Sonographic features that can be used to differentiate between small triple-negative breast cancer and fibroadenoma

Comparison of the Ultrasonography Features of the Breast in Women with Fibroadenoma and Those with Other Breast Lumps

BACKGROUND

Fibroadenoma (FA) is documented as the most common benign breast disease typically presenting as a lump. A wide variety of other diseases including breast cancer can similarly present as lumps hence the need for further differentiation. Ultrasonography plays a vital role in the evaluation and treatment of breast lumps with histological analysis as the gold standard.

OBJECTIVE

This study compared the physical and sonographic features of the breast in women with FA and women with breast lumps due to other diseases.

MATERIALS AND METHODS

This is a single-centre comparative study. Clinical and sonographic breast evaluations of the recruited patients with lumps were done and reported using the American College of Radiology Breast Imaging Reporting and Data System score. The lumps were biopsied, and histological diagnosis was documented. Clinical and imaging features of the breasts of women with FA were then compared with those of women with lumps from other breast diseases, and collated data were analysed using SPSS Statistical version 23.0.

RESULTS

Data from 118 subjects (59 in each group) were used for this study. There was a significant difference in the physical and sonographic appearance of FA concerning the patient's age, parity, change in lesion size, perilesional architecture, echogenicity, borders, capsule and background breast density. No FA was found in women with less dense breasts.

CONCLUSION

The sonographic features of breasts showed some differences from the corresponding features of FA and other breast lesions. This has the potential to increase the efficiency of pre-operative diagnosis of FA and could be further applied in developing diagnostic criteria for FA in our environment.

Association of imaging and pathological findings of breast cancer in very young women: Report of a twenty-year retrospective study

PURPOSE

In this study, we aimed to assess the new trends in characteristics, molecular subtypes, and imaging findings of breast cancer in very young women.

METHODS

We retrospectively reviewed the database of a primary breast cancer referral center in southern Iran in 342 cases of 30-year-old or younger women from 2001 to 2020. Pathologic data, including nuclear subtype and grade, tumor stage, presence of in situ cancer, imaging data including lesion type in mammogram and ultrasound, and treatment data were recorded. Descriptive statistics were applied. Differences between categorical values between groups were compared using Pearson's Chi-square test.

RESULTS

The mean age was 27.89 years. The tumor type was invasive ductal carcinoma in 82 % of cases. Fourteen patients (4.4 %) had only in situ cancer, and 170 patients had in situ components (49.7 %). Molecular subtypes were available in 278 patients, including 117 (42.1 %) Luminal A, 64 (23.0 %) Luminal B, 58 (20.9 %) triple negative, and 39 (14 %) HER2 Enriched. In those with mammograms available, 63 (30.1 %) had no findings, 53 (25.3 %) had mass, 27 (12.9 %) had asymmetry, whether focal or global, 21 (10 %) had microcalcifications solely, and 45 (21.5 %) had more than one finding. Microcalcifications were significantly more common in Luminal cancers than HER2 and triple-negative cancers (p = 0.041).

CONCLUSION

Our study shows the most common subtype to be Luminal A cancer, with 74 % of the tumors being larger than 2 cm at the time of diagnosis. Irregular masses with non-circumscribed margins were the most common imaging findings.

Ultrasound Radiomics Features to Identify Patients With Triple-Negative Breast Cancer: A Retrospective, Single-Center Study

OBJECTIVES

Patients with triple-negative breast cancer (TNBC) exhibit a fast tumor growth rate and poor survival outcomes. In this study, we aimed to develop and compare intelligent algorithms using ultrasound radiomics features in addition to clinical variables to identify patients with TNBC prior to histopathologic diagnosis.

METHODS

We used single-center, retrospective data of patients who underwent ultrasound before histopathologic verification and subsequent neoadjuvant systemic treatment (NAST). We developed a logistic regression with an elastic net penalty algorithm using pretreatment ultrasound radiomics features in addition to patient and tumor variables to identify patients with TNBC. Findings were compared to the histopathologic evaluation of the biopsy specimen. The main outcome measure was the area under the curve (AUC).

RESULTS

We included 1161 patients, 813 in the development set and 348 in the validation set. Median age was 50.1 years and 24.4% (283 of 1161) had TNBC. The integrative model using radiomics and clinical information showed significantly better performance in identifying TNBC compared to the radiomics model (AUC: 0.71, 95% confidence interval [CI]: 0.65-0.76 versus 0.64, 95% CI: 0.57-0.71, P = .004). The five most important variables were cN status, shape surface volume ratio (SA:V), gray level co-occurrence matrix (GLCM) correlation, gray level dependence matrix (GLDM) dependence nonuniformity normalized, and age. Patients with TNBC were more often categorized as BI-RADS 4 than BI-RADS 5 compared to non-TNBC patients (P = .002).

