Artificial Intelligence for Breast Ultrasound: AJR Expert Panel Narrative Review.

Breast ultrasound is used in a wide variety of clinical scenarios, including both diagnostic and screening applications. Limitations of ultrasound, however, include its low specificity and, for automated breast ultrasound screening, the time necessary to review whole-breast ultrasound images. As of this writing, four AI tools that are approved or cleared by the FDA address these limitations. Current tools, which are intended to provide decision support for lesion classification and/or detection, have been shown to increase specificity among non-specialists and to decrease interpretation times. Potential future applications include triage of patients with palpable masses in low-resource settings, preoperative prediction of axillary lymph node metastasis, and preoperative prediction of neoadjuvant chemotherapy response. Challenges in the development and clinical deployment of AI for ultrasound include: the limited availability of curated training datasets compared to mammography; the high variability in ultrasound image acquisition due to equipment- and operator-related factors (which may limit algorithm generalizability); and the lack of post-implementation evaluation studies. Furthermore, current AI tools for lesion classification were developed based on 2D data, but diagnostic accuracy could potentially be improved if multimodal ultrasound data were used, such as color Doppler, elastography, cine clips, and 3D imaging.

Artificial Intelligence for Breast Cancer Detection on Mammography: Factors Related to Cancer Detection.

RATIONALE AND OBJECTIVES: Little is known about the factors affecting the Artificial Intelligence (AI) software performance on mammography for breast cancer detection. This study was to identify factors associated with abnormality scores assigned by the AI software. MATERIALS AND METHODS: A retrospective database search was conducted to identify consecutive asymptomatic women who underwent breast cancer surgery between April 2016 and December 2019. A commercially available AI software (Lunit INSIGHT, MMG, Ver. 1.1.4.0) was used for preoperative mammography to assign individual abnormality scores to the lesions and score of 10 or higher was considered as positive detection by AI software. Radiologists without knowledge of the AI results retrospectively assessed the mammographic density and classified mammographic findings into positive and negative finding. General linear model (GLM) analysis was used to identify the clinical, pathological, and mammographic findings related to the abnormality scores, obtaining coefficient ß values that represent the mean difference per unit or comparison with the reference value. Additionally, the reasons for non-detection by the AI software were investigated. RESULTS: Among the 1001 index cancers (830 invasive cancers and 171 ductal carcinoma in situs) in 1001 patients, 717 (72%) were correctly detected by AI, while the remaining 284 (28%) were not detected. Multivariable GLM analysis showed that abnormal mammography findings (ß = 77.0 for mass, ß = 73.1 for calcification only, ß = 49.4 for architectural distortion, and ß = 47.6 for asymmetry compared to negative; all Ps < 0.001), invasive tumor size (ß = 4.3 per 1 cm, P < 0.001), and human epidermal growth receptor type 2 (HER2) positivity (ß = 9.2 compared to hormone receptor positive, HER2 negative, P = 0.004) were associated with higher mean abnormality score. AI failed to detect small asymmetries in extremely dense breasts, subcentimeter-sized or isodense lesions, and faint amorphous calcifications. CONCLUSION: Cancers with positive abnormal mammographic findings on retrospective review, large invasive size, HER2 positivity had high AI abnormality scores. Understanding the patterns of AI software performance is crucial for effectively integrating AI into clinical practice.

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

OBJECTIVE: 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). MATERIALS AND METHODS: 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). RESULTS: 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). CONCLUSION: Brief reader training improved the performance and agreement of interpretations by breast radiologists using unenhanced MRI with DWI.

Artificial Intelligence Improves Detection of Supplemental Screening Ultrasound-detected Breast Cancers in Mammography.

