Incorporating diffusion-weighted imaging in a diagnostic algorithm for multiparametric MR mammography

BACKGROUND

Apparent diffusion coefficient (ADC) measurements are not incorporated in BI-RADS classification.

PURPOSE

To assess the probability of malignancy of breast lesions at magnetic resonance mammography (MRM) at 3 T, by combining ADC measurements with the BI-RADS score, in order to improve the specificity of MRM.

MATERIAL AND METHODS

A total of 296 biopsy-proven breast lesions were included in this prospective study. MRM was performed at 3 T, using a standard protocol with dynamic sequence (DCE-MRI) and an extra echo-planar diffusion-weighted sequence. A freehand region of interest was drawn inside the lesion, and ADC values were calculated. Each lesion was categorized according to the BI-RADS classification. Logistic regression analysis was employed to predict the probability of malignancy of a lesion. The model combined the BI-RADS classification and the ADC value. Sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy were calculated.

RESULTS

In total, 153 malignant and 143 benign lesions were analyzed; 257 lesions were masses and 39 lesions were non-mass-like enhancements. The sensitivity and specificity of the combined method were 96% and 86%, respectively, in contrast to 95% and 81% with BI-RADS classification alone.

CONCLUSION

We propose a method of assessing the probability of malignancy in breast lesions by combining BI-RADS score and ADC values into a single formula, increasing sensitivity and specificity compared to BI-RADS classification alone.

BI-RADS-NET: AN EXPLAINABLE MULTITASK LEARNING APPROACH FOR CANCER DIAGNOSIS IN BREAST ULTRASOUND IMAGES

In healthcare, it is essential to explain the decision-making process of machine learning models to establish the trustworthiness of clinicians. This paper introduces BI-RADS-Net, a novel explainable deep learning approach for cancer detection in breast ultrasound images. The proposed approach incorporates tasks for explaining and classifying breast tumors, by learning feature representations relevant to clinical diagnosis. Explanations of the predictions (benign or malignant) are provided in terms of morphological features that are used by clinicians for diagnosis and reporting in medical practice. The employed features include the BI-RADS descriptors of shape, orientation, margin, echo pattern, and posterior features. Additionally, our approach predicts the likelihood of malignancy of the findings, which relates to the BI-RADS assessment category reported by clinicians. Experimental validation on a dataset consisting of 1,192 images indicates improved model accuracy, supported by explanations in clinical terms using the BI-RADS lexicon.

You'll see it when you know it: granulomatous mastitis

Granulomatous mastitis (GM) is an under-recognized and under-diagnosed disease. Patients with GM often present to the emergency room with a painful breast mass, nipple retraction, and skin changes. This pictorial essay will review the clinical presentation and imaging appearance of GM, BI-RADS reporting parameters, differential diagnoses, and diagnostic challenges posed by this disease. Early and accurate diagnosis is essential, as misdiagnosis can result in repeated core biopsies, leading to fistulae and sinus tract formation. A classic history and typical sonographic appearance allow the emergency radiologist to confidently make this diagnosis.

Quantitative breast density measurement based on three-dimensional images: a study on cone-beam breast computed tomography

BACKGROUND

Breast density is an independent predictor of breast cancer risk. Quantitative volumetric breast density (QVBD) is expected to provide more information on the prediction of breast cancer risk.

PURPOSE

To evaluate the reliability of QVBD measurements based on cone-beam breast computed tomography (CBBCT) images.

MATERIAL AND METHODS

A total of 216 breasts were used to evaluate the stability of QVBD measurements based on CBBCT images and the correlations between this volumetric measurement and visual and area-based measurement methods. The intra- and inter-observer consistency of QVBD measurements were compared. Visual breast density (VBD) was evaluated with Breast Imaging Reporting and Data System (BI-RADS) standard on CBBCT images. The correlation between QVBD and VBD was evaluated by Spearman correlation coefficient. Receiver operating characteristic (ROC) curve was used to assess the sensitivity and specificity of the volumetric method in distinguishing dense and non-dense breasts. The correlation between QVBD and quantitative area-based breast density (QABD) was determined with Pearson correlation coefficient. Then, the breast volume measured with CBBCT images was compared with the breast specimen obtained during nipple-sparing mastectomy (NSM) by Pearson correlation coefficient and linear regression.

RESULTS

Excellent intra- and inter-observer consistency was found from QVBD measurements. The volumetric method distinguished dense and non-dense breasts at a cutoff value of 9.5%, with 94.5% sensitivity and 77.1% specificity. Positive correlations were found between QVBD and QABD (r=0.890; P<0.001) and between the volume measured with CBBCT images and Archimedes method (r=0.969; P<0.001).

CONCLUSION

CBBCT images can evaluate breast density reliably on a continuous scale.