CONCLUSION

A machine learning algorithm showed promising potential to identify patients with TNBC using ultrasound radiomics features and clinical information prior to histopathologic evaluation.

The value of CT shape quantification in predicting pathological classification of lung adenocarcinoma

OBJECTIVE

To evaluate whether quantification of lung GGN shape is useful in predicting pathological categorization of lung adenocarcinoma and guiding the clinic.

METHODS

98 patients with primary lung adenocarcinoma were pathologically confirmed and CT was performed preoperatively, and all lesions were pathologically ≤ 30 mm in size. On CT images, we measured the maximum area of the lesion's cross-section (MA). The longest diameter of the tumor (LD) was marked with points A and B, and the perpendicular diameter (PD) was marked with points C and D, which was the longest diameter perpendicular to AB. and D, which was the longest diameter perpendicular to AB. We took angles A and B as big angle A (BiA) and small angle A (SmA). We measured the MA, LD, and PD, and for analysis we derived the LD/PD ratio and the BiA/SmA ratio. The data were analysed using the chi-square test, t-test, ROC analysis, and binary logistic regression analysis.

RESULTS

Precursor glandular lesions (PGL) and microinvasive adenocarcinoma (MIA) were distinguished from invasive adenocarcinoma (IAC) by the BiA/SmA ratio and LD, two independent factors (p = 0.007, p = 0.018). Lung adenocarcinoma pathological categorization was indicated by the BiA/SmA ratio of 1.35 and the LD of 11.56 mm with sensitivity of 81.36% and 71.79%, respectively; specificity of 71.79% and 74.36%, respectively; and AUC of 0.8357 (95% CI: 0.7558-0.9157, p < 0.001), 0.8666 (95% CI: 0.7866-0.9465, p < 0.001), respectively. In predicting the pathological categorization of lung adenocarcinoma, the area under the ROC curve of the BiA/SmA ratio combined with LD was 0.9231 (95% CI: 0.8700-0.9762, p < 0.001), with a sensitivity of 81.36% and a specificity of 89.74%.

CONCLUSIONS

Quantification of lung GGN morphology by the BiA/SmA ratio combined with LD could be helpful in predicting pathological classification of lung adenocarcinoma.

Attitudes of Practicing Radiologists Toward the Management of Palpable Circumscribed Breast Masses

OBJECTIVE

To investigate the attitudes of radiologists toward palpable breast masses with benign features on US and to determine the factors influencing their decision.

METHODS

A 20-question online questionnaire was sent to radiologists with membership of the Iranian Society of Radiology and included questions regarding demographics, practice experience, and management approach to palpable circumscribed breast masses based on patient age and risk factors. Radiologists' management choice for masses in themselves or close relatives/friends was also queried.

RESULTS

In total, 151 radiologists participated (response rate 16%). For palpable breast masses with benign imaging features in women at high risk, the majority of radiologists selected MRI (95/151, 62.9%) and core-needle biopsy (110/151, 72.8%). In average-risk patients, radiologists with >5 years of practice experience selected biopsy more frequently (33/79, 41.8%) than less experienced radiologists (17/79, 23.6%) for patients ≥40 years old (P < 0.001) and patients <40 years old (20/79, 25.3%; 11/72, 15.3%, respectively) (P = 0.014). Similarly, selecting biopsy was more common in radiologists who completed a breast imaging fellowship for patients ≥40 years old (23/45, 51.1% vs 27/106, 25.5%) (P = 0.04), as well as for patients <40 years old (18/45, 40% vs 13/106, 12.3%) (P = 0.02). Radiologists who were <40 years old selected biopsy more frequently if evaluating a mass in themselves (22/86, 25.6%) compared to patients (15/86, 17.4%) (P < 0.001).

CONCLUSION

Radiologist experience and educational background, as well as patient baseline breast cancer risk, can predispose radiologists to choose biopsy for palpable breast masses despite a benign appearance on imaging.

Circumscribed Masses on Breast MRI: Can MRI Features Guide Management?

OBJECTIVE

Management of circumscribed breast masses seen on MRI is largely extrapolated from mammography and US data with limited MRI-specific data available. This study aimed to assess clinical and MRI imaging features of malignant circumscribed breast masses.