Despite recent advances in artificial intelligence (AI) software with improved performance in mammography screening for breast cancer, insufficient data are available on its performance in detecting cancers that were initially missed on mammography. In this study, we aimed to determine whether AI software-aided mammography could provide additional value in identifying cancers detected through supplemental screening ultrasound. We searched our database from 2017 to 2018 and included 238 asymptomatic patients (median age, 50 years; interquartile range, 45-57 years) diagnosed with breast cancer using supplemental ultrasound. Two unblinded radiologists retrospectively reviewed the mammograms using commercially available AI software and identified the reasons for missed detection. Clinicopathological characteristics of AI-detected and AI-undetected cancers were compared using univariate and multivariate logistic regression analyses. A total of 253 cancers were detected in 238 patients using ultrasound. In an unblinded review, the AI software failed to detect 187 of the 253 (73.9%) mammography cases with negative findings in retrospective observations. The AI software detected 66 cancers (26.1%), of which 42 (63.6%) exhibited indiscernible findings obscured by overlapping dense breast tissues, even with the knowledge of magnetic resonance imaging and post-wire localization mammography. The remaining 24 cases (36.4%) were considered interpretive errors by the radiologists. Invasive tumor size was associated with AI detection after multivariable analysis (odds ratio, 2.2; 95% confidence intervals, 1.5-3.3; p < 0.001). In the control group of 160 women without cancer, the AI software identified 19 false positives (11.9%, 19/160). Although most ultrasound-detected cancers were not detected on mammography with the use of AI, the software proved valuable in identifying breast cancers with indiscernible abnormalities or those that clinicians may have overlooked.

Semiannual Breast US or MRI Screening in Patients with a Personal History of Breast Cancer.

Background The wide variability of screening imaging use in patients with a personal history of breast cancer (PHBC) warrants investigation of its comparative clinical effectiveness. While more intensive screening with US or MRI at an interval of less than 1 year could increase early-stage breast cancer detection, its benefit has not been established. Purpose To investigate the outcomes of semiannual multimodality screening in patients with PHBC. Materials and Methods An academic medical center database was retrospectively searched for patients diagnosed with breast cancer between January 2015 and June 2018 who had undergone annual mammography with either semiannual incidence US or MRI screening from July 2019 to December 2019 and three subsequent semiannual screenings over a 2-year period. The primary outcome was second breast cancers diagnosed during follow-up. Examination-level cancer detection and interval cancer rates were calculated. Screening performances were compared with χ2 or Fisher exact tests or a logistic model with generalized estimating equations. Results Our final cohort included 2758 asymptomatic women (median age, 53 years; range, 20-84 years). Among 5615 US and 1807 MRI examinations, 18 breast cancers were detected after negative findings on a prior semiannual incidence US screening examination; 44% (eight of 18) were stage 0 (three detected with MRI; five, with US), and 39% (seven of 18) were stage I (three detected with MRI; four, with US). MRI had a cancer detection rate up to 17.1 per 1000 examinations (eight of 467; 95% CI: 8.7, 33.4), and the overall cancer detection rates of US and MRI were 1.8 (10 of 5615; 95% CI: 1.0, 3.3) and 4.4 (eight of 1807; 95% CI: 2.2, 8.8) per 1000 examinations, respectively (P = .11). Conclusion Supplemental semiannual US or MRI screening depicted second breast cancers after negative findings at prior semiannual incidence US examination in patients with PHBC. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Berg in this issue.

[Interpretation of Image-Guided Biopsy Results and Assessment]. / ì˜ìƒìœ ë„í•˜ 조직검사의 해석과 íŒì •.

The success of image-guided breast biopsy depends on the biopsy method, needle selection, and appropriate technique based on the accurate judgment by the radiologist at biopsy. However, insufficient or inappropriate sampling of specimens may result in false-negative results or pathologic underestimation. Therefore, image-pathology concordance assessments after biopsy are essential for appropriate patient management. Particularly, the assessment of image-pathology concordance can avoid false-negative reports of breast cancer as a benign pathology. Therefore, this study aimed to discuss factors that impact the accurate interpretation of image-guided breast biopsy along with the appropriate assessments.

Use of imaging prediction model for omission of axillary surgery in early-stage breast cancer patients.

