly divided into a training set (n = 1805 images) and a test set (n = 452 images) in a ratio of 8:2. First, we used the training set to establish DL model, DL+ age-cutoff model and DL+ age-tree model. Then, we compared the diagnostic performance of three models to get the optimal model. Finally, we evaluated the diagnostic performance of radiologists (4 junior and 4 senior radiologists) with and without the assistance of the optimal model in the test set.

RESULTS

The DL+ age-tree model yielded higher areas under the receiver operating characteristic curve (AUC) than DL model and DL+ age-cutoff model (0.945 vs. 0.835, P < .001; 0.945 vs. 0.931, P < .001, respectively). With the assistance of DL+ age-tree model, both junior and senior radiologists' AUC had significant improvement (0.746-0.818, P = .010, 0.827-0.860, P = .005, respectively).

CONCLUSIONS

The DL+ age-tree model based on US images and age showed excellent performance in the differentiation of MBC and FA. Moreover, it can effectively improve the performance of radiologists with different degrees of experience that may contribute to reducing the misdiagnosis of MBC.

Clinical Breast MRI-based Radiomics for Distinguishing Benign and Malignant Lesions: An Analysis of Sequences and Enhanced Phases

BACKGROUND

Previous studies have used different imaging sequences and different enhanced phases for breast lesion calsification in radiomics. The optimal sequence and contrast enhanced phase is unclear.

PURPOSE

To identify the optimal magnetic resonance imaging (MRI) radiomics model for lesion clarification, and to simulate its incremental value for multiparametric MRI (mpMRI)-guided biopsy.

STUDY TYPE

Retrospective.

POPULATION

329 female patients (138 malignant, 191 benign), divided into a training set (first site, n = 192) and an independent test set (second site, n = 137).

FIELD STRENGTH/SEQUENCE

3.0-T, fast spoiled gradient-echo and fast spin-echo T1-weighted imaging (T1WI), fast spin-echo T2-weighted imaging (T2WI), echo-planar diffusion-weighted imaging (DWI), and fast spoiled gradient-echo contrast-enhanced MRI (CE-MRI).

ASSESSMENT

Two breast radiologists with 3 and 10 years' experience developed radiomics model on CE-MRI, CE-MRI + DWI, CE-MRI + DWI + T2WI, CE-MRI + DWI + T2WI + T1WI at each individual phase (P) and for multiple combinations of phases. The optimal radiomics model (Rad-score) was identified as having the highest area under the receiver operating characteristic curve (AUC) in the test set. Specificity was compared between a traditional mpMRI model and an integrated model (mpMRI + Rad-score) at sensitivity >98%.

STATISTICAL TESTS

Wilcoxon paired-samples signed rank test, Delong test, McNemar test. Significance level was 0.05 and Bonferroni method was used for multiple comparisons (P = 0.007, 0.05/7).

RESULTS

For radiomics models, CE-MRI/P3 + DWI + T2WI achieved the highest performance in the test set (AUC = 0.888, 95% confidence interval: 0.833-0.944). The integrated model had significantly higher specificity (55.3%) than the mpMRI model (31.6%) in the test set with a sensitivity of 98.4%.

DATA CONCLUSION

The CE-MRI/P3 + DWI + T2WI model is the optimized choice for breast lesion classification in radiomics, and has potential to reduce benign biopsies (100%-specificity) from 68.4% to 44.7% while retaining sensitivity >98%.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 2.

Combination of conventional ultrasound with quantitative and qualitative analyses of CEUS for the differentiation of benign and malignant breast solid lesions: A modified breast cancer model

OBJECTIVE

Breast cancer has become one of the main diseases threatening women's health and lives. Ultrasound (US) is the first diagnostic option for several patients because of its non-radiation, convenient, and low-cost features. Conventional US combined with contrast-enhanced US (CEUS) has improved diagnostic accuracy, while due to the presence of numerous parameters, no international consensus on diagnostic criteria could be attained. Therefore, it is necessary to develop a reliable diagnostic model with the involvement of a few parameters while increasing the diagnostic accuracy.

METHODS

Data from 265 patients, including conventional US, CEUS, and postoperative pathological results, were collected. 21 parameters from the conventional US and both qualitative and quantitative aspects of CEUS were analyzed through univariate and multivariate logistic regression analyses. Specific parameters with independent influential factors were identified. A nomogram was subsequently developed to visually represent the contribution and linear weighting of each parameter. The effectiveness of the new model was assessed through calibration curves and the Hosmer-Lemeshow goodness-of-fit test.

RESULTS

Six independent influential factors for breast malignant tumors were identified, including homogeneous echo, lesion vascularity, enhancement mode, enhancement shape, nourishing vessels, and slope. The area under the curve (AUC) values in the training and test datasets were 0.933 and 0.860, respectively. The modified model exhibited satisfactory diagnostic accuracy and operability.

CONCLUSION

The modified model, despite incorporating fewer parameters, maintained diagnostic accuracy. It is exhibited as a convenient, effective, and easily deployable model for diagnosing malignant breast nodules.

Mean Apparent Propagator MRI: Quantitative Assessment of Tumor-Stroma Ratio in Invasive Ductal Breast Carcinoma

Purpose To determine whether metrics from mean apparent propagator (MAP) MRI perform better than apparent diffusion coefficient (ADC) value in assessing the tumor-stroma ratio (TSR) status in breast carcinoma. Materials and Methods From August 2021 to October 2022, 271 participants were prospectively enrolled (ClinicalTrials.gov identifier: NCT05159323) and underwent breast diffusion spectral imaging and diffusion-weighted imaging. MAP MRI metrics and ADC were derived from the diffusion MRI data. All participants were divided into high-TSR (stromal component < 50%) and low-TSR (stromal component ≥ 50%) groups based on pathologic examination. Clinicopathologic characteristics were collected, and MRI findings were assessed. Logistic regression was used to determine the independent variables for distinguishing TSR status. The area under the receiver operating characteristic curve (AUC) and sensitivity, specificity, and accuracy were compared between the MAP MRI metrics, either alone or combined with clinicopathologic characteristics, and ADC, using the DeLong and McNemar test. Results A total of 181 female participants (mean age, 49 years ± 10 [SD]) were included. All diffusion MRI metrics differed between the high-TSR and low-TSR groups (P < .001 to P = .01). Radial non-Gaussianity from MAP MRI and lymphovascular invasion were significant independent variables for discriminating the two groups, with a higher AUC (0.81 [95% CI: 0.74, 0.87] vs 0.61 [95% CI: 0.53, 0.68], P < .001) and accuracy (138 of 181 [76%] vs 106 of 181 [59%], P < .001) than that of the ADC. Conclusion MAP MRI may serve as a better approach than conventional diffusion-weighted imaging in evaluating the TSR of breast carcinoma. Keywords: MR Diffusion-weighted Imaging, MR Imaging, Breast, Oncology ClinicalTrials.gov Identifier: NCT05159323 Supplemental material is available for this article. © RSNA, 2024.

A meta-analysis of MRI radiomics-based diagnosis for BI-RADS 4 breast lesions

OBJECTIVE

The aim of this study is to conduct a systematic evaluation of the diagnostic efficacy of Breast Imaging Reporting and Data System (BI-RADS) 4 benign and malignant breast lesions using magnetic resonance imaging (MRI) radiomics.

METHODS

A systematic search identified relevant studies. Eligible studies were screened, assessed for quality, and analyzed for diagnostic accuracy. Subgroup and sensitivity analyses explored heterogeneity, while publication bias, clinical relevance and threshold effect were evaluated.

RESULTS

This study analyzed a total of 11 studies involving 1,915 lesions in 1,893 patients with BI-RADS 4 classification. The results showed that the combined sensitivity and specificity of MRI radiomics for diagnosing BI-RADS 4 lesions were 0.88 (95% CI 0.83-0.92) and 0.79 (95% CI 0.72-0.84). The positive likelihood ratio (PLR), negative likelihood ratio (NLR), and diagnostic odds ratio (DOR) were 4.2 (95% CI 3.1-5.7), 0.15 (95% CI: 0.10-0.22), and 29.0 (95% CI 15-55). The summary receiver operating characteristic (SROC) analysis yielded an area under the curve (AUC) of 0.90 (95% CI 0.87-0.92), indicating good diagnostic performance. The study found no significant threshold effect or publication bias, and heterogeneity among studies was attributed to various factors like feature selection algorithm, radiomics algorithms, etc. Overall, the results suggest that MRI radiomics has the potential to improve the diagnostic accuracy of BI-RADS 4 lesions and enhance patient outcomes.

CONCLUSION

MRI-based radiomics is highly effective in diagnosing BI-RADS 4 benign and malignant breast lesions, enabling improving patients' medical outcomes and quality of life.

