BI-RADS Research Articles

Deep learning combining mammography and ultrasound images to predict the malignancy of BI-RADS US 4A lesions in women with dense breasts: a diagnostic study.

The authors aimed to assess the performance of a deep learning (DL) model, based on a combination of ultrasound (US) and mammography (MG) images, for predicting malignancy in breast lesions categorized as Breast Imaging Reporting and Data System (BI-RADS) US 4A in diagnostic patients with dense breasts. A total of 992 patients were randomly allocated into the training cohort and the test cohort at a proportion of 4:1. Another, 218 patients were enrolled to form a prospective validation cohort. The DL model was developed by incorporating both US and MG images. The predictive performance of the combined DL model for malignancy was evaluated by sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). The combined DL model was then compared to a clinical nomogram model and to the DL model trained using US image only and to that trained MG image only. The combined DL model showed satisfactory diagnostic performance for predicting malignancy in breast lesions, with an AUC of 0.940 (95% CI: 0.874-1.000) in the test cohort, and an AUC of 0.906 (95% CI: 0.817-0.995) in the validation cohort, which was significantly higher than the clinical nomogram model, and the DL model for US or MG alone ( P <0.05). The study developed an objective DL model combining both US and MG imaging features, which was proven to be more accurate for predicting malignancy in the BI-RADS US 4A breast lesions of patients with dense breasts. This model may then be used to more accurately guide clinicians' choices about whether performing biopsies in breast cancer diagnosis.

Intelligent scoring system based on dynamic optical breast imaging for early detection of breast cancer.

Early detection of breast cancer can significantly improve patient outcomes and five-year survival in clinical screening. Dynamic optical breast imaging (DOBI) technology reflects the blood oxygen metabolism level of tumors based on the theory of tumor neovascularization, which offers a technical possibility for early detection of breast cancer. In this paper, we propose an intelligent scoring system integrating DOBI features assessment and a malignancy score grading reporting system for early detection of breast cancer. Specifically, we build six intelligent feature definition models to depict characteristics of regions of interest (ROIs) from location, space, time and context separately. Similar to the breast imaging-reporting and data system (BI-RADS), we conclude the malignancy score grading reporting system to score and evaluate ROIs as follows: Malignant (≥ 80 score), Likely Malignant (60-80 score), Intermediate (35-60 score), Likely Benign (10-35 score), and Benign (<10 score). This system eliminates the influence of subjective physician judgments on the assessment of the malignant probability of ROIs. Extensive experiments on 352 Chinese patients demonstrate the effectiveness of the proposed system compared to state-of-the-art methods.

Assessing Diagnostic Performance Using the Transverse Plane Plus Coronal Plane Compared With the Transverse Plane Alone in Screening Automated Breast Ultrasound.

The coronal plane is the unique display mode of automated breast (AB) ultrasound (US), which has valuable features of showing the entire breast anatomy and providing additional diagnostic value for breast lesions. However, whether adding the coronal plane could improve the diagnostic performance in screening breast cancer remains uncertain. This study aimed to evaluate the value of adding the coronal plane in interpretation for AB US screening. In this retrospective study, AB US images from 644 women (396 in the no-finding group, 143 with benign lesions, and 105 with malignant lesions) aged 40-70 years were collected between January 2016 and October 2020. Four novice radiologists (with 1-5 years of experience with breast US) and four experienced radiologists (with >5 years of experience with breast US) were assigned to read all AB US images in the transverse plane plus coronal plane (T + C planes) and transverse plane (T plane) alone in separate reading sessions. Diagnostic performance, lesion conspicuity, and reading time were compared using analysis of variance. The mean reading time of all radiologists was significantly shorter in the T + C planes reading mode than in the T plane alone (115 ± 32 vs 128 ± 31 s, respectively; P < .05), and cancers had a higher conspicuity (odds ratio, 1.76; 95% confidence interval [CI], 1.00-3.08; P = .04). No significant differences were noted in the two reading modes (T + C planes vs T plane) in the sensitivity (82% [95% CI, 74-89%] vs 81% [95% CI, 74-88%], respectively; P = .68) and specificity (68% [95% CI, 62-75%] vs 70% [95% CI, 64-75%], respectively; P = .39) when Breast Imaging-Reporting and Data System (BI-RADS) 3 was set as the threshold. There were also no significant differences in the two reading modes (T + C planes vs T plane) in the sensitivity (70% [95% CI, 64-76%] vs 69% [95% CI, 63-75%], respectively; P = .39) and specificity (91% [95% CI, 87-96%] vs 91% [95% CI, 88-95%], respectively; P = .90) when BI-RADS 4 was set as the threshold. In addition, the mean areas under the receiver operating characteristic curves of all radiologists in the two reading modes (T + C planes vs T plane) were not significantly different (0.84 [95% CI, 0.79-0.89] vs 0.83 [95% CI, 0.78-0.89], respectively; P = .61). Adding a coronal plane in the AB US screening setting saved the reading time and improved the conspicuity of breast cancers but not the diagnostic performance.