Principal component regression-based contrast-enhanced ultrasound evaluation system for the management of BI-RADS US 4A breast masses: objective assistance for radiologists

A portion of detected breast masses might be overrated by using the Breast Imaging-Reporting and Data System ultrasonography (BI-RADS US) lexicon. A principal component regression-based contrast-enhanced ultrasound (PCR-CEUS) evaluation system was built to quantitatively illustrate whether CEUS could help radiologists to differentiate 4A masses. The PCR-CEUS evaluation system, based on principal component analysis (PCA) and logistic regression, was verified by random assignment into training and test sets and shown to reduce the data dimension and avoid collinearity in CEUS variables. This prospective study consecutively collected 238 patients with 238 4A masses confirmed pathologically. All enrolled patients accepted CEUS examination. The diagnostic performance of senior and junior radiologists, PCR-CEUS and combined methods was compared. The PCR-CEUS system had consistent diagnostic performance in both the training and test sets, with an area under the curve (AUC) of 0.831 (0.765-0.897), 0.798 (0.7034-0.892) and 0.854 (0.765-0.943) (all P > 0.05). The AUC of the combined diagnostic model (PCR-CEUS + Senior radiologists) was higher than that of senior radiologists, and the combined model had higher sensitivity (0.875 (0.781-0.969) vs. 0.729 (0.603-0.855)) without compromising specificity. Furthermore, the AUC and specificity of the combined model (PCR-CEUS + Junior radiologists) (0.852 (0.787-0.916)) was higher than that of junior radiologists (0.665 (0.592-0.737) (P < 0.00001)). PCR-CEUS demonstrated good ability in differentiating malignant BI-RADS-US 4A masses and was helpful for both senior and junior radiologists.

Superb Microvascular Imaging Technology Can Improve the Diagnostic Efficiency of the BI-RADS System

BACKGROUND

To explore whether superb microvascular imaging (SMI)SMI can improve the diagnostic efficiency by evaluating the vascular index (VI) and vascular architecture (VA) in breast lesions.

METHODS

This is a retrospective study of data collected prospectively for research use. Taking 225 consecutive cases of breast lesions from November 2016 to December 2017 as a training set, the VI values and VA types of benign and malignant lesions were calculated based on the pathological results. Taking 238 consecutive cases of breast lesions from January 2018 to October 2018 as the verification set, the diagnostic sensitivity, specificity, accuracy, positive predictive value (PPV) and negative predictive value (NPV) were calculated to compare the diagnostic efficacy.

RESULTS

The training set included 225 breast lesions and the validation set 238 breast lesions. The VI value in the malignant group (10.3 ± 8.0) was significantly higher than that in the benign group (4.3 ± 5.0)(P<0.001). A VI value of 4.05 was used as the diagnostic threshold for differentiating benign from malignant lesions, with a sensitivity of 80.5%, a specificity of 61.9%, an accuracy of 71.1%, a PPV of 62.9%, a NPV of 76.9%, and an area under the curve of 0.758 (0.696-0.819). There was a significant difference in the types of benign and malignant VA (P < 0.001), and the PPV of the root hair-like and crab claw-like VAs were 93.9% and 100.0%, respectively. The diagnostic sensitivity, specificity, accuracy, PPV, NPV and area under the AUC curve were 58.0%, 98.2%, 97.0%, 70.3% and 0.781, respectively (95%CI: 0.719-0.844). SMI combined with conventional ultrasound improved the diagnostic specificity (70.0% vs. 90.0%), accuracy (87.4% vs. 96.6%), and PPV (82.5% vs. 93.2%) without decreasing the diagnostic sensitivity (99.3%), yielded higher diagnostic performance with the area under the ROC curve was 0.941 (95%CI: 0904-0.979) compared with conventional US alone (P < 0.001).

CONCLUSION

A VI value 4.05 is a cut-off value with good diagnostic efficacy. The residual root-like and crab claw-like VAs are the characteristic VAs of malignant lesions. Conventional ultrasound combined with the VI and VA can improve the diagnostic specificity, accuracy and PPV without reducing the diagnostic sensitivity.

Spatial Distribution and Quantification of Mammographic Breast Density, and Its Correlation with BI-RADS Using an Image Segmentation Method

(1) Background: Mammographic breast density (MBD) and older age are classical breast cancer risk factors. Normally, MBDs are not evenly distributed in the breast, with different women having different spatial distribution and clustering patterns. The presence of MBDs makes tumors and other lesions challenging to be identified in mammograms. The objectives of this study were: (i) to quantify the amount of MBDs—in the whole (overall), different sub-regions, and different zones of the breast using an image segmentation method; (ii) to investigate the spatial distribution patterns of MBD in different sub-regions of the breast. (2) Methods: The image segmentation method was used to quantify the overall amount of MBDs in the whole breast (overall percentage density (PD)), in 48 sub-regions (regional PDs), and three different zones (zonal PDs) of the whole breast, and the results of the amount of MBDs in 48 sub-regional PDs were further analyzed to determine its spatial distribution pattern in the breast using Moran’s I values (spatial autocorrelation). (3) Results: The overall PD showed a negative correlation with age (p = 0.008); the younger women tended to have denser breasts (higher overall PD in breasts). We also found a higher proportion (p < 0.001) of positive autocorrelation pattern in the less dense breast group than in the denser breast group, suggesting that MBDs in the less dense breasts tend to be clustered together. Moreover, we also observed that MBDs in the mature women (<65 years old) tended to be clustered in the middle zone, while in older women (>64 years old) they tended to be clustered in both the posterior and middle zones. (4) Conclusions: There is an inverse relationship between the amount of MBD (overall PD in the breast) and age, and a different clustering pattern of MBDs between the older and mature women.