Imaging Findings in Acute Traumatic Brain Injury: a National Institute of Neurological Disorders and Stroke Common Data Element-Based Pictorial Review and Analysis of Over 4000 Admission Brain Computed Tomography Scans from the Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI) Study

In 2010, the National Institute of Neurological Disorders and Stroke (NINDS) created a set of common data elements (CDEs) to help standardize the assessment and reporting of imaging findings in traumatic brain injury (TBI). However, as opposed to other standardized radiology reporting systems, a visual overview and data to support the proposed standardized lexicon are lacking. We used over 4000 admission computed tomography (CT) scans of patients with TBI from the Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI) study to develop an extensive pictorial overview of the NINDS TBI CDEs, with visual examples and background information on individual pathoanatomical lesion types, up to the level of supplemental and emerging information (e.g., location and estimated volumes). We documented the frequency of lesion occurrence, aiming to quantify the relative importance of different CDEs for characterizing TBI, and performed a critical appraisal of our experience with the intent to inform updating of the CDEs. In addition, we investigated the co-occurrence and clustering of lesion types and the distribution of six CT classification systems. The median age of the 4087 patients in our dataset was 50 years (interquartile range, 29-66; range, 0-96), including 238 patients under 18 years old (5.8%). Traumatic subarachnoid hemorrhage (45.3%), skull fractures (37.4%), contusions (31.3%), and acute subdural hematoma (28.9%) were the most frequently occurring CT findings in acute TBI. The ranking of these lesions was the same in patients with mild TBI (baseline Glasgow Coma Scale [GCS] score 13-15) compared with those with moderate-severe TBI (baseline GCS score 3-12), but the frequency of occurrence was up to three times higher in moderate-severe TBI. In most TBI patients with CT abnormalities, there was co-occurrence and clustering of different lesion types, with significant differences between mild and moderate-severe TBI patients. More specifically, lesion patterns were more complex in moderate-severe TBI patients, with more co-existing lesions and more frequent signs of mass effect. These patients also had higher and more heterogeneous CT score distributions, associated with worse predicted outcomes. The critical appraisal of the NINDS CDEs was highly positive, but revealed that full assessment can be time consuming, that some CDEs had very low frequencies, and identified a few redundancies and ambiguity in some definitions. Whilst primarily developed for research, implementation of CDE templates for use in clinical practice is advocated, but this will require development of an abbreviated version. In conclusion, with this study, we provide an educational resource for clinicians and researchers to help assess, characterize, and report the vast and complex spectrum of imaging findings in patients with TBI. Our data provides a comprehensive overview of the contemporary landscape of TBI imaging pathology in Europe, and the findings can serve as empirical evidence for updating the current NINDS radiologic CDEs to version 3.0.

Development and Validation of MRI Radiomics Models to Differentiate HER2-Zero, -Low, and -Positive Breast Cancer

BACKGROUND. Breast cancer HER2 expression has been redefined using a three-tiered system, with HER2-zero cancers considered ineligible for HER2-targeted therapy, HER2-low cancers considered candidates for novel HER2-targeted drugs, and HER2-positive cancers treated with traditional HER2-targeted medications. OBJECTIVE. The purpose of this study was to assess MRI radiomics models for a three-tiered classification of HER2 expression of breast cancer. METHODS. This retrospective study included 592 patients with pathologically confirmed breast cancer (mean age, 47.0 ± 18.0 [SD] years) who underwent breast MRI at either of a health system's two hospitals from April 2016 through June 2022. Three-tiered HER2 status was pathologically determined. Radiologists assessed the conventional MRI features of tumors and manually segmented the tumors on multiparametric sequences (T2-weighted images, DWI, ADC maps, and T1-weighted delayed contrast-enhanced images) to extract radiomics features. Least absolute shrinkage and selection operator analysis was used to develop two radiomics signatures, to differentiate HER2-zero cancers from HER2-low or HER2-positive cancers (task 1) as well as to differentiate HER2-low cancers from HER2-positive cancers (task 2). Patients from hospital 1 were randomly assigned to a discovery set (task 1: n = 376; task 2: n = 335) or an internal validation set (task 1: n = 161; task 2: n = 143); patients from hospital 2 formed an external validation set (task 1: n = 55; task 2: n = 50). Multivariable logistic regression analysis was used to create nomograms combining radiomics signatures with clinicopathologic and conventional MRI features. RESULTS. AUC, sensitivity, and specificity in the discovery, internal validation, and external validation sets were as follows: for task 1, 0.89, 99.4%, and 69.0%; 0.86, 98.6%, and 76.5%; and 0.78, 100.0%, and 0.0%, respectively; for task 2, 0.77, 93.8%, and 32.3%; 0.75, 92.9%, and 6.8%; and 0.77, 97.0%, and 29.4%, respectively. For task 1, no nomogram was created because no clinicopathologic or conventional MRI feature was associated with HER2 status independent of the MRI radiomics signature. For task 2, a nomogram including an MRI radiomics signature and three pathologic features (histologic grade of III, high Ki-67 index, and positive progesterone receptor status) that were independently associated with HER2-low expression had an AUC of 0.87, 0.83, and 0.80 in the three sets. CONCLUSION. MRI radiomics features were used to differentiate HER2-zero from HER2-low cancers or HER2-positives cancers as well as to differentiate HER2-low cancers from HER2-positive cancers. CLINICAL IMPACT. MRI radiomics may help select patients for novel or traditional HER2-targeted therapies, particularly those patients with ambiguous results of immunohistochemical staining results or limited access to fluorescence in situ hybridization.

The value of Demetics ultrasound-assisted diagnosis system in diagnosis of breast lesions and in assessment Ki-67 status of breast cancer

PURPOSE

This study aims to explore the diagnostic efficiency of the Demetics for breast lesions and assessment of Ki-67 status.

MATERIAL

This retrospective study included 291 patients. Three combined methods (method 1: upgraded BI-RADS when Demetics classified the breast lesion as malignant; method 2: downgraded BI-RADS when Demetics classified the breast lesion as benign; method 3: BI-RADS was upgraded or downgraded according to Demetrics' diagnosis) were used to compare the diagnostic efficiency of two radiologists with different seniority before and after using Demetics. The correlation between the visual heatmap by Demetics and the Ki-67 expression level of breast cancer was explored.

RESULTS

The sensitivity, specificity, and area under curve (AUC) of diagnosis by Demetics, junior radiologist and senior radiologist were 89.5%, 83.1%, 0.863; 76.9%, 82.4%, 0.797 and 81.1%, 89.9%, 0.855, respectively. Method 1 was the best for senior radiologist, which increased AUC from 0.855 to 0.884. For junior radiologist, Method 3 was the best method, improving sensitivity (88.8% vs. 76.9%) and specificity (87.2% vs. 82.4%). Demetics paid more attention to the peripheral area of breast cancer with high expression of Ki-67.

CONCLUSION

Demetics has shown good diagnostic efficiency in the assisted diagnosis of breast lesions and is expected to further distinguish Ki-67 status of breast cancer.

Opportunistic Extraction of Quantitative CT Biomarkers: Turning the Incidental Into Prognostic Information

The past two decades have seen a significant increase in the use of CT, with a corresponding rise in the mean population radiation dose. This rise in CT use has caused improved diagnostic certainty in conditions that were not previously routinely evaluated using CT, such as headaches, back pain, and chest pain. Unused data, unrelated to the primary diagnosis, embedded within these scans have the potential to provide organ-specific measurements that can be used to prognosticate or risk-profile patients for a wide variety of conditions. The recent increased availability of computing power, expertise and software for automated segmentation and measurements, assisted by artificial intelligence, provides a conducive environment for the deployment of these analyses into routine use. Data gathering from CT has the potential to add value to examinations and help offset the public perception of harm from radiation exposure. We review the potential for the collection of these data and propose the incorporation of this strategy into routine clinical practice.

Clinical Application of Computer-Aided Diagnosis System in Breast Ultrasound: A Prospective Multicenter Study

OBJECTIVES

Ultrasound tends to present very high sensitivity but relatively low specificity and positive predictive value (PPV), which would result in unnecessary breast biopsies. The purpose of this study is to analyze the diagnostic performance of computer-aided diagnosis (CAD) (S-Detect) system in differentiating breast lesions and reducing unnecessary biopsies in non-university hospitals in less-developed regions of China.

METHODS

The study was a prospective multicenter study from 8 hospitals. The ultrasound images, and cine, CAD analysis, and BI-RADS were recorded. The accuracy, sensitivity, specificity, PPV, negative predictive value (NPV), and area under the curve (AUC) were analyzed and compared between CAD and radiologists. The Youden Index (YI) was used to determine optimal cut-off for the number of planes to downgrade.

RESULTS

A total of 491 breast lesions were included in the study. Less-experienced radiologists combined CAD was superior to less-experienced radiologists alone in AUC (0.878 vs 0.712, p < 0.001), and specificity (81.3% vs 44.6%, p < 0.001). There was no statistical difference in AUC (0.891 vs 0.878, p = 0.346), and specificity (82.3% vs 81.3%, p = 0.791) between experienced radiologists and less-experienced radiologists combined CAD. With CAD assistance, the biopsy rate of less-experienced radiologists was significantly decreased (100.0% vs 25.6%, p < 0.001), and malignant rate of biopsy was significantly increased (15.0% vs 43.9%, p < 0.001).

CONCLUSIONS

CAD system can be an effective auxiliary tool in differentiating breast lesions and reducing unnecessary biopsies for radiologists from non-university hospitals in less-developed regions of China.

The value of radiomics model based on ultrasound image features in the differentiation between minimal breast cancer and small benign breast masses

BACKGROUND

Female breast cancer has surpassed lung cancer as the most common cancer, and is also the main cause of cancer death for women worldwide. Breast cancer <1 cm showed excellent survival rate. However, the diagnosis of minimal breast cancer (MBC) is challenging.

OBJECTIVE

The purpose of our research is to develop and validate an radiomics model based on ultrasound images for early recognition of MBC.

METHODS

302 breast masses with a diameter of <10 mm were retrospectively studied, including 159 benign and 143 malignant breast masses. The radiomics features were extracted from the gray-scale ultrasound image of the largest face of each breast mass. The maximum relevance minimum reduncancy and recursive feature elimination methods were used to screen. Finally, 10 features with the most discriminating value were selected for modeling. The random forest was used to establish the prediction model, and the rad-score of each mass was calculated. In order to evaluate the effectiveness of the model, we calculated and compared the area under the curve (AUC) value, sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of the model and three groups with different experience in predicting small breast masses, and drew calibration curves and decision curves to test the stability and consistency of the model.

RESULTS

When we selected 10 radiomics features to calculate the rad-score, the prediction efficiency was the best, the AUC values for the training set and testing set were 0.840 and 0.793, which was significantly better than the insufficient experience group (AUC = 0.673), slightly better than the moderate experience group (AUC = 0.768), and was inferior to the experienced group (AUC = 0.877). The calibration curve and decision curve also showed that the radiomics model had satisfied stability and clinical application value.