Differential diagnosis of breast mucinous carcinoma with an oval shape from fibroadenoma based on ultrasonographic features

BackgroundApproximately 50% of breast mucinous carcinomas (MCs) are oval and have the possibility of being misdiagnosed as fibroadenomas (FAs). We aimed to identify the key features that can help differentiate breast MC with an oval shape from FA on ultrasonography (US).MethodsSeventy-six MCs from 71 consecutive patients and 50 FAs with an oval shape from 50 consecutive patients were included in our study. All lesions pathologically diagnosed. According to the Breast Imaging Reporting and Data System (BI-RADS), first, the ultrasonographic features of the MCs and FAs were recorded and a final category was assessed. Then, the differences in ultrasonographic characteristics between category 4 A (low-risk group) and category 4B-5 (medium-high- risk group) MCs were identified. Finally, other ultrasonographic features of MC and FA both with an oval shape were compared to determine the key factors for differential diagnosis. The Mann-Whitney test, χ2 test or Fisher’s exact test was used to compare data between groups.ResultsMCs with an oval shape (81.2%) and a circumscribed margin (25%) on US were more commonly assessed in the low-risk group (BI-RADS 4 A) than in the medium-high-risk group (BI-RADS 4B-5) (20%, p < 0.001 and 0%, p = 0.001, respectively). Compared with those with FA, patients with MC were older, and tended to have masses with non-hypoechoic patterns, not circumscribed margins, and a posterior echo enhancement on US (p < 0.001, p < 0.001, and p = 0.003, respectively).ConclusionThe oval shape was the main reason for the underestimation of MCs. On US, an oval mass found in the breast of women of older age with non-hypoechoic patterns, not circumscribed margins, and a posterior echo enhancement was associated with an increased risk of being an MC, and should be subjected to active biopsy.

Classification of BI-RADS using convolutional neural network and effecientNet-B7

From its development, image processing technology has become increasingly complex, such as detecting cancer in an image. In this context, the American College of Radiology (ACR) has developed a standard format and terminology called the breast imaging reporting and data system (BI-RADS). The aim of this research is to determine whether CNN can classify BI-RADS types (C1, C2, C3, C4), the best model, and the classification results of BI-RADS types on mammograms using CNN, and the best values for accuracy, sensitivity, specificity, and precision. Google Colaboratory and machine learning libraries were used in this research to create machine learning for BI-RADS classification. Then, a dataset from Kaggle titled "Mini-DDSM: Mammography-based Automatic Age Estimation" by Lekamlage et al., from the Association for Computing Machinery (ACM), Kyoto, Japan, was utilized. Based on the research, an accuracy of 85.9% was achieved for Category 1 classification. Category 2 classification attained an accuracy of 77.9%. The accuracy for Category 3 classification was 81.4%, and for Category 4, it reached 90.8%.

Deep-learning model to improve histological grading and predict upstaging of atypical ductal hyperplasia / ductal carcinoma in situ on breast biopsy.