Use of breast imaging-reporting and data system (BI-RADS) ultrasound classification in pediatric and adolescent patients overestimates likelihood of malignancy

BACKGROUND/PURPOSE

Breast masses in the pediatric population cause patient and family concern, partially driven by public awareness of adult breast cancer. However, the spectrum of breast masses in children differs greatly from that in adults, and malignancy is exceedingly rare. The American College of Radiology Breast Imaging Reporting and Data System (BI-RADS) ultrasound-based classification system is the diagnostic standard, yet no study has validated BI-RADS in pediatric patients. This study compares BI-RADS classification with histologic diagnoses to evaluate BI-RADS validity in pediatric patients.

METHODS

Multicenter retrospective evaluation of breast masses in patients under 21 years. Ultrasound reports were compared with histologic diagnoses.

RESULTS

There were 283 patients with breast pathology results after excluding clinical diagnoses of gynecomastia. Mean age was 16.9 (SD 2.3), ranging 10-20 years. 227 had pre-operative ultrasounds, and 84% (191/227) were assigned a BI-RADS category. BI-RADS 4 was the most frequent category (55%, n = 124), by definition predicting 2 - 95% likelihood of malignancy. However, pathology was benign in all patients.

CONCLUSIONS

The current BI-RADS categorization system overestimates cancer risk when applied to pediatric patients. BI-RADS scores should not be assigned to pediatric patients, and BIRADS-defined recommendations for biopsy should be disregarded. A pediatric-specific classification system could be useful.

Management of Pediatric Breast Masses: A Multi-institutional Retrospective Cohort Study

BACKGROUND

The objective of our study was to describe the workup, management, and outcomes of pediatric patients with breast masses undergoing operative intervention.

MATERIALS AND METHODS

A retrospective cohort study was conducted of girls 10-21 y of age who underwent surgery for a breast mass across 11 children's hospitals from 2011 to 2016. Demographic and clinical characteristics were summarized.

RESULTS

Four hundred and fifty-three female patients with a median age of 16 y (IQR: 3) underwent surgery for a breast mass during the study period. The most common preoperative imaging was breast ultrasound (95%); 28% reported the Breast Imaging Reporting and Data System (BI-RADS) classification. Preoperative core biopsy was performed in 12%. All patients underwent lumpectomy, most commonly due to mass size (45%) or growth (29%). The median maximum dimension of a mass on preoperative ultrasound was 2.8 cm (IQR: 1.9). Most operations were performed by pediatric surgeons (65%) and breast surgeons (25%). The most frequent pathology was fibroadenoma (75%); 3% were phyllodes. BI-RADS scoring ≥4 on breast ultrasound had a sensitivity of 0% and a negative predictive value of 93% for identifying phyllodes tumors.

CONCLUSIONS

Most pediatric breast masses are self-identified and benign. BI-RADS classification based on ultrasound was not consistently assigned and had little clinical utility for identifying phyllodes.

Training Radiologists to Interpret Contrast-enhanced Mammography: Toward a Standardized Lexicon

OBJECTIVE

Using terms adapted from the BI-RADS Mammography and MRI lexicons, we trained radiologists to interpret contrast-enhanced mammography (CEM) and assessed reliability of their description and assessment.

METHODS

A 60-minute presentation on CEM and terminology was reviewed independently by 21 breast imaging radiologist observers. For 21 CEM exams with 31 marked findings, observers recorded background parenchymal enhancement (BPE) (minimal, mild, moderate, marked), lesion type (oval/round or irregular mass, or non-mass enhancement), intensity of enhancement (none, weak, medium, strong), enhancement quality (none, homogeneous, heterogeneous, rim), and BI-RADS assessment category (2, 3, 4A, 4B, 4C, 5). "Expert" consensus of 3 other radiologists experienced in CEM was developed. Kappa statistic was used to assess agreement between radiologists and expert consensus, and between radiologists themselves, on imaging feature categories and final assessments. Reproducibility of specific feature descriptors was assessed as fraction of consensus-concordant responses.