PURPOSE: To develop a prediction model incorporating clinicopathological information, US, and MRI to diagnose axillary lymph node (LN) metastasis with acceptable false negative rate (FNR) in patients with early stage, clinically node-negative breast cancers. METHODS: In this single center retrospective study, the inclusion criteria comprised women with clinical T1 or T2 and N0 breast cancers who underwent preoperative US and MRI between January 2017 and July 2018. Patients were temporally divided into the development and validation cohorts. Clinicopathological information, US, and MRI findings were collected. Two prediction models (US model and combined US and MRI model) were created using logistic regression analysis from the development cohort. FNRs of the two models were compared using the McNemar test. RESULTS: A total of 964 women comprised the development (603 women, 54 ± 11 years) and validation (361 women, 53 ± 10 years) cohorts with 107 (18%) and 77 (21%) axillary LN metastases in each cohort, respectively. The US model consisted of tumor size and morphology of LN on US. The combined US and MRI model consisted of asymmetry of LN number, long diameter of LN, tumor type, and multiplicity of breast cancers on MRI, in addition to tumor size and morphology of LN on US. The combined model showed significantly lower FNR than the US model in both development (5% vs. 32%, P < .001) and validation (9% vs. 35%, P < .001) cohorts. CONCLUSION: Our prediction model combining US and MRI characteristics of index cancer and LN lowered FNR compared to using US alone, and could potentially lead to avoid unnecessary SLNB in early stage, clinically node-negative breast cancers.

Role of Doppler US and elastography prior to biopsy to identify candidates for avoidance of surgery following neoadjuvant chemotherapy for breast cancer.

PURPOSE: This study aimed to evaluate the role of Doppler ultrasound (US) and elastography to identify residual breast cancer for patients showing near complete response following chemotherapy on magnetic resonance imaging (MRI). METHODS: Between September 2016 and January 2018, 40 breast cancer patients who showed near complete response (either tumor size ≤0.5 cm or lesion-to-background parenchymal signal enhancement ratio ≤1.6) on MRI following neoadjuvant chemotherapy were prospectively enrolled. After excluding seven women who did not undergo Doppler US and elastography, 33 women (median age, 49 years; range, 32 to 67 years) were analyzed. On the day of surgery, women underwent Doppler US and elastography for tumor bed prior to US-guided core needle biopsy. Histopathologic results of biopsy and surgery were evaluated. Negative predictive value (NPV) and false negative rate (FNR) of biopsy and the combined Doppler US and elastography were analyzed, respectively. RESULTS: After surgery, nine women had residual cancers and 24 women had pathologic complete response. The NPV and FNR of biopsy were 92% (24 of 26) and 22% (2 of 9), respectively. The NPV and FNR of combined Doppler US and elastography were 100% (14 of 14) and 0% (0 of 9), respectively. All of nine women with residual cancers had positive vascularity or elasticity. Two women with false-negative biopsy results, having 0.3 cm or 2.5 cm ductal carcinoma in situ at surgery, showed positive vascularity or elasticity. CONCLUSION: Tumor bed showing positive vascularity or elasticity indicates residual breast cancer for patients showing near complete response on MRI following chemotherapy.

Digital Breast Tomosynthesis Plus Ultrasound Versus Digital Mammography Plus Ultrasound for Screening Breast Cancer in Women With Dense Breasts.