Risk stratification of atypical ductal hyperplasia (ADH) and ductal carcinoma in situ (DCIS), diagnosed using breast biopsy, has great clinical significance. Clinical trials are currently exploring the possibility of active surveillance for low-risk lesions, whereas axillary lymph node staging may be considered during surgical planning for high-risk lesions. We aimed to develop a machine-learning algorithm based on whole-slide images of breast biopsy specimens and clinical information to predict the risk of upstaging to invasive breast cancer after wide excision. Patients diagnosed with ADH/DCIS on breast biopsy were included in this study, comprising 592 (740 slides) and 141 (198 slides) patients in the development and independent testing cohorts, respectively. Histological grading of the lesions was independently evaluated by two pathologists. Clinical information, including biopsy method, lesion size, and Breast Imaging Reporting and Data System (BI-RADS) classification of ultrasound and mammograms, were collected. Deep DCIS consisted of three deep neural networks to evaluate nuclear grade, necrosis, and stromal reactivity. Deep DCIS output comprised five parameters: total patches, lesion extent, Deep Grade, Deep Necrosis, and Deep Stroma. Deep DCIS highly correlated with the pathologists' evaluations of both slide- and patient-level labels. All five parameters of Deep DCIS were significantly associated with upstaging to invasive carcinoma in subsequent wide excisional specimens. Using multivariate logistic regression, Deep DCIS predicted upstaging to invasive carcinoma with an area under the curve (AUC) of 0.81, outperforming pathologists' evaluation (AUC, 0.71 and 0.69). After including clinical and hormone receptor status information, performance further improved (AUC, 0.87). This combined model retained its predictive power in two subgroup analyses: the first subgroup included unequivocal DCIS (excluding cases of ADH and DCIS suspicious for microinvasion) (AUC, 0.83), while the second excluded cases of high-grade DCIS (AUC, 0.81). The model was validated in an independent testing cohort (AUC, 0.81). This study demonstrated that deep-learning models can refine histological evaluation of ADH and DCIS on breast biopsies, which may help guide future treatment planning.

Value of S-Detect combined with multimodal ultrasound in differentiating malignant from benign breast masses

Abstract Background Ultrasonography (US) still has some limitations in the differentiation of benign and malignant breast masses. Therefore, we introduced new technologies such as S-Detect, microvascular flow imaging (MVFI), and strain elastography (SE) into the examination and compared the multimodal method with Breast Imaging Reporting and Data System (BI-RADS). Objectives This prospective study aimed to evaluate the value of multimodal diagnostic methods that add S-Detect, MFI, and SR to US in differentiating benign from malignant breast masses. Methods We recruited 186 patients with 189 masses between July 2021 and March 2022. The masses were examined using US, S-Detect, SR, and MFI before biopsy, and the benign and malignant differentiation value of each and their combination were assessed compared with surgical pathology results using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Subgroup analysis by lesion size was also performed. Results The respective optimal cutoff values of SR and MFI for differentiating benign from malignant masses were 3.15 and 2.45, respectively, and the sensitivity and specificity were 79.3% and 85.6% and 94.6% and 69.1%, respectively. The multimodal AUC (0.907), sensitivity (97.8%), accuracy (90.5%), PPV (84.9%), and NPV (97.6%) were larger than those of each modality (p &lt; 0.05), regardless of the mass size. Conclusions The diagnostic method of S-Detect combined with multimodal ultrasound can effectively improve the diagnostic efficiency of breast masses and is expected to become a routine examination for breast in future for better evaluation the benign and malignancy of breast masses.

Diagnostic performance of 3D automated breast ultrasound (3D-ABUS) in a clinical screening setting—a retrospective study

ObjectivesTo assess the diagnostic performance of 3D automated breast ultrasound (3D-ABUS) in breast cancer screening in a clinical setting.Materials and methodsAll patients who had 3D-ABUS between January 2014 and January 2022 for screening were included in this retrospective study. The images were reported by 1 of 6 breast radiologists based on the Breast Imaging Reporting and Data Systems (BI-RADS). The 3D-ABUS was reviewed together with the digital breast tomosynthesis (DBT). Recall rate, biopsy rate, positive predictive value (PPV) and cancer detection yield were calculated.ResultsIn total, 3616 studies were performed in 1555 women (breast density C/D 95.5% (n = 3455/3616), breast density A/B 4.0% (n = 144/3616), density unknown (0.5% (n = 17/3616)). A total of 259 lesions were detected on 3D-ABUS (87.6% (n = 227/259) masses and 12.4% (n = 32/259) architectural distortions). The recall rate was 5.2% (n = 188/3616) (CI 4.5–6.0%) with only 36.7% (n = 69/188) cases recalled to another date. Moreover, recall declined over time. There were 3.4% (n = 123/3616) biopsies performed, with 52.8% (n = 65/123) biopsies due to an abnormality detected in 3D-ABUS alone. Ten of 65 lesions were malignant, resulting in a positive predictive value (PPV) of 15.4% (n = 10/65) (CI 7.6–26.5%)). The cancer detection yield of 3D-ABUS is 2.77 per 1000 screening tests (CI 1.30–5.1).ConclusionThe cancer detection yield of 3D-ABUS in a real clinical screening setting is comparable to the results reported in previous prospective studies, with lower recall and biopsy rates. 3D-ABUS also may be an alternative for screening when mammography is not possible or declined.Clinical relevance statement3D automated breast ultrasound screening performance in a clinical setting is comparable to previous prospective studies, with better recall and biopsy rates.Key Points• 3D automated breast ultrasound is a reliable and reproducible tool that provides a three-dimensional representation of the breast and allows image visualisation in axial, coronal and sagittal.• The diagnostic performance of 3D automated breast ultrasound in a real clinical setting is comparable to its performance in previously published prospective studies, with improved recall and biopsy rates.• 3D automated breast ultrasound is a useful adjunct to mammography in dense breasts and may be an alternative for screening when mammography is not possible or declined.