CONCLUSION

The radiomics model based on ultrasound image features has a satisfied predictive ability for small breast masses, and is expected to become a potential tool for the diagnosis of MBC, and it is a zero cost (in terms of patient participation and imaging time).

Impact of Imaging Biomarkers and AI on Breast Cancer Management: A Brief Review

Breast cancer stands out as the most frequently identified malignancy, ranking as the fifth leading cause of global cancer-related deaths. The American College of Radiology (ACR) introduced the Breast Imaging Reporting and Data System (BI-RADS) as a standard terminology facilitating communication between radiologists and clinicians; however, an update is now imperative to encompass the latest imaging modalities developed subsequent to the 5th edition of BI-RADS. Within this review article, we provide a concise history of BI-RADS, delve into advanced mammography techniques, ultrasonography (US), magnetic resonance imaging (MRI), PET/CT images, and microwave breast imaging, and subsequently furnish comprehensive, updated insights into Molecular Breast Imaging (MBI), diagnostic imaging biomarkers, and the assessment of treatment responses. This endeavor aims to enhance radiologists' proficiency in catering to the personalized needs of breast cancer patients. Lastly, we explore the augmented benefits of artificial intelligence (AI), machine learning (ML), and deep learning (DL) applications in segmenting, detecting, and diagnosing breast cancer, as well as the early prediction of the response of tumors to neoadjuvant chemotherapy (NAC). By assimilating state-of-the-art computer algorithms capable of deciphering intricate imaging data and aiding radiologists in rendering precise and effective diagnoses, AI has profoundly revolutionized the landscape of breast cancer radiology. Its vast potential holds the promise of bolstering radiologists' capabilities and ameliorating patient outcomes in the realm of breast cancer management.

Can Short-term Follow-up with Ultrasound be Offered as an Acceptable Alternative to Immediate Biopsy or Surgery for Patients with First Ultrasound Diagnosis of BI-RADS 4A Lesions?

OBJECTIVES

To evaluate the relevant factors associated with malignancy in Breast Imaging Reporting and Data System (BI-RADS) 4A and to determine whether it was possible to establish a safe follow-up guideline for lower-risk 4A lesions.

METHODS

In this retrospective study, patients categorized as BI-RADS 4A on ultrasound who underwent ultrasound-guided biopsy or/and surgery between June 2014 and April 2020 was analyzed. Classification-tree method and cox regression analysis were used to explore the possible correlation factors of malignancy.

RESULTS

Among 9965 patients enrolled, 1211 (mean age, 44.3 ± 13.5 years; range, 18-91 years) patients categorized as BI-RADS 4A were eligible. The result of cox regression analysis revealed the malignant rate was only associated with patient age (hazard ratio (HR) = 1.038, p < 0.001, 95% confidence interval (CI): 1.029-1.048) and the mediolateral diameter of the lesion (HR = 1.261, p < 0.001, 95% CI: 1.159-1.372). The malignant rate for patients (≤ 36 y) with BI-RADS 4A lesions (the mediolateral diameter ≤ 0.9 cm) was 0.0% (0/72). This subgroup included fibrocystic disease and adenosis in 39 patients (54.2%), fibroadenoma in 16 (22.2%), intraductal papilloma in 8 (11.1%), inflammatory lesions in 6 (8.3%), cyst in 2 (2.8%), and hamartoma in 1 (1.4%).

CONCLUSIONS

Patient age and lesion size are associated with the rate of malignancy in BI-RADS 4A. For patients with lower-risk BI-RADS 4A lesions (≤ 2% likelihood of malignancy), short-term follow-up with ultrasound may be offered as an acceptable alternative to immediate biopsy or surgery.

Cracking open the eristic rhetoric of contralateral prophylactic mastectomy research or why surgeons should not be so certain about this controversial breast cancer treatment

Contralateral prophylactic mastectomy (CPM) is a controversial breast cancer treatment in which both breasts are removed when only one is affected by cancer. Rates of CPM have been rising since the late 1990s, despite surgeons' strong agreement that the procedure should not be performed for average-risk women. This essay analyses that agreement as it is demonstrated in the surgical literature on CPM, arguing that it forms a 'rhetoric of certainty' built on the stark epistemological divide between objective and subjective forms of knowledge that operates in some areas of medicine. Further, the essay argues that this rhetoric of certainty has the potential to function as a kind of eristic rhetoric in which the right conclusion is known prior to any rhetorical exchange. As a way to 'crack open' this certainty, the essay compares the rhetoric of the surgical literature on CPM to the rhetoric of uncertainty in the radiological literature on breast cancer screening for women with a personal history of the disease. The goal of this comparison is not to suggest surgeons should support all choices for CPM. Rather, the aim is to demonstrate that choices against the procedure are not as straightforward as the surgical literature indicates and that the uncertainty affecting women's preferences for CPM is not solely the result of patient misunderstanding and/or emotional instability.

Differential Diagnosis of Benign and Malignant Breast Papillary Neoplasms on MRI With Non-mass Enhancement

RATIONALE AND OBJECTIVES

To explore the differential diagnosis of benign and malignant papillary neoplasms on MRI with non-mass enhancement.

MATERIALS AND METHODS

A total of 48 patients with surgically confirmed papillary neoplasms showing non-mass enhancement were included. Clinical findings, mammography and MRI features were retrospectively analyzed, and lesions were described according to the breast imaging report and data system (BI-RADS). Multivariate analysis of variance was used to compare the clinical and imaging features of benign and malignant lesions.

RESULTS

Fifty-three papillary neoplasms were shown on MR images with non-mass enhancement, including 33 intraductal papilloma and 20 papillary carcinomas (9 intraductal papillary carcinoma, 6 solid papillary carcinomas, and 5 invasive papillary carcinoma). Mammography showed amorphous calcification in 20% (6/30), of which 4 were in papilloma and 2 were in papillary carcinoma. On MRI, papilloma mostly showed linear distribution in 54.55% (18/33), clumped enhancement in 36.36% (12/33). Papillary carcinoma showed segmental distribution in 50% (10/20), clustered ring enhancement in 75% (15/20). ANOVA showed age (p = 0.025), clinical symptoms (p < 0.001), apparent diffusion coefficient (ADC) value (p = 0.026), distribution pattern (p = 0.029) and internal enhancement pattern (p < 0.001) were statistically significant between benign and malignant of papillary neoplasms. Multivariate analysis of variance suggested that the internal enhancement pattern was the only statistically significant factor (p = 0.010).

CONCLUSIONS

Papillary carcinoma on MRI with non-mass enhancement mostly showed internal clustered ring enhancement, while papilloma mostly showed internal clumped enhancement; additional mammography is of limited diagnostic value, and suspected calcification occurs mostly in papilloma.

The adoption of LI-RADS: a survey of non-academic radiologists

PURPOSE

To understand the practice and determinants of non-academic radiologists regarding LI-RADS and the four current LI-RADS algorithms: CT/MRI, contrast-enhanced ultrasound (CEUS), ultrasound (US), and CT/MRI Treatment Response.

MATERIALS AND METHODS

Seven themes were covered in this international survey, as follows: (1) demographics of participants and sub-specialty, (2) HCC practice and interpretation, (3) reporting practice, (4) screening and surveillance, (5) HCC imaging diagnosis, (6) treatment response, and (7) CT and MRI technique.

RESULTS

Of the 232 participants, 69.4% were from the United States, 25.0% from Canada, and 5.6% from other countries and 45.9% were abdominal/body imagers. During their radiology training or fellowship, no formal HCC diagnostic system was used by 48.7% and LI-RADS was used by 44.4% of participants. In their current practice, 73.6% used LI-RADS, 24.7% no formal system, 6.5% UNOS-OPTN, and 1.3% AASLD. Barriers to LI-RADS adoption included lack of familiarity (25.1%), not used by referring clinicians (21.6%), perceived complexity (14.5%), and personal preference (5.3%). The US LI-RADS algorithm was used routinely by 9.9% of respondents and CEUS LI-RADS was used by 3.9% of the respondents. The LI-RADS treatment response algorithm was used by 43.5% of the respondents. 60.9% of respondents thought that webinars/workshops on LI-RADS Technical Recommendations would help them implement these recommendations in their practice.

CONCLUSION

A majority of the non-academic radiologists surveyed use the LI-RADS CT/MR algorithm for HCC diagnosis, while nearly half use the LI-RADS TR algorithm for assessment of treatment response. Less than 10% of the participants routinely use the LI-RADS US and CEUS algorithms.

The added value of apparent diffusion coefficient and microcalcifications to the Kaiser score in the evaluation of BI-RADS 4 lesions

PURPOSE

To explore the added value of combining microcalcifications or apparent diffusion coefficient (ADC) with the Kaiser score (KS) for diagnosing BI-RADS 4 lesions.

METHODS

This retrospective study included 194 consecutive patients with 201 histologically verified BI-RADS 4 lesions. Two radiologists assigned the KS value to each lesion. Adding microcalcifications, ADC, or both these criteria to the KS yielded KS1, KS2, and KS3, respectively. The potential of all four scores to avoid unnecessary biopsies was assessed using the sensitivity and specificity. Diagnostic performance was evaluated by the area under the curve (AUC) and compared between KS and KS1.

RESULTS

The sensitivity of KS, KS1, KS2, and KS3 ranged from 77.1% to 100.0%.KS1 yielded significantly higher sensitivity than other methods (P < 0.05), except for KS3 (P > 0.05), most of all, when assessing NME lesions. For mass lesions, the sensitivity of these four scores was comparable (p > 0.05). The specificity of KS, KS1, KS2, and KS3 ranged from 56.0% to 69.4%, with no statistically significant differences(P > 0.05), except between KS1 and KS2 (p < 0.05).The AUC of KS1 (0.877) was significantly higher than that of KS (0.837; P = 0.0005), particularly for assessing NME (0.847 vs 0.713; P < 0.0001).