OBJECTIVE: To compare the outcomes of digital breast tomosynthesis (DBT) screening combined with ultrasound (US) with those of digital mammography (DM) combined with US in women with dense breasts. MATERIALS AND METHODS: A retrospective database search identified consecutive asymptomatic women with dense breasts who underwent breast cancer screening with DBT or DM and whole-breast US simultaneously between June 2016 and July 2019. Women who underwent DBT + US (DBT cohort) and DM + US (DM cohort) were matched using 1:2 ratio according to mammographic density, age, menopausal status, hormone replacement therapy, and a family history of breast cancer. The cancer detection rate (CDR) per 1000 screening examinations, abnormal interpretation rate (AIR), sensitivity, and specificity were compared. RESULTS: A total of 863 women in the DBT cohort were matched with 1726 women in the DM cohort (median age, 53 years; interquartile range, 40-78 years) and 26 breast cancers (9 in the DBT cohort and 17 in the DM cohort) were identified. The DBT and DM cohorts showed comparable CDR (10.4 [9 of 863; 95% confidence interval {CI}: 4.8-19.7] vs. 9.8 [17 of 1726; 95% CI: 5.7-15.7] per 1000 examinations, respectively; P = 0.889). DBT cohort showed a higher AIR than the DM cohort (31.6% [273 of 863; 95% CI: 28.5%-34.9%] vs. 22.4% [387 of 1726; 95% CI: 20.5%-24.5%]; P < 0.001). The sensitivity for both cohorts was 100%. In women with negative findings on DBT or DM, supplemental US yielded similar CDRs in both DBT and DM cohorts (4.0 vs. 3.3 per 1000 examinations, respectively; P = 0.803) and higher AIR in the DBT cohort (24.8% [188 of 758; 95% CI: 21.8%-28.0%] vs. 16.9% [257 of 1516; 95% CI: 15.1%-18.9%; P < 0.001). CONCLUSION: DBT screening combined with US showed comparable CDR but lower specificity than DM screening combined with US in women with dense breasts.

Background Parenchymal Enhancement at Postoperative Surveillance Breast MRI: Association with Future Second Breast Cancer Risk.

Background Background parenchymal enhancement (BPE) is a known risk factor for breast cancer. However, studies on the association between BPE and second breast cancer risk are still lacking. Purpose To investigate whether BPE at surveillance breast MRI is associated with subsequent second breast cancer risk in women with a personal history of breast cancer. Materials and Methods A retrospective search of the imaging database of an academic medical center identified consecutive surveillance breast MRI examinations performed between January 2008 and December 2017 in women who underwent surgery for primary breast cancer and had no prior diagnosis of second breast cancer. BPE at surveillance breast MRI was qualitatively assessed using a four-category classification of minimal, mild, moderate, or marked. Future second breast cancer was defined as ipsilateral breast tumor recurrence or contralateral breast cancer diagnosed at least 1 year after each surveillance breast MRI examination. Factors associated with future second breast cancer risk were evaluated using the multivariable Fine-Gray subdistribution hazard model. Results Among the 2668 women (mean age at baseline surveillance breast MRI, 49 years ± 8 [SD]), 109 developed a second breast cancer (49 ipsilateral, 58 contralateral, and two ipsilateral and contralateral) at a median follow-up of 5.8 years. Mild, moderate, or marked BPE at surveillance breast MRI (hazard ratio [HR], 2.1 [95% CI: 1.4, 3.1]; P < .001), young age (<45 years) at initial breast cancer diagnosis (HR, 3.4 [95% CI: 1.7, 6.4]; P < .001), positive results from a BRCA1/2 genetic test (HR, 6.5 [95% CI: 3.5, 12.0]; P < .001), and negative hormone receptor expression in the initial breast cancer (HR, 1.6 [95% CI: 1.1, 2.6]; P = .02) were independently associated with an increased risk of future second breast cancer. Conclusion Background parenchymal enhancement at surveillance breast MRI was associated with future second breast cancer risk in women with a personal history of breast cancer. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Niell in this issue.

Use of Artificial Intelligence for Reducing Unnecessary Recalls at Screening Mammography: A Simulation Study.