METHODS

In this IRB-approved retrospective study, breast MRIs performed between April 1, 2008, and August 30, 2020, containing circumscribed masses, excluding multiple bilateral circumscribed masses, were reviewed. Clinical and imaging features of all eligible masses were recorded, and associations with malignant outcomes were assessed using Fisher's exact test and Wilcoxon rank sum test, with P < 0.05 considered significant.

RESULTS

For the 165 masses that met study criteria in 158 women, the mean age was 48 years (SD 12.0 years). Nine of 165 masses were malignant (5.5%). Round masses were significantly more likely to be malignant (7/37, 18.9%) compared to oval masses (2/128, 1.7%) (P < 0.001). Among masses with available dynamic contrast kinetics data, the malignancy rate was 0/84 (0%) for persistent kinetics, 2/23 (8.7%) for plateau kinetics, and 4/24 (16.7%) for washout kinetics (P = 0.002). The malignancy rate for oval masses without washout kinetics was 0% (0/92). T2 hyperintense masses had a malignancy rate of 7/104 (6.7%), and homogeneously enhancing masses had a malignancy rate of 5/91 (5.5%).

CONCLUSION

These data support the use of mass shape and dynamic contrast enhancement kinetics to guide management of circumscribed breast masses seen by MRI, with oval masses without washout kinetics and any circumscribed mass with persistent kinetics showing no malignancies in this study.

Prevalence of breast fibroadenoma in healthy physical examination population in Guangdong province of China: a cross-sectional study

OBJECTIVE

To provide an accurate assessment of the prevalence of breast fibroadenoma in a large population and to confirm the diagnostic accuracy of ultrasound for fibroadenoma.

DESIGN

This was a cross-sectional survey.

SETTING

This research was conducted at Nanfang Hospital, Guangzhou, Guangdong, China.

PARTICIPANTS

A total of 11 898 women aged 18-40 years who underwent breast screening between 1 January 2019 and 31 December 2019 were included in the fibroadenoma prevalence study. From 1 June 2019 to 31 December 2019, 342 breast lesions with pathology reports and preoperative ultrasound images were collected for diagnostic fibroadenoma testing (vs histological diagnostic testing).

PRIMARY OUTCOME MEASURES

Pearson's χ² test was performed to compare the prevalence of different lesions between age groups, and descriptive statistics were used to report the clinical characteristics of fibroadenoma. For ultrasound diagnosis, fibroadenoma was defined as a well-circumscribed lesion with round or oval shape, consisting of a homogeneously hypoechoic or isoechoic solid mass, located parallel to the chest wall with a smooth margin and no posterior shadowing. Diagnostic test results for breast fibroadenoma were stratified by diagnostic type (histological vs ultrasound).

RESULTS

Of the women aged 18-40 years, 27.6% (3285/11 898) had an ultrasound diagnosis offibroadenoma. Of these, the prevalence of fibroadenoma was stable across age groups (p=0.14) and did not differ between the left and right sides of the breast. Almost two-thirds of women presented with a single fibroadenoma, and most fibroadenomas did not exceed 1 cm in size. The sensitivity and specificity for fibroadenoma were 97.0% (95% CI for sensitivity: 93.7% to 98.8%) and 91.4% (95% CI for specificity: 85.4% to 95.5%) for ultrasonography, respectively.

CONCLUSIONS

The prevalence of fibroadenoma in South China is as high as 27.6%, and ultrasound could be used as a tool to diagnose fibroadenoma.

Ultrasound-based radiomics nomogram for differentiation of triple-negative breast cancer from fibroadenoma

OBJECTIVE

This study aimed to develop a radiomics nomogram that incorporates radiomics, conventional ultrasound (US) and clinical features in order to differentiate triple-negative breast cancer (TNBC) from fibroadenoma.

METHODS

A total of 182 pathology-proven fibroadenomas and 178 pathology-proven TNBCs, which underwent preoperative US examination, were involved and randomly divided into training (n = 253) and validation cohorts (n = 107). The radiomics features were extracted from the regions of interest of all lesions, which were delineated on the basis of preoperative US examination. The least absolute shrinkage and selection operator model and the maximum relevance minimum redundancy algorithm were established for the selection of tumor status-related features and construction of radiomics signature (Rad-score). Then, multivariate logistic regression analyses were utilized to develop a radiomics model by incorporating the radiomics signature and clinical findings. Finally, the usefulness of the combined nomogram was assessed by using the receiver operator characteristic curve, calibration curve, and decision curve analysis (DCA).