CONCLUSION

KS can stratify BI-RADS 4 lesions to avoid unnecessary biopsies. Adding microcalcifications, but not adding ADC, as an adjunct to KS improves diagnostic performance, particularly for NME lesions. ADC provides no additional diagnostic benefit to KS. Thus, only combining microcalcifications with KS is most conducive to clinical practice.

Diagnostic value of preoperative examination for evaluating margin status in breast cancer

BACKGROUND

A positive resection margin is a major risk factor for local breast cancer recurrence after breast-conserving surgery (BCS). Preoperative imaging examinations are frequently employed to assess the surgical margin.

AIM

To investigate the role and value of preoperative imaging examinations [magnetic resonance imaging (MRI), molybdenum target, and ultrasound] in evaluating margins for BCS.

METHODS

A retrospective study was conducted on 323 breast cancer patients who met the criteria for BCS and consented to the procedure from January 2014 to July 2021. The study gathered preoperative imaging data (MRI, ultrasound, and molybdenum target examination) and intraoperative and postoperative pathological information. Based on their BCS outcomes, patients were categorized into positive and negative margin groups. Subsequently, the patients were randomly split into a training set (226 patients, approximately 70%) and a validation set (97 patients, approximately 30%). The imaging and pathological information was analyzed and summarized using R software. Non-conditional logistic regression and LASSO regression were conducted in the validation set to identify factors that might influence the failure of BCS. A column chart was generated and applied to the validation set to examine the relationship between pathological margin range and prognosis. This study aims to identify the risk factors associated with failure in BCS.

RESULTS

The multivariate non-conditional logistic regression analysis demonstrated that various factors raise the risk of positive margins following BCS. These factors comprise non-mass enhancement (NME) on dynamic contrast-enhanced MRI, multiple focal vascular signs around the lesion on MRI, tumor size exceeding 2 cm, type III time-signal intensity curve, indistinct margins on molybdenum target examination, unclear margins on ultrasound examination, and estrogen receptor (ER) positivity in immunohistochemistry. LASSO regression was additionally employed in this study to identify four predictive factors for the model: ER, molybdenum target tumor type (MT Xmd Shape), maximum intensity projection imaging feature, and lesion type on MRI. The model constructed with these predictive factors exhibited strong consistency with the real-world scenario in both the training set and validation set. Particularly, the outcomes of the column chart model accurately predicted the likelihood of positive margins in BCS.

CONCLUSION

The proposed column chart model effectively predicts the success of BCS for breast cancer. The model utilizes preoperative ultrasound, molybdenum target, MRI, and core needle biopsy pathology evaluation results, all of which align with the real-world scenario. Hence, our model can offer dependable guidance for clinical decision-making concerning BCS.

Diagnostic value of preoperative examination for evaluating margin status in breast cancer

BACKGROUND

A positive resection margin is a major risk factor for local breast cancer recurrence after breast-conserving surgery (BCS). Preoperative imaging examinations are frequently employed to assess the surgical margin.

AIM

To investigate the role and value of preoperative imaging examinations [magnetic resonance imaging (MRI), molybdenum target, and ultrasound] in evaluating margins for BCS.

METHODS

A retrospective study was conducted on 323 breast cancer patients who met the criteria for BCS and consented to the procedure from January 2014 to July 2021. The study gathered preoperative imaging data (MRI, ultrasound, and molybdenum target examination) and intraoperative and postoperative pathological information. Based on their BCS outcomes, patients were categorized into positive and negative margin groups. Subsequently, the patients were randomly split into a training set (226 patients, approximately 70%) and a validation set (97 patients, approximately 30%). The imaging and pathological information was analyzed and summarized using R software. Non-conditional logistic regression and LASSO regression were conducted in the validation set to identify factors that might influence the failure of BCS. A column chart was generated and applied to the validation set to examine the relationship between pathological margin range and prognosis. This study aims to identify the risk factors associated with failure in BCS.

RESULTS

The multivariate non-conditional logistic regression analysis demonstrated that various factors raise the risk of positive margins following BCS. These factors comprise non-mass enhancement (NME) on dynamic contrast-enhanced MRI, multiple focal vascular signs around the lesion on MRI, tumor size exceeding 2 cm, type III time-signal intensity curve, indistinct margins on molybdenum target examination, unclear margins on ultrasound examination, and estrogen receptor (ER) positivity in immunohistochemistry. LASSO regression was additionally employed in this study to identify four predictive factors for the model: ER, molybdenum target tumor type (MT Xmd Shape), maximum intensity projection imaging feature, and lesion type on MRI. The model constructed with these predictive factors exhibited strong consistency with the real-world scenario in both the training set and validation set. Particularly, the outcomes of the column chart model accurately predicted the likelihood of positive margins in BCS.

CONCLUSION

The proposed column chart model effectively predicts the success of BCS for breast cancer. The model utilizes preoperative ultrasound, molybdenum target, MRI, and core needle biopsy pathology evaluation results, all of which align with the real-world scenario. Hence, our model can offer dependable guidance for clinical decision-making concerning BCS.

Invasive lobular carcinoma of the breast detected with real-time virtual sonography: a case report

BACKGROUND

Invasive lobular carcinoma (ILC) sometimes presents with unique clinical, pathologic, and radiographic features. In this case report, we describe a patient with ILC, whose initial presentation consisted with symptoms secondary to bone-marrow dissemination. In addition, the breast primary was revealed only by magnetic resonance imaging (MRI) followed by real-time virtual sonography (RVS).

CASE PRESENTATION

A 51-year-old woman presented to our outpatient clinic with dyspnea on exertion. She had severe anemia (hemoglobin, 5.3 g/dL) and thrombocytopenia (platelet count, 31 × 10³/mL). Bone-marrow biopsy was performed to evaluate hematopoietic function. The pathologic diagnosis was bone-marrow carcinomatosis due to metastatic breast cancer. Initial mammography followed by ultrasonography (US) failed to detect the primary tumor. On MRI, a non-mass-enhancement lesion was observed. While second-look US also did not detect the lesion, it was clearly visualized with RVS. We were finally able to biopsy the breast lesion. The pathologic diagnosis was ILC positive for both estrogen receptor and progesterone receptor, with 1 + immunohistochemical staining for human epidermal growth factor receptor 2. This case of ILC was characterized by bone-marrow metastasis. Due to decreased cell adhesion, the risk of bone-marrow metastasis is higher in ILC than in invasive ductal carcinoma, the most prevalent type of breast cancer. Biopsy of the primary lesion, which was initially only detected with MRI, was successfully performed with clear visualization during RVS, which is based on the fusion of MRI and US images.

CONCLUSION

In this case report and literature review, we describe the unique clinical characteristics of ILC and a strategy for identifying primary lesions that are initially only visualized with MRI.

Universal Liver Imaging Lexicon: Imaging Atlas for Research and Clinical Practice

The use of standardized terms in assessing and reporting disease processes has well-established benefits, such as clear communication between radiologists and other health care providers, improved diagnostic accuracy and reproducibility, and the enhancement and facilitation of research. Recently, the Liver Imaging Reporting and Data System (LI-RADS) Steering Committee released a universal liver imaging lexicon. The current version of the lexicon includes 81 vetted and precisely defined terms that are relevant to acquisition of images using all major liver imaging modalities and contrast agents, as well as lesion- and organ-level features. Most terms in the lexicon are applicable to all patients undergoing imaging of the liver, and only a minority of the terms are strictly intended to be used for patients with high risk factors for hepatocellular carcinoma. This pictorial atlas familiarizes readers with the liver imaging lexicon and includes discussion of general concepts, providing sample definitions, schematics, and clinical examples for a subset of the terms in the liver imaging lexicon. The authors discuss general, technical, and imaging feature terms used commonly in liver imaging, with the goal of illustrating their use for clinical and research applications. Work of the U.S. Government published under an exclusive license with the RSNA. Online supplemental material is available for this article.

Radiomics in clinical trials: perspectives on standardization

The term biomarker is used to describe a biological measure of the disease behavior. The existing imaging biomarkers are associated with the known tissue biological characteristics and follow a well-established roadmap to be implemented in routine clinical practice. Recently, a new quantitative imaging analysis approach named radiomics has emerged. It refers to the extraction of a large number of advanced imaging features with high-throughput computing. Extensive research has demonstrated its value in predicting disease behavior, progression, and response to therapeutic options. However, there are numerous challenges to establishing it as a clinically viable solution, including lack of reproducibility and transparency. The data-driven nature also does not offer insights into the underpinning biology of the observed relationships. As such, additional effort is needed to establish it as a qualified biomarker to inform clinical decisions. Here we review the technical difficulties encountered in the clinical applications of radiomics and current effort in addressing some of these challenges in clinical trial designs. By addressing these challenges, the true potential of radiomics can be unleashed.

Evaluating breast ultrasound S-detect image analysis for small focal breast lesions

Background

S-Detect is a computer-assisted, artificial intelligence-based system of image analysis that has been integrated into the software of ultrasound (US) equipment and has the capacity to independently differentiate between benign and malignant focal breast lesions. Since the revision and upgrade in both the breast imaging-reporting and data system (BI-RADS) US lexicon and the S-Detect software in 2013, evidence that supports improved accuracy and specificity of radiologists' assessment of breast lesions has accumulated. However, such assessment using S-Detect technology to distinguish malignant from breast lesions with a diameter no greater than 2 cm requires further investigation.

Methods

The US images of focal breast lesions from 295 patients in our hospital from January 2019 to June 2022 were collected. The BI-RADS data were evaluated by the embedded program and as manually modified prior to the determination of a pathological diagnosis. The receiver operator characteristic (ROC) curves were constructed to compare the diagnostic accuracy between the assessments of the conventional US images, the S-Detect classification, and the combination of the two.