OBJECTIVE: To conduct a simulation study to determine whether artificial intelligence (AI)-aided mammography reading can reduce unnecessary recalls while maintaining cancer detection ability in women recalled after mammography screening. MATERIALS AND METHODS: A retrospective reader study was performed by screening mammographies of 793 women (mean age ± standard deviation, 50 ± 9 years) recalled to obtain supplemental mammographic views regarding screening mammography-detected abnormalities between January 2016 and December 2019 at two screening centers. Initial screening mammography examinations were interpreted by three dedicated breast radiologists sequentially, case by case, with and without AI aid, in a single session. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and recall rate for breast cancer diagnosis were obtained and compared between the two reading modes. RESULTS: Fifty-four mammograms with cancer (35 invasive cancers and 19 ductal carcinomas in situ) and 739 mammograms with benign or negative findings were included. The reader-averaged AUC improved after AI aid, from 0.79 (95% confidence interval [CI], 0.74-0.85) to 0.89 (95% CI, 0.85-0.94) (p < 0.001). The reader-averaged specificities before and after AI aid were 41.9% (95% CI, 39.3%-44.5%) and 53.9% (95% CI, 50.9%-56.9%), respectively (p < 0.001). The reader-averaged sensitivity was not statistically different between AI-unaided and AI-aided readings: 89.5% (95% CI, 83.1%-95.9%) vs. 92.6% (95% CI, 86.2%-99.0%) (p = 0.053), although the sensitivities of the least experienced radiologists before and after AI aid were 79.6% (43 of 54 [95% CI, 66.5%-89.4%]) and 90.7% (49 of 54 [95% CI, 79.7%-96.9%]), respectively (p = 0.031). With AI aid, the reader-averaged recall rate decreased by from 60.4% (95% CI, 57.8%-62.9%) to 49.5% (95% CI, 46.5%-52.4%) (p < 0.001). CONCLUSION: AI-aided reading reduced the number of recalls and improved the diagnostic performance in our simulation using women initially recalled for supplemental mammographic views after mammography screening.

Abbreviated Screening MRI for Women with a History of Breast Cancer: Comparison with Full-Protocol Breast MRI.

Background Few studies have compared abbreviated breast MRI with full-protocol MRI in women with a personal history of breast cancer (PHBC), and they have not adjusted for confounding variables. Purpose To compare abbreviated breast MRI with full-protocol MRI in women with PHBC by using propensity score matching to adjust for confounding variables. Materials and Methods In this single-center retrospective study, women with PHBC who underwent full-protocol MRI (January 2008-August 2017) or abbreviated MRI (September 2017-April 2019) were identified. With use of a propensity score-matched cohort, screening performances were compared between the two MRI groups with the McNemar test or a propensity score-adjusted generalized estimating equation. The coprimary analyses were sensitivity and specificity. The secondary analyses were the cancer detection rate, interval cancer rate, positive predictive value for biopsies performed (PPV3), and Breast Imaging Reporting and Data System (BI-RADS) category 3 short-term follow-up rate. Results There were 726 women allocated to each MRI group (mean age ± SD, 50 years ± 8 for both groups). Abbreviated MRI and full-protocol MRI showed comparable sensitivity (15 of 15 cancers [100%; 95% CI: 78, 100] vs nine of 13 cancers [69%; 95% CI: 39, 91], respectively; P = .17). Abbreviated MRI showed higher specificity than full-protocol MRI (660 of 711 examinations [93%; 95% CI: 91, 95] vs 612 of 713 examinations [86%; 95% CI: 83, 88], respectively; P < .001). The cancer detection rate (21 vs 12 per 1000 examinations), interval cancer rate (0 vs five per 1000 examinations), and PPV3 (61% [14 of 23 examinations] vs 41% [nine of 22 examinations]) were comparable (all P < .05). The BI-RADS category 3 short-term follow-up rate of abbreviated MRI was less than half that of full-protocol MRI (5% [36 of 726 examinations] vs 12% [84 of 726 examinations], respectively; P < .001). Ninety-three percent (14 of 15) of cancers detected at abbreviated MRI were node-negative T1-invasive cancers (n = 6) or ductal carcinoma in situ (n = 8). Conclusion Abbreviated breast MRI showed comparable sensitivity and superior specificity to full-protocol MRI in breast cancer detection in women with a personal history of breast cancer. © RSNA, 2022 Online supplemental material is available for this article.