RESULTS

The radiomics signature, composed of 12 selected features, achieved good diagnostic performance. The nomogram incorporated with radiomics signature and clinical data showed favorable diagnostic efficacy in the training cohort (AUC 0.986, 95% CI, 0.975-0.997) and validation cohort (AUC 0.977, 95% CI, 0.953-1.000). The radiomics nomogram outperformed the Rad-score and clinical models (p < 0.05). The calibration curve and DCA demonstrated the good clinical utility of the combined radiomics nomogram.

CONCLUSION

The radiomics signature is a potential predictive indicator for differentiating TNBC and fibroadenoma. The radiomics nomogram associated with Rad-score, US conventional features, and clinical data outperformed the Rad-score and clinical models.

ADVANCES IN KNOWLEDGE

Recent advances in radiomics-based US are increasingly showing potential for improved diagnosis, assessment of therapeutic response and disease prediction in oncology. Rad-score is an independent predictive indicator for differentiating TNBC and fibroadenoma. The radiomics nomogram associated with Rad-score, US conventional features, and clinical data outperformed the Rad-score and clinical models.

Value of Histogram of Gray-Scale Ultrasound Image in Differential Diagnosis of Small Triple Negative Breast Invasive Ductal Carcinoma and Fibroadenoma

Objective

To investigate the value of gray-scale ultrasound (US) image histogram in the differential diagnosis between small (≤2.00 cm), oval, or round triple negative breast invasive ductal carcinoma (TN-IDC) and fibroadenoma (FA).

Methods

Fifty-five cases of triple negative breast invasive ductal carcinoma (TN-IDC group) and 57 cases of breast fibroadenoma (FA group) confirmed by pathology in Hubei cancer hospital from September 2017 to September 2021 were analyzed retrospectively. The gray-scale US images were analyzed by histogram analysis method, from which some parameters (including mean, variance, skewness, kurtosis and 1st, 10th, 50th, 90th and 99th percentile) can be obtained. Intraclass correlation coefficient (ICC) was used to evaluate the inter observer reliability of histogram parameters. Histogram parameters between the TN-IDC and FA groups were compared using independent Student’s t-test or Mann-Whitney U-test, respectively. In addition, the receiver operating characteristic (ROC) curve analysis was used for the significant parameters to calculate the differential diagnosis efficiency.

Results

All the histogram parameters showed excellent inter-reader consistency, with the ICC values ranged from 0.883 to 0.999. The mean value, 1st, 10th, 50th, 90th and 99th percentiles of TN-IDC group were significantly lower than those of FA group (P < 0.05). The area under ROC curve (AUC) values of mean and n percentiles were from 0.807 to 0.848. However, there were no significant differences in variance, skewness and kurtosis between the two groups (P > 0.05).

Conclusion

Histogram analysis of gray-scale US images can well distinguish small, oval, or round TN-IDC from FA.

Non-BRCA Early-Onset Breast Cancer in Young Women

The incidence of breast cancer in younger women is rising. Although early-onset breast cancer is highly associated with biologically aggressive tumors such as triple-negative and human epidermal growth factor 2 (HER2)-positive cancers, the more recent increase is disproportionately driven by an increase in the incidence of luminal cancer. In particular, the increase in de novo stage IV disease and the inherent age-based poorer survival rate among younger women with even early-stage luminal cancers suggest underlying distinct biologic characteristics that are not well understood. Further contributing to the higher number of early-onset breast cancers is pregnancy-associated breast cancer (PABC), which is attributed to persistent increases in maternal age over time. Although guidelines for screening of patients who carry a BRCA1 or BRCA2 gene mutation are well established, this population comprises only a fraction of those with early-onset breast cancer. A lack of screening in most young patients precludes timely diagnosis, underscoring the importance of early education and awareness. The disproportionate disease burden in young women of certain racial and ethnic groups, which is further exacerbated by socioeconomic disparity in health care, results in worse outcomes. An invited commentary by Monticciolo is available online. ^©RSNA, 2022.

Predicting lung adenocarcinoma invasiveness by measurement of pure ground-glass nodule roundness by using multiplanar reformation: a retrospective analysis

AIM

To explore the value of roundness measurement based on thin-section axial, coronal, and sagittal section computed tomography (CT) images for predicting pure ground-glass nodule (pGGN) invasiveness.