RESULTS

Radiologists demonstrated moderate agreement for BPE, (mean kappa, 0.43; range, 0.05-0.69), and lowest reproducibility for "minimal." Agreement was substantial for lesion type (mean kappa, 0.70; range, 0.47-0.93), moderate for intensity of enhancement (mean kappa, 0.57; range, 0.44-0.76), and moderate for enhancement quality (mean kappa, 0.59; range, 0.20-0.78). Agreement on final assessment was fair (mean kappa, 0.26; range, 0.09-0.44), with BI-RADS category 3 the least reproducible. Decision to biopsy (BI-RADS 2-3 vs 4-5) showed moderate agreement with consensus (mean kappa, 0.54; range, -0.06-0.87).

CONCLUSION

With minimal training, agreement for description of CEM findings by breast imaging radiologists was comparable to other BI-RADS lexicons.

Diagnostic performance of the Kaiser score for characterizing lesions on breast MRI with comparison to a multiparametric classification system

PURPOSE

To determine the diagnostic performance of the Kaiser score and to compare it with the BI-RADS-based multiparametric classification system (MCS).

METHOD

Two breast radiologists, blinded to the clinical and pathological information, separately evaluated a database of 499 consecutive patients with structural 3.0 T breast MRI and 697 histopathologically verified lesions. The Kaiser scores and corresponding MCS categories were recorded. The sensitivity and specificity of the Kaiser score and the MCS categories to differentiate benign from malignant lesions were calculated. The interobserver reproducibility and receiver operating characteristic (ROC) parameters were analysed.

RESULTS

The sensitivity and specificity of the MCS were 100 % and 12 %, respectively, and those of the Kaiser score were 98.5 % and 34.8 % for reader 1 and 98.7 % and 47.5 % for reader 2. The area under the ROC-curve was 85.9 and 87.6 for readers 1 and 2. The interobserver intraclass correlation coefficient was excellent at 0.882. Reader 1 upgraded six lesions from BI-RADS 3 to a Kaiser score of >4, and reader 2 upgraded seven lesions. When applying the Kaiser score to 158 benign lesions readers 1 and 2 would have reduced the biopsy rate by 22.8 % and 35.4 %, respectively.

CONCLUSIONS

The Kaiser score showed high diagnostic accuracy with excellent interobserver reproducibility. The MCS had perfect sensitivity but low specificity. Although the Kaiser score had slightly lower sensitivity, its specificity was 3-4 times greater than that of the MCS. Thus, the Kaiser score has the potential to considerably reduce the biopsy rate for true negative lesions.

Density map and fuzzy classification for breast density by using BI-RADS

Mammographic density (MD) is conformed by a different percentage of stromal, epithelial, and adipose tissue within the breast. One of the most critical findings in mammographic patterns for establishing a diagnosis of breast cancer is high breast tissue density. There is a wide variety of works focused on the study and automatic calculation of general breast density; however, they do not provide more detailed information about the changes that may occur within the breast tissue. This work proposes to generate a breast density map based on a texture analysis to identify the internal composition and distribution of the breast tissue through the diffuse division technique of the different densities inside the breast. Therefore, it is possible to obtain a density map associated with the breast that allows us to distinguish and quantify the different types of breast densities and their distribution according to the Breast Imaging Reporting and Data System (BI-RADS Breast Density Category). The proposed methodology was tested with mammograms from the BCDR and InBreast databases, demonstrating consistency in results and reaching an accuracy of 84.2% and 81.3%, respectively. Finally, the information obtained from the density map and its analysis could be a support tool for the specialist physician to monitor changes in breast density over time, since the fuzzy classification carried out allows quantifying the degree of membership in the BI-RADS breast density classes.

Effects of gadobutrol on background parenchymal enhancement and differential diagnosis between benign and malignant lesions in dynamic magnetic resonance imaging of the breast

BACKGROUND

The high concentration of gadolinium in gadobutrol, which is widely used in Japan, helps visualize signal enhancement of neoplastic lesions, however, there was concern that high T1 relaxivity could decrease the contrast between the lesion and the background mammary gland. We evaluate the effect of gadobutrol on background parenchymal enhancement (BPE) and differential diagnosis between benign and malignant lesions in dynamic MRI of the breast.

METHODS

Ninety-nine patients were enrolled prospectively. Measurements of the following signal intensities (SIs) were obtained: breast tissue on a pre-contrast image (SI_pre) and an early-phase image (SI_early); and the SIs of breast cancer on a pre-contrast image (SI_pre-cancer) and an early-phase image (SI_early-cancer). We calculated the BPE ratio, i.e., (SI_early - SI_pre)/SI_pre and the cancer/BPE ratio, i.e., (SI_early-cancer - SI_pre-cancer)/(SI_early on the affected side - SI_pre on the affected side). These quantitative assessments were compared with the data from the recently published multicenter study (reference study without use of gadobutrol). In addition, two radiologists reinterpreted each of the MR images, and a third radiologist set the ROIs in the lesions and performed kinetic analysis as a Reader 3.

