A predictive model using MRI and clinicopathologic features for breast cancer recurrence in young women treated with upfront surgery.

OBJECTIVES: To identify preoperative breast MR imaging and clinicopathological variables related to recurrence and develop a risk prediction model for recurrence in young women with breast cancer treated with upfront surgery. METHODS: This retrospective study analyzed 438 consecutive women with breast cancer aged 35 years or younger between January 2007 and December 2016. Breast MR images before surgery were independently reviewed by breast radiologists blinded to patient outcomes. The clinicopathological data including patient demographics, clinical features, and tumor characteristics were reviewed. Univariate and multivariate logistic regression analyses were used to identify the independent factors associated with recurrence. The risk prediction model for recurrence was developed, and the discrimination and calibration abilities were assessed. RESULTS: Of 438 patients, 95 (21.7%) developed recurrence after a median follow-up of 65 months. Tumor size at MR imaging (HR = 1.158, p = 0.006), multifocal or multicentric disease (HR = 1.676, p = 0.017), and peritumoral edema on T2WI (HR = 2.166, p = 0.001) were identified as independent predictors of recurrence, while adjuvant endocrine therapy (HR = 0.624, p = 0.035) was inversely associated with recurrence. The prediction model showed good discrimination ability in predicting 5-year recurrence (C index, 0.707 in the development cohort; 0.686 in the validation cohort) and overall recurrence (C index, 0.699 in the development cohort; 0.678 in the validation cohort). The calibration plot demonstrated an excellent correlation (concordance correlation coefficient, 0.903). CONCLUSION: A prediction model based on breast MR imaging and clinicopathological features showed good discrimination to predict recurrence in young women with breast cancer treated with upfront surgery, which could contribute to individualized risk stratification. CLINICAL RELEVANCE STATEMENT: Our prediction model, incorporating preoperative breast MR imaging and clinicopathological features, predicts recurrence in young women with breast cancer undergoing upfront surgery, facilitating personalized risk stratification and informing tailored management strategies. KEY POINTS: Younger women with breast cancer have worse outcomes than those diagnosed at more typical ages. The described prediction model showed good discrimination performance in predicting 5-year and overall recurrence. Incorporating better risk stratification tools in this population may help improve outcomes.

Use of a commercial artificial intelligence-based mammography analysis software for improving breast ultrasound interpretations.

OBJECTIVES: To evaluate the use of a commercial artificial intelligence (AI)-based mammography analysis software for improving the interpretations of breast ultrasound (US)-detected lesions. METHODS: A retrospective analysis was performed on 1109 breasts that underwent both mammography and US-guided breast biopsy. The AI software processed mammograms and provided an AI score ranging from 0 to 100 for each breast, indicating the likelihood of malignancy. The performance of the AI score in differentiating mammograms with benign outcomes from those revealing cancers following US-guided breast biopsy was evaluated. In addition, prediction models for benign outcomes were constructed based on clinical and imaging characteristics with and without AI scores, using logistic regression analysis. RESULTS: The AI software had an area under the receiver operating characteristics curve (AUROC) of 0.79 (95% CI, 0.79-0.82) in differentiating between benign and cancer cases. The prediction models that did not include AI scores (non-AI model), only used AI scores (AI-only model), and included AI scores (integrated model) had AUROCs of 0.79 (95% CI, 0.75-0.83), 0.78 (95% CI, 0.74-0.82), and 0.85 (95% CI, 0.81-0.88) in the development cohort, and 0.75 (95% CI, 0.68-0.81), 0.82 (95% CI, 0.76-0.88), and 0.84 (95% CI, 0.79-0.90) in the validation cohort, respectively. The integrated model outperformed the non-AI model in the development and validation cohorts (p < 0.001 for both). CONCLUSION: The commercial AI-based mammography analysis software could be a valuable adjunct to clinical decision-making for managing US-detected breast lesions. CLINICAL RELEVANCE STATEMENT: The commercial AI-based mammography analysis software could potentially reduce unnecessary biopsies and improve patient outcomes. KEY POINTS: • Breast US has high rates of false-positive interpretations. • A commercial AI-based mammography analysis software could distinguish mammograms having benign outcomes from those revealing cancers after US-guided breast biopsy. • A commercial AI-based mammography analysis software may improve interpretations for breast US-detected lesions.

Statistical Methods for Comparing Predictive Values in Medical Diagnosis.