MATERIALS AND METHODS

A total of 168 pGGNs in 155 patients (44 male, 111 females; mean age, 55.74 ± 10.57 years), and confirmed by surgery and histopathology, were analysed retrospectively and divided into pre-invasive (n=72) and invasive (n=96) groups. Photoshop (CS6) software was used to measure pGGN roundness based on conventional axial section, as well as coronal and sagittal sections generated by multiplanar reformation, from thin-section (1-mm-thick) CT lung images.

RESULTS

pGGN roundness values, measured in axial, coronal, and sagittal thin-section CT sections from the pre-invasive group were 0.8 ± 0.049, 0.816 ± 0.05, and 0.818 ± 0.043, respectively, while those in the invasive group were 0.745 ± 0.077, 0.684 ± 0.106, and 0.678 ± 0.106; differences between the two groups were significant (all p<0.001). Binary logistic regression analysis showed that roundness values based on coronal and sagittal sections (p<0.001) were better than those from axial sections (p>0.05) in predicting pGGN invasiveness, with odds ratio (OR) values of 14.858 and 23.315, respectively. ROC analysis showed that evaluation of roundness measured in sagittal sections was better at predicting pGGN invasiveness than when coronal sections were used (AUC 0.870 versus 0.832).

CONCLUSION

Roundness is useful for predicting pGGN invasiveness, with measurements from coronal and sagittal sections better than those from conventional axial sections, with sagittal section images having the best predictive value.

Systematic Review and Meta-analysis of the Malignant Ultrasound Features of Triple-Negative Breast Cancer

OBJECTIVES

The malignant ultrasound (US) features of breast cancer are known to include an irregular shape, a noncircumscribed margin, an echogenic halo, a nonparallel orientation, posterior acoustic attenuation, microcalcification, and others. However, these US features are uncertain and controversial for the diagnosis of triple-negative breast cancer (TNBC). This study aimed to analyze the diagnostic value of malignant US features for TNBC by a systematic review and meta-analysis, analyze the US characteristics of TNBC, and provide US evidence for clinical diagnosis.

METHODS

A comprehensive search was performed to identify relevant English articles concerning the US diagnosis of TNBC (from the date of database establishment to November 2019). The pooled sensitivity, pooled specificity, positive likelihood ratio, negative likelihood ratio, diagnostic odds ratio with 95% confidence interval, summary receiver operating characteristic curve, and area under the curve for the different malignant US features were calculated.

RESULTS

Ten studies (620 patients) met the eligibility criteria. The sensitivity (range, 0.14-0.68) and specificity (range, 0.19-0.66) of the malignant US features were not high. Summary receiver operating characteristic curves showed that the area under the curve (range, 0.25-0.47) of the malignant US features was low, demonstrating that these features have poor diagnostic value for TNBC. The positive likelihood ratio (range, 0.4-to 0.9) of the malignant US features was low, and the negative likelihood ratio (range, 1.09-2.02) was not low, revealing that these features had a poor ability to confirm or exclude TNBC.

CONCLUSIONS

Triple-negative breast cancer lacks the typical malignant US features of breast cancer and has its own US features.

Characterization of soft tissue tumours with ultrasound, shear wave elastography and MRI

OBJECTIVE

To predict accurately whether a soft tissue mass was benign or malignant and to characterize its type using ultrasound, shear wave elastography and MRI. We hypothesized that with the addition of shear wave elastography, it would be possible to determine a threshold velocity value to classify a lesion as benign or malignant.

MATERIALS AND METHODS

A total of 151 consecutive, consenting adult patients were prospectively recruited to this study in a tertiary referral musculoskeletal oncology centre. All lesions were assessed with ultrasound, including B mode, Doppler and shear wave elastography measurements. One hundred thirty-eight patients also underwent MRI of the lesion. A histological diagnosis was obtained for all lesions.

RESULTS

Malignant lesions were larger than benign lesions and had a greater Doppler activity. There was no useful threshold shear wave velocity to differentiate between benign and malignant lesions. Longitudinal and transverse shear wave velocities were strongly positively correlated with each other. An inverse correlation was shown with lesion size and depth, regardless of whether it was benign or malignant. A logistic regression model combining the ultrasound and MRI characteristics did not confidently classify a lesion as benign or malignant and was inferior to expert opinion.

CONCLUSION

The strongest predictors of malignancy are large lesion size and high vascularity. The combination of all ultrasound characteristics (including shear wave elastography) and MRI features does not confidently classify a lesion as benign or malignant, and histological diagnosis remains the gold standard.