Results

There were 326 lesions identified in 295 patients, of which pathological confirmation demonstrated that 239 were benign and 87 were malignant. The sensitivity, specificity, and accuracy of the conventional imaging group were 75.86%, 93.31%, and 88.65%. The sensitivity, specificity, and accuracy of the S-Detect classification group were 87.36%, 88.28%, and 88.04%, respectively. The assessment of the amended combination of S-Detect with US image analysis (Co-Detect group) was improved with a sensitivity, specificity, and accuracy of 90.80%, 94.56%, and 93.56%, respectively. The diagnostic accuracy of the conventional US group, the S-Detect group, and the Co-Detect group using area under curves was 0.85, 0.88 and 0.93, respectively. The Co-Detect group had a better diagnostic efficiency compared with the conventional US group (Z = 3.882, p = 0.0001) and the S-Detect group (Z = 3.861, p = 0.0001). There was no significant difference in distinguishing benign from malignant small breast lesions when comparing conventional US and S-Detect techniques.

Conclusions

The addition of S-Detect technology to conventional US imaging provided a novel and feasible method to differentiate benign from malignant small breast nodules.

Volumetric breast density evaluation using fully automated Volpara software, its comparison with BIRADS density types and correlation with the risk of malignancy

Background

Mammography is currently the modality of choice for mass screening of breast cancer, although its sensitivity is low in dense breasts. Besides, higher breast density has been identified as independent risk factor so it has been conceptualized that women with dense breasts should be encouraged for supplemental screening. In this study, we aimed to estimate the distribution of volumetric breast density using fully automated Volpara software and to analyze the level of agreement between volumetric density grades and Breast Imaging Reporting and Data System (BI-RADS) density grades. We also aim to estimate the distribution of breast cancer in different VDG and to find a correlation between VDG and risk of malignancy.

Results

VDG-c was most common followed by VDG-b and BIRADS grade B was commonest followed by grade C. The density distribution was found inversely related to the age. Level of agreement between VDG and BIRADS grades was moderate (κ = 0.5890). Statistically significant correlation was noted between VDG-c and d for risk of malignancy (p < 0.001).

Conclusion

Difficulties associated with the use of BI-RADS density categories may be avoided if assessed using a fully automated volumetric method. High VDG can be considered as independent risk factor for malignancy. Thus, awareness of a woman’s breast density might be useful in determining the frequency and imaging modality for screening.

Efficacy and Accuracy of Using Magnetic Seed for Preoperative Non-Palpable Breast Lesions Localization: Our Experience with Magseed

In this retrospective study we share our single-center experience using a magnetic seed for the preoperative localization of non-palpable breast lesions. Patients who underwent a preoperative localization with Magseed® (Endomagnetics, Cambridge, UK) placement between 2020 and 2022 were enrolled. Indications to Magseed placement have been established during multidisciplinary meetings prior to surgery and all patients underwent breast-conserving surgery (BCS). 45 patients were included. Magnetic seeds have been introduced under ultrasound guidance in 40 patients (88.9%) and under stereotactic guidance in 5 patients (11.1%). We registered a highly successful placement rate (97.8%), with only one case of migration (2.2%). After BCS, all the magnetic seeds were recovered (100% retrieval rate). The re-excision rate for positive margins was 0%. Our experience, with a highly successful placement and retrieval rate and a re-excision rate equal to 0%, is consistent with the encouraging literature published on Magseed so far, suggesting this technique to be extremely effective. Moreover, our single case of seed migration supports the existing data stating that Magseed migration is rare. In conclusion, despite acknowledging Magseed limitations, we highly value the advantages linked to this technique, and we, therefore, uphold its use.

Estimating lifetime risk for breast cancer as a screening tool for identifying those who would benefit from additional services among women utilizing mobile mammography

BACKGROUND

To estimate lifetime risk of breast cancer among women utilizing mobile mammography and to determine the proportion that might benefit from additional services, such as genetic counseling and educational programs.

METHODS

Retrospective analysis of electronic health records for 2214 women screened for breast cancer on a mobile mammography van was conducted. Participants answered questions about their demographic characteristics, breast health, and family history of cancer. Logistic regression analyses were used to assess the odds of being recommended for additional services by the Tyrer-Cuzick (TC) lifetime risk score.

RESULTS

The average TC ten-year risk score was 2.76 % ± 2.01 %, and the average TC lifetime risk score was 7.30 % ± 4.80 %. Using lifetime risk scores ≥ 10 %, it was determined that 444 patients (20.23 %) could be referred to additional services. Less than one percent of patients had been tested for the BRCA genes previously. The odds of being recommended for additional services by the TC model were significantly greater among those who were eligible for the New York Cancer Services Program (i.e., a proxy for lack of insurance) when compared to those who were ineligible (OR=1.31, 95 % CI: 1.03-1.66). After adjustment, screening borough and race/ethnicity were not significantly associated with being recommended for services.

CONCLUSION

Genetic counseling and education are some of the tools available to promote awareness and early detection of breast cancer; however, screening guidelines do not mandate genetic counseling or referrals for individuals at high-risk.

POLICY SUMMARY

Patients and providers should have discussions about predicted TC lifetime risk scores at follow-up breast cancer screening appointments, as this is a missed opportunity to improve care at both fixed sites and mobile clinics.

Which combination of different ultrasonography modalities is more appropriate to diagnose breast cancer?: A network meta-analysis (a PRISMA-compliant article)

BACKGROUND

Abundant amount of literature that analyze the various detection of different ultrasound methods, no comprehensive literature that investigates the diagnostic values of breast cancer (BC) by different ultrasonography modalities through a network meta-analysis (NMA) has been made available. Each imaging diagnostic examination has its own advantages and disadvantages, and any imaging examination is not enough to make an accurate diagnosis of the disease. Thus, this study aimed to compare diagnostic values among different ultrasonography modalities, including the information of 2-dimension, stiffness and blood flow, by a network meta-analysis in the hopes of understanding which imaging methods are better and which combination of different ultrasonography modalities is more appropriate to diagnose BC.

METHODS

We made use of Cochrane Library, PubMed, and Embase in order to obtain literature and papers. The combination analysis of both direct and indirect evidence in terms of sensitivity, specificity, positive predictive value (PPV), negative predictive value(NPV) and accuracy was conducted so as to assess the odds ratios (ORs) and surface under the cumulative ranking curve (SUCRA) values of the 8 different ultrasound methods.

RESULTS

A total of 36 eligible diagnostic tests regarding 8 ultrasound methods were included in the study. According to this network meta-analysis, Breast Imaging Reporting and Data System (BI-RADS) 4b exhibited higher specificity, PPV, and accuracy and lower sensitivity and NPV than BI-RADS 4a. Contrast-enhanced ultrasound (CEUS) had the highest sensitivity, PPV, NPV and accuracy and superb microvascular imaging (SMI) had the highest specificity among color Doppler flow imaging (CDFI), power Doppler imaging(PDI), SMI and CEUS. There was no significant difference in diagnostic indexes between SMI and CEUS. Shear wave elastrography (SWE) had higher PPV and accuracy and lower sensitivity, specificity NPV than strain elastography (SE).

CONCLUSION

The results of this network meta-analysis suggested more appropriate combination of different ultrasound modalities is BI-RADS 4b, SMI, and SWE for the diagnosis of breast cancer.

Using Breast Tissue Information and Subject-Specific Finite-Element Models to Optimize Breast Compression Parameters for Digital Mammography

Digital mammography has become a first-line diagnostic tool for clinical breast cancer screening due to its high sensitivity and specificity. Mammographic compression force is closely associated with image quality and patient comfort. Therefore, optimizing breast compression parameters is essential. Subjects were recruited for digital mammography and breast magnetic resonance imaging (MRI) within a month. Breast MRI images were used to calculate breast volume and volumetric breast density (VBD) and construct finite element models. Finite element analysis was performed to simulate breast compression. Simulated compressed breast thickness (CBT) was compared with clinical CBT and the relationships between compression force, CBT, breast volume, and VBD were established. Simulated CBT had a good linear correlation with the clinical CBT (R2 = 0.9433) at the clinical compression force. At 10, 12, 14, and 16 daN, the mean simulated CBT of the breast models was 5.67, 5.13, 4.66, and 4.26 cm, respectively. Simulated CBT was positively correlated with breast volume (r > 0.868) and negatively correlated with VBD (r < –0.338). The results of this study provides a subject-specific and evidence-based suggestion of mammographic compression force for radiographers considering image quality and patient comfort.

A Comprehensive Model for Diagnosis of Primary Breast Lymphoma Differentiated From Breast Cancer and Prognosis Evaluation of Surgical Treatment

Background

The objective of this work was to discriminate between primary breast lymphoma (PBL) and breast cancer by systematically analyzing clinical characteristics, laboratory examination results, ultrasound features, and mammography findings to establish a diagnostic model for PBL and to analyze the influence of surgical treatment on the prognosis of PBL patients.

Method

We analyzed 20 PBL and 70 breast cancer patients treated during the same period by comparing several characteristics: clinical features, such as age, tumor position, and breast complaints; laboratory examination findings, such as the lactate dehydrogenase (LDH) level, and imaging features such as the maximum diameter, shape, margins, aspect ratio, and calcification of the mass and axillary lymph node involvement. A diagnostic model was then developed using logistic regression analysis. The impact of surgery on the prognosis of PBL patients was assessed through Kaplan–Meier survival analysis.

Result

Breast cancer and PBL could be distinguished based on imaging features, including the maximum diameter, shape, margin, and calcification of the mass, and lymph node involvement (P < 0.05). There were no significant differences between PBL and breast cancer patients in terms of clinical features, or the LDH level. The area under the receiver operating characteristic curve was 0.821. The log-rank test showed that surgery had no significant influence on the prognosis of PBL patients.