A Multi-group similarity-decoding-based method for deep model ensembling applied in the microcalcification classification on digital mammograms

Classifying mammograms scored at Breast Imaging-Reporting and Data System (BI-RADS ) 4 is crucial for the early detection of breast cancer. But it is particularly challenging because microcalcifications (MCs) vary greatly in shape and distribution. Traditional machine learning and deep models are either time-consuming or poorly generalized. Recently, deep ensemble learning, which can improve generalization, has been developed rapidly. However, most ensembling strategies are based on weighted average and often sensitive to biased learners. To achieve data-adaption, they employ complex techniques to implement dynamic weight calculation. In this paper, we proposed a novel multi-group similarity-decoding-based method (MG-SDM) which enables a more robust and easier ensembling of different deep models. Firstly, the multi-group (MG) strategy is designed to transform model ensembling into a process of feature-level fusion, which could alleviate the impact of a single model on overall performance. Specifically, individual features of different models are grouped based on the position, and feature fusion is performed within each group. Secondly, the similarity-decoding-based method (SDM) is developed to fuse features. All individual features are vectorized through linear transformation. Then their similarities with a learnable latent embedding, which is introduced to denote most task-related features, are calculated using inner product. Finally, the similarity values among features within same group are normalized to be weights for a subsequent weighted summation operation. Extensive experiments on the clinical dataset demonstrate the superiority of the proposed over other state-of-the-art methods.

BIRADS 0 patient reclassification in a first-level of care unit

In Mexico and the world, breast cancer is the cancer type with the highest incidence and mortality for women. Its incidence has increased due to a higher life expectancy and a higher exposure to risk factors. Screening is done by mammography using the BIRADS (Breast Imaging Reporting and Data System) system, the standard for mammography screening report which classifies lesions assigning recommendations for patient follow-up. The system goes from 0 (not conclusive) to 6 (demonstrated malignancy), being of interest for this study the BIRADS 0 category. To describe patients classified as BIRADS 0 by mammography and their reclassification in a first-level hospital during 2021. Retrospective, descriptive, cross-sectional, observational study. Women over 40 years with a BIRADS 0 result were studied. The following databases were used: Institutional Cancer Registry, Family Medicine Information System, Electronic Clinical File, and the mammography and patient list from preventive medicine. Reclassification by ultrasound (US) was achieved in 100% of patients, in all of the BIRADS US categories. In 3.8% of BIRADS 0 patients, ductal adenocarcinoma was found and confirmed by histological testing. All of the reassessed lesions with US were adequately reclassified.

The Accuracy of Breast Cancer Diagnostic Tools.