Microcalcifications and Peritumoral Edema Predict Survival Outcome in Luminal Breast Cancer Treated with Neoadjuvant Chemotherapy.

Background Little is known regarding findings at imaging associated with survival in patients with luminal breast cancer treated with neoadjuvant chemotherapy (NAC). Purpose To determine the relationship between imaging (MRI, US, and mammography) and clinical-pathologic variables in predicting distant metastasis-free survival (DMFS) and overall survival (OS) in patients with luminal breast cancer treated with NAC. Materials and Methods In this retrospective study, consecutive women with luminal breast cancer who underwent NAC followed by surgery were identified from the breast cancer registries of two hospitals. Women from one hospital between January 2003 and July 2015 were classified into the development cohort, and women from the other hospital between January 2007 and July 2015 were classified into the validation cohort. MRI scans, US scans, and mammograms before and after NAC (hereafter, referred to as pre- and post-NAC, respectively) and clinical-pathologic data were reviewed. Peritumoral edema was defined as the water-like high signal intensity surrounding the tumor on T2-weighted MRI scans. The prediction model was developed in the development cohort by using Cox regression and then tested in the validation cohort. Results The development cohort consisted of 318 women (68 distant metastases, 54 deaths) and the validation cohort consisted of 165 women (37 distant metastases, 14 deaths) (median age, 46 years in both cohorts). Post-NAC MRI peritumoral edema, age younger than 40 years, clinical N2 or N3, and lymphovascular invasion were associated with worse DMFS (all, P < .05). Pre-NAC mammographic microcalcifications, post-NAC MRI peritumoral edema, age older than 60 years, and clinical T3 or T4 were associated with worse OS (all, P < .05). The prediction model showed good discrimination ability (C index, 0.67-0.75 for DMFS and 0.70-0.77 for OS) and stratified prognosis into low-risk and high-risk groups (10-year DMFS rates, 79% vs 21%, respectively; and 10-year OS rates, 95%-96% vs 63%-67%, respectively) in the validation cohort. Conclusion MRI features and clinical-pathologic variables were identified that were associated with prolonged survival of patients with luminal breast cancer treated with neoadjuvant chemotherapy. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Kataoka in this issue.

Added value of ultrafast sequence in abbreviated breast MRI surveillance in women with a personal history of breast cancer: A multireader study.

PURPOSE: To evaluate the added value of ultrafast MRI in abbreviated breast MRI (AB-MRI) surveillance in women with a personal history of breast cancer (PHBC). METHOD: Between September 2017 and November 2019, consecutive postoperative surveillance AB-MRIs with ultrafast MRIs (20 images with a 4.0-second temporal resolution using 4D time-resolved angiography with keyhole technique) were retrospectively collected. Four blinded radiologists independently classified the Breast Imaging Reporting and Data System (BI-RADS) category for AB-MRI alone versus the combined protocol (AB-MRI + ultrafast MRI). Readers were recommended to change BI-RADS category according to the time to enhancement cut-off of 12 s in ultrafast MRI. McNemar test and generalized estimation equation model were used to compare the diagnostic performances. RESULTS: A total of 867 MRI examinations in 867 women (mean age ± standard deviation, 51 years ± 8) were evaluated. The sensitivity of both protocols among all readers was the same, at 90% (9/10). Addition of ultrafast MRI improved the specificity (a mean of 95.3% vs. 88.6 %, p < 0.001 for all readers) and positive predictive value 1 (PPV1) (a mean of 21% vs. 10%, p < 0.001 for all readers) compared to AB-MRI alone. Downgrading BI-RADS category 3 to 2 in four readers in a mean of 6.7% (57 of 857) of negative or benign findings was the main reason for the improved specificity and PPV1. CONCLUSION: Addition of ultrafast MRI to AB-MRI improved the specificity and PPV1 by reducing unnecessary short-term follow-ups without compromising sensitivity in postoperative surveillance.