Conclusion

Ultrasound and mammography are the most useful methods for detecting malignant breast tumors. Compared with breast cancer tumors, breast lymphoma tumors are larger with a more regular shape and less calcification and are often accompanied by axillary lymph node involvement. Patients with a breast malignancy should not undergo surgical excision without an accurate diagnosis.

Radiomics Based on Digital Mammography Helps to Identify Mammographic Masses Suspicious for Cancer

Objectives

This study aims to build radiomics model of Breast Imaging Reporting and Data System (BI-RADS) category 4 and 5 mammographic masses extracted from digital mammography (DM) for mammographic masses characterization by using a sensitivity threshold similar to that of biopsy.

Materials and Methods

This retrospective study included 288 female patients (age, 52.41 ± 10.31) who had BI-RADS category 4 or 5 mammographic masses with an indication for biopsy. The patients were divided into two temporal set (training set, 82 malignancies and 110 benign lesions; independent test set, 48 malignancies and 48 benign lesions). A total of 188 radiomics features were extracted from mammographic masses on the combination of craniocaudal (CC) position images and mediolateral oblique (MLO) position images. For the training set, Pearson’s correlation and the least absolute shrinkage and selection operator (LASSO) were used to select non-redundant radiomics features and useful radiomics features, respectively, and support vector machine (SVM) was applied to construct a radiomics model. The receiver operating characteristic curve (ROC) analysis was used to evaluate the classification performance of the radiomics model and to determine a threshold value with a sensitivity higher than 98% to predict the mammographic masses malignancy. For independent test set, identical threshold value was used to validate the classification performance of the radiomics model. The stability of the radiomics model was evaluated by using a fivefold cross-validation method, and two breast radiologists assessed the diagnostic agreement of the radiomics model.

Results

In the training set, the radiomics model obtained an area under the receiver operating characteristic curve (AUC) of 0.934 [95% confidence intervals (95% CI), 0.898–0.971], a sensitivity of 98.8% (81/82), a threshold of 0.22, and a specificity of 60% (66/110). In the test set, the radiomics model obtained an AUC of 0.901 (95% CI, 0.835–0.961), a sensitivity of 95.8% (46/48), and a specificity of 66.7% (32/48). The radiomics model had relatively stable sensitivities in fivefold cross-validation (training set, 97.39% ± 3.9%; test set, 98.7% ± 4%).

Conclusion

The radiomics method based on DM may help reduce the temporarily unnecessary invasive biopsies for benign mammographic masses over-classified in BI-RADS category 4 and 5 while providing similar diagnostic performance for malignant mammographic masses as biopsies.

Recurrence Yield of Stereotactic Biopsy of Suspicious Calcifications After Breast Conservation Therapy

Aim To analyze the histopathological outcome of stereotactic biopsies of newly developed suspicious calcifications at lumpectomy scar site in patients with breast conservation surgery (BCS) to determine the incidence of malignancy and the association of mammographic appearance of recurrent microcalcification and their distribution. We also determined the association of disease recurrence with the presence of calcifications in original tumor and lumpectomy resection margins with the risk of recurrence. Materials and methods This study is a retrospective review of mammograms of patients with breast cancer from 2010 to 2021 who underwent stereotactic biopsy of newly developed suspicious calcifications at scar site appreciated on annual follow-up mammogram after breast conservation surgery (BCS) with no mass on correlative ultrasound. The radiological and pathological features of the patients' primary tumor and new calcifications were obtained from the hospital's electronic patient record system. Results A total of 84 patients with breast cancer developed suspicious microcalcifications at the lumpectomy scar site detected on follow-up mammograms after BCS, and 28.6% showed malignant histopathological outcomes. All malignant cases demonstrated pleomorphic morphology. All amorphous (9.5%) and coarse heterogeneous (54.8%) calcifications were benign. The distribution pattern of recurrent malignant calcifications was grouped in 9.5%, regional in 2.4%, linear in 9.5%, and segmental in 7.1%. Calcifications in primary tumors were found in 20.2% of cases. Positive margins were found in 7.1% of these malignant cases. Statistically, there was a strong association between calcification morphology, calcification distribution, presence of calcifications on baseline mammogram, and tumor resection margins. The presence of calcifications in primary tumors and positive resection margins were identified as significant independent risk factors of malignant recurrent calcifications in the logistic regression model and marginal statistical significance in the multivariable logistic regression (MLR) model. Conclusion The interval development of pleomorphic calcifications after BCS with either linear or segmental pattern, positive resection margins, and associated calcifications in primary tumors was related to the increase in the risk of recurrence. Although amorphous and coarse heterogeneous morphology with grouped distribution showed benign outcomes, stereotactic biopsy is recommended to exclude disease recurrence in this high-risk patient population.

Dynamic contrast-enhanced breast magnetic resonance imaging findings that affect the magnetic resonance-directed ultrasound correlation of non-mass enhancement lesions: a single-center retrospective study

OBJECTIVE

Our single-center retrospective study aimed to evaluate the relationship between magnetic resonance (MR)-directed ultrasound (MDUS) detectability and MRI findings of non-mass enhancement (NME) lesions, regarding the morphologic and enhancement features, the distance from the skin and nipple, and the presence of concomitant landmarks.

METHODS

A total of 350 MRI-detected NME lesions that were determined between January 2015 and May 2019 and subsequently underwent MDUS were analyzed. The MRI findings, biopsy results, and follow-up outcomes of lesions were recorded. The correlation between the MRI findings of the lesions and MDUS detectability was analyzed.

RESULTS

114 (32.6%) of the 350 lesions had a counterpart in the MDUS. Respectively, 66 (37.9%), 38 (43.2%) and 59 (38.3%) of the lesions detected in MDUS were larger than 20 mm in size, with a distance of less than 20 mm to the nipple and 15 mm to the skin. The lesion size and lesion distance to the nipple and skin were significantly associated with a ultrasound correlate (p < 0.05). The MDUS detection rate was significantly higher in NME lesions with MR findings including diffuse distribution (p < 0.001), clustered-ring enhancement pattern (p < 0.001), washout kinetic curve (p = 0.006), and MR-BIRADS category 5 (p < 0.001). Multivariate logistic regression showed that only the clustered-ring enhancement pattern was significantly associated with an MDUS correlation (p < 0.001).

CONCLUSION

Statistically significant correlations were found between the size, distance to the nipple and skin, distribution pattern, enhancement pattern and kinetic curve of the NME lesions on MRI and ultrasound detectability.

ADVANCES IN KNOWLEDGE

We found that clustered-ring enhancement patterns were significantly more frequent in MR-directed ultrasound detectable lesions.

Preoperative Prediction Power of Radiomics for Breast Cancer: A Systemic Review and Meta-Analysis

Background

To evaluate the preoperative predictive value of radiomics in the diagnosis of breast cancer (BC).

Methods

By searching PubMed and Embase libraries, our study identified 19 eligible studies. We conducted a meta-analysis to assess the differential value in the preoperative assessment of BC using radiomics methods.

Results

Nineteen radiomics studies focusing on the diagnostic efficacy of BC and involving 5865 patients were enrolled. The integrated sensitivity and specificity were 0.84 (95% CI: 0.80–0.87, I^{2 =} 76.44%) and 0.83 (95% CI: 0.78–0.87, I^{2 =} 81.79%), respectively. The AUC based on the SROC curve was 0.91, indicating a high diagnostic value.

Conclusion

Radiomics has shown excellent diagnostic performance in the preoperative prediction of BC and is expected to be a promising method in clinical practice.

Plasma Growth Factor Gene Expression and Mammographic Breast Density in Postmenopausal Women

Mammographic breast density (MBD) is a risk factor for breast cancer, but its molecular basis is poorly understood. Growth factors stimulate cellular and epithelial proliferation and could influence MBD via these mechanisms. Studies investigating the associations of circulating growth factors with MBD have, however, yielded conflicting results especially in postmenopausal women. We, therefore, investigated the associations of plasma growth factor gene expression (IGF-1, IGFBP-3, FGF-1, FGF-12, TGFB-1 and BMP-2) with MBD in postmenopausal women. We used NanoString nCounter platform to quantify plasma growth factor gene expression and Volpara to evaluate volumetric MBD measures. We investigated the associations of growth factor gene expression with MBD using both multiple linear regression (fold change) and multinomial logistic regression models, adjusted for potential confounders. The mean age of the 368 women enrolled was 58 years (range: 50-64). In analyses using linear regression models, one unit increase in IGF-1 gene expression was associated with a 35% higher VPD (1.35, 95%CI 1.13-1.60, p-value=0.001). There were suggestions that TGFB-1 gene expression was positively associated with VPD while BMP gene expression was inversely associated with VPD, but these were not statistically significant. In analyses using multinomial logistic regression, TGFB-1 gene expression was 33% higher (OR=1.33, 95%CI 1.13-1.56, p-value=0.0008) in women with extremely dense breasts than those with almost entirely fatty breasts. There were no associations between growth factor gene expression and dense volume or non-dense volume. Our study provides insights into the associations of growth factors with MBD in postmenopausal women and require confirmation in other study populations.

A High-Performance Deep Neural Network Model for BI-RADS Classification of Screening Mammography

Globally, the incidence rate for breast cancer ranks first. Treatment for early-stage breast cancer is highly cost effective. Five-year survival rate for stage 0-2 breast cancer exceeds 90%. Screening mammography has been acknowledged as the most reliable way to diagnose breast cancer at an early stage. Taiwan government has been urging women without any symptoms, aged between 45 and 69, to have a screening mammogram bi-yearly. This brings about a large workload for radiologists. In light of this, this paper presents a deep neural network (DNN)-based model as an efficient and reliable tool to assist radiologists with mammographic interpretation. For the first time in the literature, mammograms are completely classified into BI-RADS categories 0, 1, 2, 3, 4A, 4B, 4C and 5. The proposed model was trained using block-based images segmented from a mammogram dataset of our own. A block-based image was applied to the model as an input, and a BI-RADS category was predicted as an output. At the end of this paper, the outperformance of this work is demonstrated by an overall accuracy of 94.22%, an average sensitivity of 95.31%, an average specificity of 99.15% and an area under curve (AUC) of 0.9723. When applied to breast cancer screening for Asian women who are more likely to have dense breasts, this model is expected to give a higher accuracy than others in the literature, since it was trained using mammograms taken from Taiwanese women.