RESULTS

While there was no significant difference in the SI of breast cancer in the premenopausal patients between the two studies, that in postmenopausal patients was significantly higher in the present study than in the reference study (p = 0.002). Although there was no significant difference in the cancer/BPE ratio in the postmenopausal patients between the two studies, the cancer/BPE ratio in the premenopausal patients was significantly higher in the reference study than in the present study (p = 0.028). For differentiation between benign and malignant masses, the mass margin was found to be the most important term (p < 0.001). According to the data of Reader 3, visual washout was observed in all 18 patients in whom the interpretation was changed from "plateau" to "washout".

CONCLUSIONS

Gadobutrol may decrease the contrast between breast cancer and background parenchyma in premenopausal patients, and it may have a characteristic that "washout" does not easily occur, leading to "plateau" in patients with breast cancer.

Qualitative characterization of breast tumors with diffusion-weighted imaging has comparable accuracy to quantitative analysis

PURPOSE

To evaluate the applicability and accuracy of a new qualitative diffusion-weighted imaging (DWI) assessment method in the characterization of breast tumors compared to quantitative ADC measurement and dynamic contrast enhanced magnetic resonance imaging (DCE-MRI).

MATERIALS AND METHODS

After review board approval, MRIs of 216 consecutive women with final diagnoses (131 malignant, 85 benign) were retrospectively analyzed. Two radiologists independently scored DWI and dynamic contrast-enhanced MRI (DCE-MRI) according to malignancy probability. Qualitative assessments were performed by combined analysis of tumor morphology and diffusion signal. Quantitative data was obtained from apparent diffusion coefficient (ADC) measurements. Lastly, descriptive DWI features were evaluated and recorded. Cohen's kappa, receiver operating characteristic and multivariate analyzes were applied.

RESULTS

Of malignant tumors, 97% were visible on DWI. Qualitative and quantitative DWI assessments provided comparable sensitivities of 89-94% and 88-92% and specificities of 51-61% and 59-67%, respectively. There was no statistical difference between the accuracies of qualitative and quantitative DWI (p ≥ 0.105). Best diagnostic values were obtained with DCE-MRI (sensitivity, 99-100%; specificity, 69-71%). Inter-reader agreement was moderate (kappa = 0.597) for qualitative DWI and substantial (kappa = 0.689) for DCE-MRI (p < 0.001). Agreement between qualitative DWI and DCE-MRI scores was moderate (kappa = 0.536 and 0.442). Visual diffusion signal, mass margin and shape were the most predictive features of malignancy on multivariate analysis of qualitative assessment.

CONCLUSION

Qualitative characterization of breast tumors on DWI has comparable accuracy to quantitative ADC analysis. This method might be used to make DWI more widely available with eliminating the need to a predetermined ADC threshold in tumor characterization. However, lower accuracy and inter-reader agreement of it compared to DCE-MRI should be considered.

The mammographic breast density distribution of Finnish women with breast cancer and comparison of breast density reporting using the 4th and 5th editions of the Breast Imaging-Reporting and Data System

PURPOSE

To examine the breast density distribution in patients diagnosed with breast cancer in an eastern Finnish population and to examine the changes in breast density reporting patterns between the 4^th and 5^th editions of the Breast Imaging-Reporting and Data System (BI-RADS).

METHOD

821 women (mean age 62.8 ± 12.2 years, range 28-94 years) with breast cancer were included in this retrospective study and their digital mammographic examinations were assessed semi-automatically and then visually by two radiologists in accordance with the 4^th and 5^th editions of the BI-RADS. Intraclass correlation coefficients (ICCs) were used to evaluate interobserver reproducibility. Chi-square tests were used to examine the associations between the breast density distribution and age or body mass index (BMI).

RESULTS

Interobserver reproducibility of the visual assessment was excellent, with an ICCr = 0.93. The majority of breast cancers occurred in fatty breasts (93.8 %) when density was assessed according to the 4^th edition of the BI-RADS. The distributions remained constant after correction for age and BMI. Using the 5^th edition, there was an overall 50.2 % decrease in almost entirely fatty (p <  0.001), 19.4 % increase in scattered fibroglandular (p <  0.001), 28.7 % increase in heterogeneously dense (p <  0.001), and 2.1 % increase in extremely dense (p <  0.001) categories.

CONCLUSIONS

Most breast cancers in eastern Finland occur in fatty breasts with an area density of < 50 %. Assessing breast density using the 5^th edition of the BI-RADS greatly increased denser assessments.