Breast Cancer Assessment With Pulse-Echo Speed of Sound Ultrasound From Intrinsic Tissue Reflections: Proof-of-Concept

PURPOSE

The aim of this study was to differentiate malignant and benign solid breast lesions with a novel ultrasound (US) technique, which measures speed of sound (SoS) using standard US transducers and intrinsic tissue reflections and scattering (speckles) as internal reference.

MATERIALS AND METHODS

This prospective, institutional review board-approved, Health Insurance Portability and Accountability Act-compliant prospective comparison study was performed with prior written informed consent from 20 women. Ten women with histological proven breast cancer and 10 with fibroadenoma were measured. A conventional US system with a linear probe was used for SoS-US (SonixTouch; Ultrasonix, Richmond, British Columbia, Canada). Tissue speckle reflections served as a timing reference for the US signals transmitted through the breasts. Relative phase inconsistencies were detected using plane wave measurements from different angular directions, and SoS images with 0.5-mm resolution were generated using a spatial domain reconstruction algorithm. The SoS of tumors were compared with the breast density of a larger cohort of 106 healthy women.

RESULTS

Breast lesions show focal increments ΔSoS (meters per second) with respect to the tissue background. Peak ΔSoS values were evaluated. Breast carcinoma showed significantly higher ΔSoS than fibroadenomas ([INCREMENT]SoS > 41.64 m/s: sensitivity, 90%; specificity, 80%; area under curve, 0.910) and healthy breast tissue of different densities (area under curve, 0.938; sensitivity, 90%; specificity, 96.5%). The lesion localization in SoS-US images was consistent with B-mode imaging and repeated SoS-US measurements were reproducible.

CONCLUSIONS

Using SoS-US, based on conventional US and tissue speckles as timing reference, breast carcinoma showed significantly higher SoS values than fibroadenoma and healthy breast tissue of different densities. The SoS presents a promising technique for differentiating solid breast lesions.

Benign Disorders of the Breast in Pregnancy and Lactation

Benign cystic or solid lumps frequently occur in the breasts of young women, and consequently can also be seen during pregnancy and lactation. Simple cysts do not increase the risk of malignancy. The current management is routine follow-up. Complex cysts are thick walled or contain a mass, and should be followed by a US-guided biopsy and then treated similar to any non-gravid, non-lactating patient.Galactoceles can be detected during the last trimester of pregnancy and during or after stopping lactation. Aspiration can be done to confirm the content. Co-existence of galactocele and malignancy is extremely rare, and the key is to follow up until it resolves.Fibroadenoma is the most frequent lesion found during pregnancy and lactation. Management is usually conservative after triple assessment. Surgery is usually not recommended in pregnant and lactating women unless rapid increase in size occurs or there is discordance in the triple assessment.Lactating adenomas are sometimes interpreted as a variant of fibroadenoma . They can naturally disappear at the end of pregnancy or lactation. Management is usually conservative, and an excisional biopsy is only mandated if it is rapidly enlarging or if there is discordance in the triple assessment.Gestational gigantomastia is a rare condition consisting of diffuse severe hypertrophy of both breasts during pregnancy . Mastectomy and reconstruction may rarely be required in such cases.

Radiomics of US texture features in differential diagnosis between triple-negative breast cancer and fibroadenoma

Triple-negative breast cancer (TNBC) is sometimes mistaken for fibroadenoma due to its tendency to show benign morphology on breast ultrasound (US) albeit its aggressive nature. This study aims to develop a radiomics score based on US texture analysis for differential diagnosis between TNBC and fibroadenoma, and to evaluate its diagnostic performance compared with pathologic results. We retrospectively included 715 pathology-proven fibroadenomas and 186 pathology-proven TNBCs which were examined by three different US machines. We developed the radiomics score by using penalized logistic regression with a least absolute shrinkage and selection operator (LASSO) analysis from 730 extracted features consisting of 14 intensity-based features, 132 textural features and 584 wavelet-based features. The constructed radiomics score showed significant difference between fibroadenoma and TNBC for all three US machines (p < 0.001). Although the radiomics score showed dependency on the type of US machine, we developed more elaborate radiomics score for a subgroup in which US examinations were performed with iU22. This subsequent radiomics score also showed good diagnostic performance, even for BI-RADS category 3 or 4a lesions (AUC 0.782) which were presumed as probably benign or low suspicious of malignancy by radiologists. It was expected to assist radiologist’s diagnosis and reduce the number of invasive biopsies, although US standardization should be overcome before clinical application.