Sonographic focally thick duct of breast found in screening, why is it concerning? A report of three cases

We report three cases of focally thickened ductal lesions found on screening ultrasonography with fine needle aspiration (FNA)-proven benign cytology in order to demonstrate the different fates of this radiographic finding. All three patients, aged 74, 69 and 68 years old, had their first time mammography and concurrent ultrasonography. Their mammograms did not show abnormalities except a focal asymmetry in one case. The sonographic focally thick ducts were the lesions of concern and all the patients had long-term follow-up.One patient had a slightly decreased lesion size on follow-up, likely to be a non-proliferative alteration of the breast. One patient's FNA revealed a benign papillary lesion whose ductal diameter slightly increased in size with internal echo after two years with repeat FNA demonstrating epithelial papillae consistent with intraductal papilloma. The final patient had an alteration of the imaged ductal lesion in the third year of follow-up and the final specimen after surgical wide excision that was done in the fourth year confirmed cancer. We emphasize the importance of focally thickened ductal lesions found on screening sonography and underscore their need for scrutinized characterization and long term follow-up.

Microwave Imaging in Breast Cancer - Results from the First-In-Human Clinical Investigation of the Wavelia System

RATIONALE AND OBJECTIVES

Microwave Breast Imaging (MBI) is an emerging non-ionising technology with the potential to detect breast pathology. The investigational device considered in this article is a low-power electromagnetic wave MBI prototype that demonstrated the ability to detect dielectric contrast between tumour phantoms and synthetic fibroglandular tissue in preclinical studies. Herein, we evaluate the MBI system in the clinical setting. The capacity of the MBI system to detect and localise breast tumours in addition to benign breast pathology is assessed. Secondly, the safety profile and patient experience of this device is established.

MATERIALS AND METHODS

Female patients were recruited from the symptomatic unit to 1 of 3 groups: Biopsy-proven breast cancers (Group-1), unaspirated cysts (Group-2) and biopsy-proven benign breast lesions (Group-3). Breast Density was determined by Volpara VDM (Volumetric Density Measurement) Software. MBI, radiological, pathological and histological findings were reviewed. Subjects were surveyed to assess patient experience.

RESULTS

A total of 25 patients underwent MBI. 24 of these were included in final data analysis (11 Group-1, 8 Group-2 and 5 Group-3). The MBI system detected and localised 12 of 13 benign breast lesions, and 9 out of the 11 breast cancers. This included 1 case of a radiographically occult invasive lobular cancer. No device related adverse events were recorded. 92% (n = 23) of women reported that they would recommend MBI imaging to other women.

CONCLUSION

The MBI system detected and localized the majority of breast lesions. This modality may have the potential to offer a non-invasive, non-ionizing and painless adjunct to breast cancer diagnosis. Further larger studies are required to validate the findings of this study.

The Utility of the Fifth Edition of the BI-RADS Ultrasound Lexicon in Category 4 Breast Lesions: A Prospective Multicenter Study in China

RATIONALE AND OBJECTIVES

The objective of this study was to evaluate the utility of the fifth edition of the Breast Imaging-Reporting and Data System (BI-RADS) in clinical breast radiology by using prospective multicenter real-time analyses of ultrasound (US) images.

MATERIALS AND METHODS

We prospectively studied 2049 female patients (age range, 19-86 years; mean age 46.88 years) with BI-RADS category 4 breast masses in 32 tertiary hospitals. All the patients underwent B-mode, color Doppler US, and US elastography examination. US features of the mass and associated features were described and categorized according to the fifth edition of the BI-RADS US lexicon. The pathological results were used as the reference standard. The positive predictive values (PPVs) of subcategories 4a-4c were calculated.

RESULTS

A total of 2094 masses were obtained, including 1124 benign masses (54.9%) and 925 malignant masses (45.1%). For BI-RADS US features of mass shape, orientation, margin, posterior features, calcifications, architectural distortion, edema, skin changes, vascularity, and elasticity assessment were significantly different for benign and malignant masses (p< 0.05). Typical signs of malignancy were irregular shape (PPV, 57.2%), spiculated margin (PPV, 83.7%), nonparallel orientation (PPV, 63.9%), and combined pattern of posterior features (PPV, 60.6%). For the changed or newly added US features, the PPVs for intraductal calcifications were 80%, 56.4% for internal vascularity, and 80% for a hard pattern on elastography. The associated features such as architectural distortion (PPV, 89.3%), edema (PPV, 69.2%), and skin changes (PPV, 76.2%) displayed high predictive value for malignancy. The rate of malignant was 7.4% (72/975) in category 4a, 61.4% (283/461) in category 4b, and 93.0% (570/613) in category 4c. The PPV for category 4b was higher than the likelihood ranges specified in BI-RADS and the PPVs for categories 4a and 4c were within the acceptable performance ranges specified in the fifth edition of BI-RADS in our study.

CONCLUSION

Not only the US features of the breast mass, but also associated features, including vascularity and elasticity assessment, have become an indispensable part of the fifth edition of BI-RADS US lexicon to distinguish benign and malignant breast lesions. The subdivision of category 4 lesions into categories 4a, 4b, and 4c for US findings is helpful for further assessment of the likelihood of malignancy of breast lesions.

Ipsilateral microcalcifications after breast-conserving surgery: is it possible to differentiate benign from malignant calcifications?

AIM

To analyse stereotactic biopsies of microcalcifications in patients with previous ipsilateral breast-conserving surgery (BCS) to identify the positivity rate, assess for an association between the patient's primary cancer or mammographic appearances of the microcalcifications, and the risk of recurrence.

MATERIALS AND METHODS

Relevant patients from 2018-2020 were identified via a retrospective review of the prospectively maintained radiological procedure database. Clinicopathological features of the patients' primary tumour and new calcifications were obtained from the hospital electronic patient record system and the national integrated medical imaging system.

RESULTS

Thirty-one percent of recurrences post-ipsilateral BCS presented as isolated microcalcifications on mammography. Fifty-three percent of patients undergoing stereotactic biopsy of ipsilateral calcifications had recurrence. A positive margin status was associated with new or recurrent malignancy. There was no significant correlation between oestrogen-receptor status, sentinel lymph node status, adjuvant radiotherapy or chemotherapy and the risk of recurrence. Calcifications within the tumour bed were more likely to be benign while calcifications within the same quadrant but remote from the tumour bed were more likely malignant. All coarse calcifications were benign while 67% of fine linear/fine linear branching and 89% of fine pleomorphic calcifications were malignant.

CONCLUSION

Increased time since diagnosis, positive margin status, fine pleomorphic and fine linear calcifications in the same quadrant as the tumour bed were associated with malignancy. Patients with coarse calcifications and calcifications within the tumour bed may avoid stereotactic biopsy and undergo short-interval surveillance.

The Potential Value of Texture Analysis Based on Dynamic Contrast-Enhanced MR Images in the Grading of Breast Phyllode Tumors

Purpose

To explore the value of texture analysis (TA) based on dynamic contrast-enhanced MR (DCE-MR) images in the differential diagnosis of benign phyllode tumors (BPTs) and borderline/malignant phyllode tumors (BMPTs).

Methods

A total of 47 patients with histologically proven phyllode tumors (PTs) from November 2012 to March 2020, including 26 benign BPTs and 21 BMPTs, were enrolled in this retrospective study. The whole-tumor texture features based on DCE-MR images were calculated, and conventional imaging findings were evaluated according to the Breast Imaging Reporting and Data System (BI-RADS). The differences in the texture features and imaging findings between BPTs and BMPTs were compared; the variates with statistical significance were entered into logistic regression analysis. The receiver operating characteristic (ROC) curve was used to assess the diagnostic performance of models from image-based analysis, TA, and the combination of these two approaches.

Results

Regarding texture features, three features of the histogram, two features of the gray-level co-occurrence matrix (GLCM), and three features of the run-length matrix (RLM) showed significant differences between the two groups (all p < 0.05). Regarding imaging findings, however, only cystic wall morphology showed significant differences between the two groups (p = 0.014). The areas under the ROC curve (AUCs) of image-based analysis, TA, and the combination of these two approaches were 0.687 (95% CI, 0.518–0.825, p = 0.014), 0.886 (95% CI, 0.760–0.960, p < 0.0001), and 0.894 (95% CI, 0.754–0.970, p < 0.0001), respectively.

Conclusion

TA based on DCE-MR images has potential in differentiating BPTs and BMPTs.

High Precision Mammography Lesion Identification From Imprecise Medical Annotations

Breast cancer screening using Mammography serves as the earliest defense against breast cancer, revealing anomalous tissue years before it can be detected through physical screening. Despite the use of high resolution radiography, the presence of densely overlapping patterns challenges the consistency of human-driven diagnosis and drives interest in leveraging state-of-art localization ability of deep convolutional neural networks (DCNN). The growing availability of digitized clinical archives enables the training of deep segmentation models, but training using the most widely available form of coarse hand-drawn annotations works against learning the precise boundary of cancerous tissue in evaluation, while producing results that are more aligned with the annotations rather than the underlying lesions. The expense of collecting high quality pixel-level data in the field of medical science makes this even more difficult. To surmount this fundamental challenge, we propose LatentCADx, a deep learning segmentation model capable of precisely annotating cancer lesions underlying hand-drawn annotations, which we procedurally obtain using joint classification training and a strict segmentation penalty. We demonstrate the capability of LatentCADx on a publicly available dataset of 2,620 Mammogram case files, where LatentCADx obtains classification ROC of 0.97, AP of 0.87, and segmentation AP of 0.75 (IOU = 0.5), giving comparable or better performance than other models. Qualitative and precision evaluation of LatentCADx annotations on validation samples reveals that LatentCADx increases the specificity of segmentations beyond that of existing models trained on hand-drawn annotations, with pixel level specificity reaching a staggering value of 0.90. It also obtains sharp boundary around lesions unlike other methods, reducing the confused pixels in the output by more than 60%.