Association between changes in mammographic density category and the risk of breast cancer: A nationwide cohort study in East-Asian women

Breast density is strongly associated with breast cancer risk; however, studies on the association between density changes and breast cancer risk have controversial results. The aim of our study was to determine the association between breast density changes and breast cancer risk in East-Asian women. We included 3 301 279 women aged ≥40 years screened for breast cancer twice during 2009 to 2010 and 2011 to 2012. Data were obtained from the National Health Insurance Service (NHIS) database. Breast density was evaluated using the Breast Imaging-Reporting and Data System (BI-RADS). Relative risk (RR) and 5-year risk of developing breast cancer according to density category changes were calculated. Overall, 23.0% of the women had a higher breast density and 22.2% of the women had a lower breast density in second screening compared to the first. An increase in the BI-RADS density category between two subsequent mammographic screenings was associated with an increase in breast cancer risk and vice versa in terms of RR. The 5-year breast cancer risk was affected by the initial BI-RADS density category, changes in density category and patients' characteristics such as age, menopausal status and family history of breast cancer. In patients with breast cancer family history, the 5-year breast cancer risk was prominent, at a maximum of 2.39% (95% CI = 1.23-3.55) in women with breast density category of 2 to 4. Changes in the BI-RADS density category were associated with breast cancer risk. Longitudinal measures of BI-RADS density may be helpful in identifying high-risk women, especially those with a breast cancer family history.

Role of "Stiff Rim" sign obtained by shear wave elastography in diagnosis and guiding therapy of breast cancer

Background: Because the halo around the tumor in shear wave elastography (SWE) is defined as the "stiff rim" sign, the diagnosis of breast lesions with the stiff rim sign is popular. However, only a few studies have described the stiff rim sign quantitatively. Objective: This study aimed to investigate the usefulness of the stiff rim sign in the diagnosis and tumor, node, metastasis stage of breast cancer. Methods: Two hundred and ten breast lesions were analyzed retrospectively. The maximum, mean, minimum Young's modulus (YM), and the YM standard deviation in the lesion, the peritumoral stiffness (shell), and the region containing lesion and shell were obtained. The suspicious SWE feature with the best diagnostic performance was chosen to downgrade or upgrade the Breast Imaging Reporting and Data System (BI-RADS) classification. The coincidence rates of SWE and B-mode ultrasound in T staging and their positive predictive value (PPV) for T staging were compared. Results: The presence of "stiff rim" sign was selected to upgrade or downgrade the BI-RADS classification because of its best performance. In pathological benign lesions, 18.9% (25 of 132) of lesions should undergo biopsy if BI-RADS combined with the stiff rim sign were referred while it was 57.6% (76 of 132) if BI-RADS alone was referred. The coincidence rate of T2 staging evaluated by SWE was significantly higher than B-mode ultrasound (about 30% increase, P < 0.001). The PPVs of SWE for T1 and T2 staging were higher than B-mode ultrasound (P < 0.05). Conclusions: BI-RADS combined with "stiff rim" sign is expected to improve the diagnostic performance of breast lesions to avoid unnecessary biopsy. The maximum diameter of the lesion measured in SWE is more accurate than B-mode ultrasound in the estimation of T staging, which is beneficial to the treatment and prognosis of breast cancer.

Diagnostic role of shear wave elastography for differentiating benign and malignant breast masses

Background

Use of B-mode ultrasound (US) may not obviate the need for diagnosis by histopathology, which is an invasive technique and remains the gold standard. These limitations are being overcome with the advent of shear wave elastography (SWE).

Objectives

To assess the diagnostic role of SWE parameters and combined SWE and B-mode US in diagnosing malignant breast lesions.

Method

This cross-sectional study included all patients with a breast mass on clinical examination. A B-mode US with a Breast Imaging Reporting and Data System (BI-RADS) assessment and SWE evaluation (distance ratio [DR], area ratio [AR] and shear wave velocity [SWV]) in the lesion and healthy breast tissue of all recruited patients was performed. Cut-offs for SWE parameters were derived by receiver operating characteristic (ROC) analysis. The diagnostic performance of the B-mode US, the SWE parameters and the combined imaging in diagnosing malignancy was assessed.

Results

This study included a total of 175 breast masses. The median values of the SWE parameters were significantly higher (p < 0.001) in the malignant breast masses (DR, 1.29 vs. 1.03; AR, 1.69 vs. 1.06; and SWV, 9.1 metre per second [m/s] vs. 2.1 m/s). The ROC cut-off for malignancy was derived at 1.135 m/s, 1.18 m/s and 3.18 m/s, respectively, for DR, AR and SWV. The area under the ROC curve was highest for the DR (0.930), whilst this value was 0.914 and 0.901 for the SWV and AR, respectively. Amongst the respective sensitivities and specificities of the B-mode US (90.6% and 90%), SWE (97.6% and 61.1%), SWE (excluding AR) (96.5% and 77.8%) and combined imaging (100% and 72.2%), the highest sensitivity was noted for the combined method.

Conclusion

All the SWE parameters were significantly higher in the malignant breast masses, compared to the benign lesions. On combining SWE and B-mode US, there was a significant increase in sensitivity but a decrease in specificity.