Evaluating the performance of a binary diagnostic test, including artificial intelligence classification algorithms, involves measuring sensitivity, specificity, positive predictive value, and negative predictive value. Particularly when comparing the performance of two diagnostic tests applied on the same set of patients, these metrics are crucial for identifying the more accurate test. However, comparing predictive values presents statistical challenges because their denominators depend on the test outcomes, unlike the comparison of sensitivities and specificities. This paper reviews existing methods for comparing predictive values and proposes using the permutation test. The permutation test is an intuitive, non-parametric method suitable for datasets with small sample sizes. We demonstrate each method using a dataset from MRI and combined modality of mammography and ultrasound in diagnosing breast cancer.

Prediction of the MammaPrint Risk Group Using MRI Features in Women With Estrogen Receptor-Positive, HER2-Negative, and 1 to 3 Node-Positive Invasive Breast Cancer.

BACKGROUND: MammaPrint assigns chemotherapeutic benefits to patients with estrogen receptor (ER)-positive, human epidermal growth factor receptor 2 (HER2)-negative, and 1 to 3 node-positive invasive breast cancer. However, its cost and time-consuming nature limit its use in certain clinical settings. We aimed to develop and validate the prediction models for the low MammaPrint risk group using clinicopathologic and MRI features. PATIENTS AND METHODS: Overall, 352 women with ER-positive, HER2-negative, and 1 to 3 node-positive invasive breast cancer were retrospectively reviewed and assigned to development (n = 235) and validation sets (n = 117). Univariate and multivariate analyses identified features associated with the low MammaPrint risk group. The area under the receiver operating characteristic curves (AUROCs) of models based on clinicopathologic, MRI, and combined features were evaluated. RESULTS: Development set multivariate analysis showed that clinicopathologic features including low histologic grade (odds ratio [OR], 5.29; P = .02), progesterone receptor-positivity (OR, 3.23; P = .01), and low Ki-67 (OR, 6.05; P < .001) and MRI features, including peritumoral edema absence (OR, 2.24; P = .04) and a high proportion of persistent components (OR, 1.15; P = .004) were significantly associated with the low MammaPrint risk group. The AUROCs of models based on clinicopathologic, MRI, and combined features were 0.77, 0.64, and 0.80 in the development and 0.66, 0.60, and 0.70 in the validation sets, respectively. CONCLUSION: The combined model incorporating clinicopathologic and MRI features showed potential in predicting the low MammaPrint risk group, and may support decision-making in clinical settings with limited access to MammaPrint.

High-resolution diffusion-weighted MRI plus mammography for detecting clinically occult breast cancers in women with dense breasts.

PURPOSE: To compare the performance of mammography, high-resolution DW-MRI, DCE-MRI, and their combinations in detecting clinically occult breast cancer in women with dense breasts. METHOD: 544 breasts from 281 consecutive asymptomatic women with dense breasts were retrospectively identified. They underwent breast MRI for preoperative evaluation of breast cancers (n = 214) or as supplemental screening (n = 67) including DCE-MRI and DW-MRI (b values, 0 and 1000 sec/mm2; in-plane resolution, 1.1 × 1.1 mm2 and 1.3 × 1.3 mm2; section thickness, 3 mm), in addition to mammography. Three readers independently reviewed each examination on a per-breast basis. Histopathology and at least two year of imaging follow-up served as the gold standard. The sensitivities and specificities of different imaging modalities were compared using McNemar test. RESULTS: 230 of 544 breasts (42 %) had malignant lesions. The sensitivity of DW-MRI was higher than that of mammography (77.0 % vs 57.9 %; adjusted p < 0.001), but lower than that of DCE-MRI (84.8 %; adjusted p = 0.014). The specificity of DW-MRI was comparable to those of mammography (98.1 % vs 99.1 %; adjusted p > 0.999) and DCE-MRI (97.1 %; adjusted p > 0.999). DW-MRI plus mammography had a comparable sensitivity and specificity to those of DCE-MRI plus mammography (88.6 % vs 90.9 % and 97.1 % vs 96.2 %; adjusted p > 0.999 for both). CONCLUSIONS: High-resolution DW-MRI had a sensitivity higher than mammography and lower than DCE-MRI. Nevertheless, DW-MRI plus mammography showed a comparable sensitivity and specificity to DCE-MRI plus mammography for detecting clinically occult cancers in women with dense breasts.

Background Breast Parenchymal Signal During Menstrual Cycle on Diffusion-Weighted MRI: A Prospective Study in Healthy Premenopausal Women.