The diagnostic accuracy of diffusion-weighted magnetic resonance imaging and shear wave elastography in comparison to dynamic contrast-enhanced MRI for diagnosing BIRADS 3 and 4 lesions

Background

Breast cancer is one of the leading causes of female morbidity and mortality. Management options vary between lesions of BIRADS categories 3 and 4. Therefore, reliable differentiation would improve outcome. Although sonomammography and contrast-enhanced breast magnetic resonance imaging (CE-MRI) remain the cornerstone for assessment of breast disease, additional, non-invasive techniques can be used to increase the efficiency of evaluation such as shear wave elastography (SWE) and diffusion-weighted magnetic resonance imaging (DW-MRI). This prospective study included 66 breast lesions that were categorized as BIRADS 3 or 4 by ultrasound ± mammography. All lesions were evaluated by SWE, CE-MRI and DW-MRI. For SWE, lesions were evaluated by both qualitative and quantitative methods. For CE-MRI, both morphological and kinematic evaluations were done and for DW-MRI, both qualitative and quantitative assessments were studied. Results of all imaging modalities were correlated to histopathology.

Results

Thirty-seven out of the examined 66 lesions (56.06%) were categorised as BIRADS 3, out of which 1 (2.7%) turned out to be malignant on histopathology and 36 (97.29%) were proved benign. Twenty-nine (43.93%) were categorized as BIRADS 4, out of which 2 (6.89%) turned out to be benign on pathology and 27 (93.1%) were proved malignant. Morphological and kinematic evaluations of CE-MRI showed 92.59% and 92.86%sensitivity, 94.74% and 84.21% specificity, 92.59 and 81.25%PPV, 94.74 and 94.12% NPV, and 93.85% and 87.88% accuracy respectively. Color-coded scoring of SWE showed indices of 89.29%, 68.42%, 67.57%, 89.66%, and 77.27% respectively. The calculated cut-off value for Emax differentiating benign from malignant was 65.15 kpa, resulting in indices of 96.43%, 57.89%, 95.65%, 62.79%, and 74.24% respectively. For Eratio, the calculated cut-off value was 4.55, resulting in indices of 71.43%, 68.42%, 76.47%, 62.50% and 69.70% respectively. For qualitative evaluation of DW-MRI, indices were 78.57%, 65.79%, 62.86%, 80.65%, and 71.21% respectively. For ADC, the calculated cut-off value was 1.25 × 103 mm2/s, which resulted in indices of 75.00%, 84.21%, 82.05%, 77.78%, and 80.30% respectively.

Conclusion

CE-MRI showed the best diagnostic performance indices. While, SWE and DW-MRI present variable diagnostic performance, both techniques can be used as an adjunct to other imaging modalities to aid the clinical decision and increase its diagnostic confidence.

Imaging temporomandibular disorders: Reliability of a novel MRI-based scoring system

The aim of this study was to assess the inter- and intrarater reliability of a recently proposed scoring system for temporomandibular disorders (TMD), based upon radiological findings from magnetic resonance imaging (MRI). Patients with clinically suspected uni- or bilateral TMD, and subsequently conducted MRI examination of both temporomandibular joints, were included in this study. MRI data were independently evaluated by two experienced radiologists according to the DLJ scoring system proposed by Wurm et al., which includes assessment of the following categories: articular disk (prefix 'D'), direction of disk luxation (prefix 'L'), and osseous joint alterations (prefix 'J'). 60 patients (49 female and 11 male) were eligible for analysis. No significant differences were found between both observers regarding 'D' and 'L' scores (p = 0.13 and p = 0.59, respectively). Significant differences were found for the assessment of subtle osseous changes ('J0' category: p = 0.041; 'J1' category: p = 0.018). Almost perfect intra- and interrater agreements were found for 'D' and 'L' categories (intrarater and interrater agreements for 'D': κ = 0.92 and κ = 0.84, respectively; intrarater and interrater agreements for 'L': κ = 0.93 and κ = 0.89, respectively). However, the assessment of 'J' categories revealed only moderate interrater agreement (κ = 0.49). The DLJ scoring system based upon MRI findings is feasible for routine clinical TMD assessment, and may help to simplify interdisciplinary communication between radiologists and clinicians.

Utility of Digital Breast Tomosynthesis with Two-Dimensional Synthesized Mammography Images: A Pictorial Essay

Background  Mammography has been established as the key modality in the detection and diagnosis of breast cancers. Digital breast tomosynthesis (DBT) has emerged as a mammographic technique which allows improved visualization of abnormalities by reducing the effect of overlapping breast tissue.

Purpose  This article is a pictorial essay which highlights the advantages of DBT with two-dimensional (2D) synthesized mammography (2DSM) images, its clinical applications, and its role in breast imaging.

Materials and Methods  Selenia Dimensions HD mammography machine performs DBT which acquires a series of low-dose digital mammographic images of the compressed breast followed by full-field digital mammography. Software using specialized algorithms helps to create a 2DSM image reconstructed from the DBT data set. The images are interpreted on a dedicated work station on high-resolution monitors by the radiologist. American College of Radiology Breast Imaging-Reporting and Data System (BI-RADS) lexicon is used for reporting. High-resolution breast ultrasound which includes evaluation of the axilla is done for all cases.

Conclusion  DBT improves detection and better characterization of lesions which thereby increases confidence of interpretation of mammograms and assigning BI-RADS categories for further management.

Does circulating progesterone mediate the associations of single nucleotide polymorphisms in progesterone receptor (PGR)-related genes with mammographic breast density in premenopausal women?

Progesterone is a proliferative hormone in the breast but the associations of genetic variations in progesterone-regulated pathways with mammographic breast density (MD) in premenopausal women and whether these associations are mediated through circulating progesterone are not clearly defined. We, therefore, investigated these associations in 364 premenopausal women with a median age of 44 years. We sequenced 179 progesterone receptor (PGR)-related single nucleotide polymorphisms (SNPs). We measured volumetric percent density (VPD) and non-dense volume (NDV) using Volpara. Linear regression models were fit on circulating progesterone or VPD/NDV separately. We performed mediation analysis to evaluate whether the effect of a SNP on VPD/NDV is mediated through circulating progesterone. All analyses were adjusted for confounders, phase of menstrual cycle and the Benjamini-Hochberg false discovery (FDR) adjusted p-value was applied to correct for multiple testing. In multivariable analyses, only PGR rs657516 had a direct effect on VPD (averaged direct effect estimate = - 0.20, 95%CI = - 0.38 ~ - 0.04, p-value = 0.02) but this was not statistically significant after FDR correction and the effect was not mediated by circulating progesterone (mediation effect averaged across the two genotypes = 0.01, 95%CI = - 0.02 ~ 0.03, p-value = 0.70). Five SNPs (PGR rs11571241, rs11571239, rs1824128, rs11571150, PGRMC1 rs41294894) were associated with circulating progesterone but these were not statistically significant after FDR correction. SNPs in PGR-related genes were not associated with VPD, NDV and circulating progesterone did not mediate the associations, suggesting that the effects, if any, of these SNPs on MD are independent of circulating progesterone.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s12672-021-00438-1.

Predicting the molecular subtype of breast cancer and identifying interpretable imaging features using machine learning algorithms

OBJECTIVES

To evaluate the performance of interpretable machine learning models in predicting breast cancer molecular subtypes.

METHODS

We retrospectively enrolled 600 patients with invasive breast carcinoma between 2012 and 2019. The patients were randomly divided into a training (n = 450) and a testing (n = 150) set. The five constructed models were trained based on clinical characteristics and imaging features (mammography and ultrasonography). The model classification performances were evaluated using the area under the receiver operating characteristic (ROC) curve (AUC), accuracy, sensitivity, and specificity. Shapley additive explanation (SHAP) technique was used to interpret the optimal model output. Then we choose the optimal model as the assisted model to evaluate the performance of another four radiologists in predicting the molecular subtype of breast cancer with or without model assistance, according to mammography and ultrasound images.

RESULTS

The decision tree (DT) model performed the best in distinguishing triple-negative breast cancer (TNBC) from other breast cancer subtypes, yielding an AUC of 0.971; accuracy, 0.947; sensitivity, 0.905; and specificity, 0.941. The accuracy, sensitivity, and specificity of all radiologists in distinguishing TNBC from other molecular subtypes and Luminal breast cancer from other molecular subtypes have significantly improved with the assistance of DT model. In the diagnosis of TNBC versus other subtypes, the average sensitivity, average specificity, and average accuracy of less experienced and more experienced radiologists increased by 0.090, 0.125, 0.114, and 0.060, 0.090, 0.083, respectively. In the diagnosis of Luminal versus other subtypes, the average sensitivity, average specificity, and average accuracy of less experienced and more experienced radiologists increased by 0.084, 0.152, 0.159, and 0.020, 0.100, 0.048.

CONCLUSIONS

This study established an interpretable machine learning model to differentiate between breast cancer molecular subtypes, providing additional values for radiologists.

KEY POINTS

• Interpretable machine learning model (MLM) could help clinicians and radiologists differentiate between breast cancer molecular subtypes. • The Shapley additive explanations (SHAP) technique can select important features for predicting the molecular subtypes of breast cancer from a large number of imaging signs. • Machine learning model can assist radiologists to evaluate the molecular subtype of breast cancer to some extent.