Current Status and Future of BI-RADS in Multimodality Imaging, From the AJR Special Series on Radiology Reporting and Data Systems

BI-RADS is a communication and data tracking system that has evolved since its inception as a brief mammography lexicon and reporting guide into a robust structured reporting platform and comprehensive quality assurance tool for mammography, ultrasound, and MRI. Consistent and appropriate use of the BI-RADS lexicon terminology and assessment categories effectively communicates findings, estimates the risk of malignancy, and provides management recommendations to patients and referring clinicians. The impact of BI-RADS currently extends internationally through six language translations. A condensed version has been proposed to facilitate a phased implementation of BI-RADS in resource-constrained regions. The primary advance of the 5th edition of BI-RADS is harmonization of the lexicon terms across mammography, ultrasound, and MRI. Harmonization has also been achieved across these modalities for the reporting structure, assessment categories, management recommendations, and data tracking system. Areas for improvement relate to certain common findings that lack lexicon descriptors and a need for further clarification of proper use of category 3. BI-RADS is anticipated to continue to evolve for application to a range of emerging breast imaging modalities.

Prostate MRI and quality: lessons learned from breast imaging rad-path correlation

Radiologic-pathologic correlation of Prostate Imaging Reporting & Data System (PI-RADS) scores ensures local quality and offers opportunities to improve future iterations of the reporting system. Tracking positive predictive values of lesion-targeted biopsies helps provide generalizable population-level risks associated with each PI-RADS category and can highlight the sources of variation. While this process of formalized pathologic correlation is somewhat new to abdominal radiology, we are fortunate to have a model to follow which was developed by our colleagues in breast imaging. If the success and multi-national adoption of BI-RADS is an indicator, building a scoring system anchored on a histologic reference is an important step to ensuring diagnostic quality and reliability.

Correlation of the BI-RADS assessment categories of Papua New Guinean women with mammographic parenchymal patterns, age and diagnosis

INTRODUCTION

Women with increased breast density are at increased risk of breast cancer. The aim of this research is to evidence for the first time the mammographic breast findings of Papua New Guinean (PNG) women and the relationship between Breast Imaging-Reporting and Data System (BI-RADS) assessment, mammographic parenchymal patterns (MPPs) and age.

METHODS

A retrospective analysis of 1357 mammograms of women imaged at the Pacific International Hospital (PIH) from August 2006 to July 2010 was undertaken. Mammographic findings were categorised using the BI-RADS Atlas® 5th Edition. MPPs were recorded for each woman using the Tabár Pattern I-V classification system. Age was recorded in years. Statistical analysis was by descriptive analysis and Kruskal-Wallis with Dunn's post-test and Spearman's rho correlation for inferential analysis.

RESULTS

True pathological findings (benign and malignant); BI-RADS 2-5 were noted in 111 women (8.2%); 1242 (91.5%) were negative. BI-RADS categories for malignancy were reported in 16 (88.9%) of women aged 30 to 60 years. The lower risk Tabár Type I, II and III MPPs were associated with 94.4% (n = 17) of malignancies. Linear correlations between variables were weak and not statistically significant: age and Tabár pattern r = 0.031, P = 0.0261; age and BI-RADS r = 0.018, P = 0.517; Tabár pattern and BI-RADS r = 0.020, P = 0.459 (n = 1357).

CONCLUSION

There was no correlation demonstrated between BI-RADS category, age and MPP. Importantly, there was no correlation demonstrated between BI-RADS categories 4 and 5 for breast malignancy and high-risk Tabár Type IV and V MPPs. The results of this study again reflect that the incidence of breast cancer in PNG cannot be explained by breast density and suggest that any formalised screening program in PNG has a target age group aimed at women younger than that of Western screening programs.

A decision support system for mammography reports interpretation

PURPOSE

Mammography plays a key role in the diagnosis of breast cancer; however, decision-making based on mammography reports is still challenging. This paper aims to addresses the challenges regarding decision-making based on mammography reports and propose a Clinical Decision Support System (CDSS) using data mining methods to help clinicians to interpret mammography reports.

METHODS

For this purpose, 2441 mammography reports were collected from Imam Khomeini Hospital from March 21, 2018, to March 20, 2019. In the first step, these mammography reports are analyzed and program code is developed to transform the reports into a dataset. Then, the weight of every feature of the dataset is calculated. Random Forest, Naïve Bayes, K-nearest neighbor (K-NN), Deep Learning classifiers are applied to the dataset to build a model capable of predicting the need for referral to biopsy. Afterward, the models are evaluated using cross-validation with measuring Area Under Curve (AUC), accuracy, sensitivity, specificity indices.

RESULTS

The mammography type (diagnostic or screening), mass and calcification features mentioned in the reports are the most important features for decision-making. Results reveal that the K-NN model is the most accurate and specific classifier with the accuracy and specificity values of 84.06% and 84.72% respectively. The Random Forest classifier has the best sensitivity and AUC with the sensitivity and AUC values of 87.74% and 0.905 respectively.

CONCLUSIONS

Accordingly, data mining approaches are proved to be a helpful tool to make the final decision as to whether patients should be referred to biopsy or not based on mammography reports. The developed CDSS may also be helpful especially for less experienced radiologists.