Background Breast cancer (BC)remains a significant health concern,leadingtoillnessanddeathamong womenglobally. Itisessential to detectBCearly usingimagingtechniquesthataccurately reflectthe final pathology, guiding suitable intervention strategies. Objectives This study aimed toevaluatetheagreementbetween radiological findings and histopathological resultsinBCcases. Methods We conducted aretrospective reviewofbreast core needle biopsies (CNBs)inwomenover a six-year period (2017-2022) at Imam Abdulrahman Bin Faisal University, Dammam, Saudi Arabia. The pathologicaldiagnoses were compared with thefindingsfrompreceding radiological investigations.We also compared the tumour sizes inthe resection specimenswiththeir radiologicalcounterparts. Results A total of 641 cases were includedin the study.Ultrasound (US),mammography,andmagnetic resonance imaging (MRI)yieldeddiagnostic accuracies of 85%, 77.9%, and 86.9%,respectively. MRIhadthe highest sensitivityat72.2%, while US hadthe lowestat61%. MRI provided the best agreementwiththefinalresected tumor size. By contrast,mammographytended to overestimate the size (41.9%), and US most frequently underestimated it(67.7%).The connectionbetween basal-like molecular subtypes and the Breast Imaging Reporting and Data System (BIRADS)-5 classifications wasonlystatistically significantfor MRI (p=0.04). The luminal subtypewas more likely to showspeculation in mammography.Meanwhile,BIRADS-4revealedaconsiderablenumber of benign pathologiesacrossall the threemodalities. Conclusions MRIdemonstrated thehighestaccuracy,sensitivity, specificity,andpositive predictive value (PPV) fordiagnosingandestimating the tumorsize.Mammographyoutperformed US in terms of sensitivityandyielded thehighestnegative predictive value (NPV). US, meanwhile, offered superiorspecificity, PPV,and accuracy. Therefore, combiningthese diagnostic methods could yield significant benefits.

Multiparametric MRI model with synthetic MRI, DWI multi-quantitative parameters, and differential sub-sampling with cartesian ordering enables BI-RADS 4 lesions diagnosis with high accuracy.

To assess the feasibility and diagnostic performances of synthetic magnetic resonance imaging (SyMRI) combined with diffusion-weighted imaging (DWI) and differential subsampling with cartesian ordering (DISCO) in breast imaging reporting and data system (BI-RADS) 4 lesions. A total of 98 BI-RADS 4 patients, including 68 cases assigned to a malignant group and 33 cases assigned to a benign group, were prospectively enrolled, and their MRI and clinical information were collected. Two physicians jointly analyzed the characteristics of conventional MRI. T1, T2, proton density (PD), and ADC values were obtained from three different regions of interest (ROIs). Logistic regression analyses were used to select features and build models, and a nomogram was constructed with the best model. Using the ROI delineation method at the most obvious enhancement to measure the ADC value revealed the best diagnostic performance in diagnosing BI-RADS type 4 mass lesions. The diagnostic efficiency of the maximum level drawing method of the quantitative relaxation model was better than that of the whole drawing method and the most obvious enhancement method. The best relaxation model (model A) was composed of two parameters: T2stand and ΔT1%stand (AUC=0.887), and the BI-RADS model (model B) was constructed by two MRI features of edge and TIC curve (AUC=0.793). Using the quantitative parameters of SyMRI and DWI of the best ROC method combined with DISCO enhanced MRI features to establish a joint diagnostic model (model C: edge, TIC curve type, ADClocal, T2stand, ΔT1%stand) showed the best diagnostic efficiency (AUC=0.953). The nomogram also had calibration curves with good overlap. The combined diagnosis model of SyMRI and DWI quantitative parameters combined with DISCO can improve the diagnostic efficiency of BI-RADS 4 types of mass lesions. Also, the line diagram based on this model can be used as an auxiliary diagnostic tool.

Breast Cancer Screening and BI-RADS Scoring Trends Before and During the COVID-19 Pandemic in an Academic Safety-Net Hospital.

Little is known about how the COVID-19 pandemic affected screening mammography rates and Breast Imaging Reporting and Data Systems (BI-RADS) categorizations within populations facing social and economic inequities. Our study seeks to compare trends in breast cancer screening and BI-RADS assessments in an academic safety-net patient population before and during the COVID-19 pandemic. Our single-center retrospective study evaluated women ≥ 18 years old with no known breast cancer diagnosis who received breast cancer screening from March 2019-September 2020. The screening BI-RADS score, completion of recommended diagnostic imaging, and diagnostic BI-RADS scores were compared between the pre-COVID-19 era (from 1 March 2019 to 19 March 2020) and COVID-19 era (from 20 March 2020 to 30 September 2020). Among the 11,798 patients identified, screened patients were younger (median age 57 versus 59 years, p < 0.001) and more likely covered by private insurance (35.9% versus 32.3%, p < 0.001) during the COVID-19 era compared with the pre-COVID-19 era. During the pandemic, there was an increase in screening mammograms categorized as BI-RADS 0 compared with the pre-COVID-19 era (20% versus 14.5%, p < 0.0001). There was no statistically significant difference in rates of completion of diagnostic imaging (81.6% versus 85.4%, p = 0.764) or assignment of suspicious BI-RADS scores (BI-RADS 4-5; 79.9% versus 80.8%, p = 0.762) between the two eras. Although more patients were recommended to undergo diagnostic imaging during the pandemic, there were no significant differences in race, completion of diagnostic imaging, or proportions of mammograms categorized as suspicious between the two time periods. These findings likely reflect efforts to maintain equitable care among diverse racial groups served by our safety-net hospital.