OBJECTIVE: To prospectively investigate the influence of the menstrual cycle on the background parenchymal signal (BPS) and apparent diffusion coefficient (ADC) of the breast on diffusion-weighted MRI (DW-MRI) in healthy premenopausal women. MATERIALS AND METHODS: Seven healthy premenopausal women (median age, 37 years; range, 33-49 years) with regular menstrual cycles participated in this study. DW-MRI was performed during each of the four phases of the menstrual cycle (four examinations in total). Three radiologists independently assessed the BPS visual grade on images with b-values of 800 sec/mm² (b800), 1200 sec/mm² (b1200), and a synthetic 1500 sec/mm² (sb1500). Additionally, one radiologist conducted a quantitative analysis to measure the BPS volume (%) and ADC values of the BPS (ADCBPS) and fibroglandular tissue (ADCFGT). Changes in the visual grade, BPS volume (%), ADCBPS, and ADCFGT during the menstrual cycle were descriptively analyzed. RESULTS: The visual grade of BPS in seven women varied from mild to marked on b800 and from minimal to moderate on b1200 and sb1500. As the b-value increased, the visual grade of BPS decreased. On b800 and sb1500, two of the seven volunteers showed the highest visual grade in the early follicular phase (EFP). On b1200, three of the seven volunteers showed the highest visual grades in EFP. The BPS volume (%) on b800 and b1200 showed the highest value in three of the six volunteers with dense breasts in EFP. Three of the seven volunteers showed the lowest ADCBPS in the EFP. Four of the seven volunteers showed the highest ADCBPS in the early luteal phase (ELP) and the lowest ADCFGT in the late follicular phase (LFP). CONCLUSION: Most volunteers did not exhibit specific BPS patterns during their menstrual cycles. However, the highest BPS and lowest ADCBPS were more frequently observed in EFP than in the other menstrual cycle phases, whereas the highest ADCBPS was more common in ELP. The lowest ADCFGT was more frequent in LFP.

Diagnostic yield of contrast-enhanced abdominal staging CT in patients with initially diagnosed breast cancer.

PURPOSE: To estimate the diagnostic yield (DY) of abdominal staging CT for detecting breast cancer liver metastasis (BCLM) in patients with initially diagnosed breast cancer and to determine the indications for abdominal staging CT. METHODS: Patients with newly diagnosed breast cancer who underwent abdominal CT as an initial staging work-up between January 2019 and December 2020 were retrospectively analyzed. DY was calculated and analyzed according to patient age, type of treatments, histologic type, histologic grade, lymphovascular invasion, Ki-67 status, hormone receptor status, subtype, and the American Joint Committee on Cancer anatomical staging. RESULTS: A total of 2056 patients (mean age, 51 ± 11 years) were included. The DY of abdominal staging CT for detecting BCLM was 1.1 % (22 of 2056). DY was significantly higher in stage III than in stage I or II cancers (3.9 % [18 of 467] vs. 0 % [0 of 412] or 0.4 % [4 of 1158], respectively, p < .001), and in human epidermal growth factor receptor-2 (HER2)-enriched cancers than in luminal or triple negative cancers (2.9 % [16 of 560] vs. 0.4 % [4 of 1090] or 0.5 % [2 of 406], respectively, p < .001). CONCLUSIONS: The DY of abdominal staging CT for detecting BCLM was low among all patients with initially diagnosed breast cancer. However, although abdominal staging CT for detecting BCLM is probably unnecessary in all patients, it can be clinically useful in patients with stage III or human epidermal growth factor receptor-2-enriched breast cancers.

Optimizing angular range in digital breast tomosynthesis: A phantom study investigating lesion detection across varied breast density and thickness.

PURPOSE: To determine the optimal angular range (AR) for digital breast tomosynthesis (DBT) systems that provides highest lesion visibility across various breast densities and thicknesses. METHOD: A modular DBT phantom, consisting of tissue-equivalent adipose and glandular modules, along with a module embedded with test objects (speckles, masses, fibers), was used to create combinations simulating different breast thicknesses, densities, and lesion locations. A prototype DBT system operated at four ARs (AR±7.5°, AR±12.5°, AR±19°, and AR±25°) to acquire 11 projection images for each combination, with separate fixed doses for thin and thick combinations. Three blinded radiologists independently assessed lesion visibility in reconstructed images; assessments were averaged and compared using linear mixed models. RESULTS: Speckle visibility was highest with AR±7.5° or AR±12.5°, decreasing with wider ARs in all density and thickness combinations. The difference between AR±7.5° and AR±12.5° was not statistically significant, except for the tube-side speckles in thin-fatty combinations (5.83 [AR±7.5°] vs. 5.39 [AR±12.5°], P = 0.019). Mass visibility was not affected by AR in thick combinations, while AR±12.5° exhibited the highest mass visibility for both thin-fatty and thin-dense combinations (P = 0.032 and 0.007, respectively). Different ARs provided highest fiber visibility for different combinations; however, AR±12.5° consistently provided highest or comparable visibility. AR±12.5° showed highest overall lesion visibility for all density and thickness combinations. CONCLUSIONS: AR±12.5° exhibited the highest overall lesion visibility across various phantom thicknesses and densities using a projection number of 11.