Multi-Institutional Assessment and Crowdsourcing Evaluation of Deep Learning for Automated Classification of Breast Density

OBJECTIVE

We developed deep learning algorithms to automatically assess BI-RADS breast density.

METHODS

Using a large multi-institution patient cohort of 108,230 digital screening mammograms from the Digital Mammographic Imaging Screening Trial, we investigated the effect of data, model, and training parameters on overall model performance and provided crowdsourcing evaluation from the attendees of the ACR 2019 Annual Meeting.

RESULTS

Our best-performing algorithm achieved good agreement with radiologists who were qualified interpreters of mammograms, with a four-class κ of 0.667. When training was performed with randomly sampled images from the data set versus sampling equal number of images from each density category, the model predictions were biased away from the low-prevalence categories such as extremely dense breasts. The net result was an increase in sensitivity and a decrease in specificity for predicting dense breasts for equal class compared with random sampling. We also found that the performance of the model degrades when we evaluate on digital mammography data formats that differ from the one that we trained on, emphasizing the importance of multi-institutional training sets. Lastly, we showed that crowdsourced annotations, including those from attendees who routinely read mammograms, had higher agreement with our algorithm than with the original interpreting radiologists.

CONCLUSION

We demonstrated the possible parameters that can influence the performance of the model and how crowdsourcing can be used for evaluation. This study was performed in tandem with the development of the ACR AI-LAB, a platform for democratizing artificial intelligence.

Investigation of Synthetic Relaxometry and Diffusion Measures in the Differentiation of Benign and Malignant Breast Lesions as Compared to BI-RADS

BACKGROUND

Breast cancer is the most common malignant tumor in women and a quantitative contrast-free method is highly desirable for its diagnosis.

PURPOSE

To investigate the performance of quantitative MRI in differentiating malignant from benign breast lesions and to compare with the Breast Imaging Reporting and Data System (BI-RADS).

STUDY TYPE

Retrospective.

SUBJECTS

Eighty patients (56 with malignant lesions and 24 with benign lesions).

FIELD STRENGTH/SEQUENCE

Diffusion-weighted imaging (DWI) with a single-shot echo planar sequence and synthetic MRI with magnetic resonance image compilation (MAGiC) were performed at 3T.

ASSESSMENT

T₁ relaxation time (T₁ ), T₂ relaxation time (T₂ ), and proton density (PD) from synthetic MRI and apparent diffusion coefficient (ADC) from DWI were analyzed by two radiologists (Reader A, Reader B). Univariable and multivariable models were developed to optimize differentiation between malignant and benign lesions and their performances compared to BI-RADS.

STATISTICAL TESTS

The diagnostic performance was evaluated using multivariate logistic regression analysis and area under the receiver operating characteristic (ROC) curves (AUC).

RESULTS

T₂ , PD, and ADC values for malignant lesions were significantly lower than those in benign breast lesions for both radiologists (all P < 0.05). The combined T₂ , PD, and ADC model had the best performance for differentiating malignant and benign lesions with AUC, sensitivity, specificity, positive predictive value, and negative predictive values of 0.904, 94.6%, 87.5%, 94.6%, and 87.5%, respectively. The corresponding results for BI-RADS were no AUC, 94.6%, 75.0%, 89.8%, and 85.7%, respectively.

DATA CONCLUSION

The approach that combined synthetic MRI and DWI outperformed BI-RADS in the differential diagnosis of malignant and benign breast lesions and was achieved without contrast agents. This approach may serve as an alternative and effective strategy for the improvement of breast lesion differentiation.

LEVEL OF EVIDENCE

3.

TECHNICAL EFFICACY STAGE

3.

A novel approach with dual-sampling convolutional neural network for ultrasound image classification of breast tumors

Breast cancer is one of the leading causes of female cancer deaths. Early diagnosis with prophylactic may improve the patients' prognosis. So far ultrasound (US) imaging is a popular method in breast cancer diagnosis. However, its accuracy is bounded to traditional handcrafted feature methods and expertise. A novel method named Dual-Sampling Convolutional Neural Networks (DSCNN) was proposed in this paper for the differential diagnosis of breast tumors based on US images. Combining traditional convolutional and residual networks, DSCNN prevented gradient disappearance and degradation. The prediction accuracy was increased by the parallel dual-sampling structure, which can effectively extract potential features from US images. Compared with other advanced deep learning methods and traditional handcraftedfeaturemethods,DSCNNreachedthebestperformance withanaccuracyof91.67%andan AUC of 0.939. The robustness of the proposed method was also verified by using a public dataset. Moreover, DSCNN was compared with evaluation from three radiologists utilizing US-BI-RADS lexicon categories for overall breast tumors assessment. The result demonstrated that the prediction sensitivity, specificity and accuracy of the DSCNN were higher than those of the radiologist with 10- year experience, suggesting that the DSCNN has the potential to help doctors make judgement in clinic.