Beyond BI-RADS: Nonmass Abnormalities on Breast Ultrasound.

Abnormalities on breast ultrasound (US) images which do not meet the criteria for masses are referred to as nonmass lesions. These features and outcomes have been investigated in several studies conducted by Asian researchers. However, the term "nonmass" is not included in the American College of Radiology (ACR) Breast Imaging Reporting and Data System (BI-RADS) 5th edition for US. According to the Japan Association of Breast and Thyroid Sonology guidelines, breast lesions are divided into mass and nonmass. US findings of nonmass abnormalities are classified into five subtypes: abnormalities of the ducts, hypoechoic areas in the mammary glands, architectural distortion, multiple small cysts, and echogenic foci without a hypoechoic area. These findings can be benign or malignant; however, focal or segmental distributions and presence of calcifications suggest malignancy. Intraductal, invasive ductal, and lobular carcinomas can present as nonmass abnormalities. For the nonmass concept to be included in the next BI-RADS and be widely accepted in clinical practice, standardized terminologies, an interpretation algorithm, and outcome-based evidence are required for both screening and diagnostic US.

Characteristics of Suspicious Breast Lesions Visible Only on MR Imaging: Is It Possible to Classify into Immediate Biopsy and Careful Observation Groups?

To investigate the characteristics of suspicious MRI-only visible lesions and to explore the validity of subcategorizing these lesions into the following two groups: lesions that would require immediate biopsy (4Bi) and lesions for which careful clinical follow-up could be recommended (4Fo). A retrospective review of 108 MRI-only visible lesions in 106 patients who were diagnosed as Breast Imaging Reporting and Data System (BI-RADS) category 4 between June 2018 and June 2022 at our institution was performed by two radiologists. The breast MR images were evaluated according to BI-RADS and additional MRI descriptors (linear ductal, branching, and apparent diffusion coefficient values). The lesions were categorized by previously reported classification systems, and the positive predictive values (PPVs) for the different categories were determined and compared. Subsequently, a new classification system was developed in this study. The total malignancy rate was 31% (34/108). No significant differences between benign and malignant lesions were identified for focus and mass lesions. For non-mass lesions, linear ductal and heterogeneous internal enhancement suggested a benign lesion (P = 0.0013 and P = 0.023, respectively), and branching internal enhancement suggested malignancy (P = 0.0066). Segmental distribution suggested malignancy (P = 0.0097). However, the PPV of segmental distribution with heterogeneous enhancement was significantly lower than that of category 4 segmental lesions with other enhancement patterns (11% vs. 59%; P = 0.0198).As a new classification, the distribution of focal, linear, and segmental was given a score of 0, 1, or 2, and the internal enhancement of heterogeneous, linear-ductal, clumped, branching, and clustered-ring enhancement was given a score of 0, 1, 2, 3, and 4, respectively. When categorized using a scoring system, a statistically significant difference in PPV was observed between 4Fo (n = 27) and 4Bi (n = 33) (7% vs. 61%, P = 0.000029). The new classification system was found to be highly capable of subcategorizing BI-RADS category 4 MRI-only visible non-mass lesions into 4Fo and 4Bi.

Diagnostic Utility of an Adjusted DWI Lexicon Using Multiple b-values to Evaluate Breast Lesions in Combination with BI-RADS.

We aimed to investigate the diagnostic feasibility of an adjusted diffusion-weighted imaging (DWI) lexicon using multiple b values to assess breast lesions according to DWI-based breast imaging reporting and data system (BI-RADS). This Institutional Review Board (IRB)-approved prospective study included 127 patients with suspected breast cancer. Breast MRI was performed using a 3T scanner. Breast DW images were acquired using five b-values of 0, 200, 800, 1000, and 1500 s/mm2 (5b-value DWI) on 3T MRI. Two readers independently assessed lesion characteristics and normal breast tissue using DWI alone (5b-value DWI and 2b-value DWI with b = 0 and 800 s/mm2) according to DWI-based BI-RADS and in combination with the standard dynamic contrast-enhanced images (combined MRI). Interobserver and intermethod agreements were assessed using kappa statistics. The specificity and sensitivity of lesion classification were evaluated. Ninety-five breast lesions (39 malignant and 56 benign) were evaluated. Interobserver agreement for lesion assessment on 5b-value DWI was very good (k ≥ 0.82) for DWI-based BI-RADS categories, lesion type, and mass characteristics; good (k = 0.75) in breast composition; and moderate (k ≥ 0.44) in background parenchymal signal (BPS) and non-mass distribution. Intermethod agreement between assessments performed using either 5b-value DWI or combined MRI was good-to-moderate (k = 0.52-0.67) for lesion type; moderate (k = 0.49-0.59) for DWI-based BI-RADS category and mass characteristics; and fair (k = 0.25-0.40) for mass shape, BPS, and breast composition. The sensitivity and positive predictive values (PPVs) for 5b-value DWI were 79.5%, 84.6% and 60.8%, 61.1% for each reader, respectively; 74.4%, 74.4% and 63.0%, 61.7% for 2b-value DWI; and 97.4%, 97.4% and 73.1%, 76.0% for combined MRI. The specificity and negative predictive values (NPVs) were 64.3%, 62.5% and 81.8%, 85.4% for 5b-value DWI; 69.6%, 67.9% and 79.6%, 79.2% for 2b-value DWI; and 75.0%, 78.6% and 97.7%, 97.8% for combined MRI. Good observer agreement was observed in the 5b-value DWI. The 5b-value DWI based on multiple b-values might have the potential to complement the 2b-value DWI; however, their diagnostic performance tended to be inferior to that of combined MRI for the characterization of breast tumors.

Breast Mass Detection and Classification Using Machine Learning Approaches on Two-Dimensional Mammogram: A Review.

Breast cancer is a leading cause of mortality among women, both in India and globally. The prevalence of breast masses is notably common in women aged 20 to 60. These breast masses are classified, according to the breast imaging-reporting and data systems (BI-RADS) standard, into categories such as fibroadenoma, breast cysts, benign, and malignant masses. To aid in the diagnosis of breast disorders, imaging plays a vital role, with mammography being the most widely used modality for detecting breast abnormalities over the years. However, the process of identifying breast diseases through mammograms can be time-consuming, requiring experienced radiologists to review a significant volume of images. Early detection of breast masses is crucial for effective disease management, ultimately reducing mortality rates. To address this challenge, advancements in image processing techniques, specifically utilizing artificial intelligence (AI) and machine learning (ML), have tiled the way for the development of decision support systems. These systems assist radiologists in the accurate identification and classification of breast disorders. This paper presents a review of various studies where diverse machine learning approaches have been applied to digital mammograms. These approaches aim to identify breast masses and classify them into distinct subclasses such as normal, benign and malignant. Additionally, the paper highlights both the advantages and limitations of existing techniques, offering valuable insights for the benefit of future research endeavors in this critical area of medical imaging and breast health.

A Rare Case of Chondrolipoma of the Breast

In 1971, Arrigoni MG et al., used the term “hamartoma” for breast lesions in 10 patients who presented with encapsulated breast tumours clinically and grossly resembling fibroadenomas. Hamartomas in breast lesions are very uncommon and include adenolipoma and chondrolipoma. Despite the availability of imaging modalities, it is often difficult to distinguish fibroadenoma from breast carcinoma. Chondrolipoma of the breast is a rare benign mesenchymal tumour composed of adipose and mature cartilaginous tissue, which is often mistaken for malignant lesions in preoperative studies, leading to overdiagnosis and overtreatment. Hence, a proper histopathological examination is required for a correct diagnosis. Only eight cases have been reported in the literature. This report presents one such rare case of lump in a 67-year-old female, which was suspected to be a fibroadenoma clinically and radiologically, but was diagnosed as chondrolipoma on histopathological examination. All routine investigations were within normal limits, and a clinical diagnosis of fibroadenoma was made. Mammography was done, comprising fat, soft tissue, and calcific strandings along with coarse calcific specks suggestive of BI-RADS (Breast Imaging-Reporting and Data System) Category 3: high probability of being benign.

Variability in Breast Density Estimation and Its Impact on Breast Cancer Risk Assessment.

Breast density is an independent risk factor for breast cancer, although variability exists in measurements. This study sought to evaluate the agreement between radiologists and automated breast density assessment software and assess the impact of breast density measures on breast cancer risk estimates using the Breast Cancer Surveillance Consortium (BCSC) model (v.2). A retrospective database search identified women who had undergone mammography between December 2021 and June 2022. The Breast Imaging Reporting and Data System (BI-RADS) breast composition index assigned by a radiologist (R) was recorded and analyzed using three commercially available software programs (S1, S2, and S3). The agreement rate and Cohen's kappa (κ) were used to evaluate inter-rater agreements concerning breast density measures. The 5-year risk of invasive breast cancer in women was calculated using the BCSC model (v.2) with breast density inputs from various density estimation methods. Absolute differences in risk between various density measurements were evaluated. Overall, 1,949 women (mean age, 53.2 years) were included. The inter-rater agreement between R, S1, and S2 was 75.0-75.6%, while that between S3 and the others was 60.2%-63.3%. Kappa was substantial between R, S1, and S2 (0.66-0.68), and moderate (0.49-0.50) between S3 and the others. S3 placed fewer women in mammographic density d (14.9%) than R, S1, and S2 (40.5%-44.0%). In BCSC risk assessment (v.2), S3 assessed fewer women with a high 5-year risk of invasive breast cancer than the other methods, resulting in an absolute difference of 0% between R, S1, and S2 in 75.0%-75.6% of cases, whereas the difference between S3 and the other methods occurs in 60.2%-63.3% of cases. Breast density assessment using various methods showed moderate-to-substantial agreement, potentially affecting risk assessments. Precise and consistent breast density measurements may lead to personalized and effective strategies for breast cancer prevention.

Unenhanced Breast MRI With Diffusion-Weighted Imaging for Breast Cancer Detection: Effects of Training on Performance and Agreement of Subspecialty Radiologists.

To investigate whether reader training improves the performance and agreement of radiologists in interpreting unenhanced breast magnetic resonance imaging (MRI) scans using diffusion-weighted imaging (DWI). A study of 96 breasts (35 cancers, 24 benign, and 37 negative) in 48 asymptomatic women was performed between June 2019 and October 2020. High-resolution DWI with b-values of 0, 800, and 1200 sec/mm² was performed using a 3.0-T system. Sixteen breast radiologists independently reviewed the DWI, apparent diffusion coefficient maps, and T1-weighted MRI scans and recorded the Breast Imaging Reporting and Data System (BI-RADS) category for each breast. After a 2-h training session and a 5-month washout period, they re-evaluated the BI-RADS categories. A BI-RADS category of 4 (lesions with at least two suspicious criteria) or 5 (more than two suspicious criteria) was considered positive. The per-breast diagnostic performance of each reader was compared between the first and second reviews. Inter-reader agreement was evaluated using a multi-rater κ analysis and intraclass correlation coefficient (ICC). Before training, the mean sensitivity, specificity, and accuracy of the 16 readers were 70.7% (95% confidence interval [CI]: 59.4-79.9), 90.8% (95% CI: 85.6-94.2), and 83.5% (95% CI: 78.6-87.4), respectively. After training, significant improvements in specificity (95.2%; 95% CI: 90.8-97.5; P = 0.001) and accuracy (85.9%; 95% CI: 80.9-89.8; P = 0.01) were observed, but no difference in sensitivity (69.8%; 95% CI: 58.1-79.4; P = 0.58) was observed. Regarding inter-reader agreement, the κ values were 0.57 (95% CI: 0.52-0.63) before training and 0.68 (95% CI: 0.62-0.74) after training, with a difference of 0.11 (95% CI: 0.02-0.18; P = 0.01). The ICC was 0.73 (95% CI: 0.69-0.74) before training and 0.79 (95% CI: 0.76-0.80) after training (P = 0.002). Brief reader training improved the performance and agreement of interpretations by breast radiologists using unenhanced MRI with DWI.