Artificial intelligence computer-aided detection enhances synthesized mammograms: comparison with original digital mammograms alone and in combination with tomosynthesis images in an experimental setting.

BACKGROUND: It remains unclear whether original full-field digital mammograms (DMs) can be replaced with synthesized mammograms in both screening and diagnostic settings. To compare reader performance of artificial intelligence computer-aided detection synthesized mammograms (AI CAD SMs) with that of DM alone or in combination with digital breast tomosynthesis (DBT) images in an experimental setting. METHODS: We compared the performance of multireader (n = 4) and reading multicase (n = 388), in 84 cancers, 83 biopsy-proven benign lesions, and 221 normal or benign cases with negative results after 1-year follow-up. Each reading was independently interpreted with four reading modes: DM, AI CAD SM, DM + DBT, and AI CAD SM + DBT. The accuracy of probability of malignancy (POM) and five-category ratings were evaluated using areas under the receiver operating characteristic curve (AUC) in the random-reader analysis. RESULTS: The mean AUC values based on POM for DM, AI CAD SM, DM + DBT, and AI CAD SM + DBT were 0.871, 0.902, 0.895, and 0.909, respectively. The mean AUC of AI CAD SM was significantly higher (P = 0.002) than that of DM. For calcification lesions, the sensitivity of SM and DM did not differ significantly (P = 0.204). The mean AUC for AI CAD SM + DBT was higher than that of DM + DBT (P = 0.082). ROC curves based on the five-category ratings showed similar proximity of the overall performance levels. CONCLUSIONS: AI CAD SM alone was superior to DM alone. Also, AI CAD SM + DBT was superior to DM + DBT but not statistically significant.

Comparisons between artificial intelligence computer-aided detection synthesized mammograms and digital mammograms when used alone and in combination with tomosynthesis images in a virtual screening setting.

PURPOSE: To compare the reader performance of artificial intelligence computer-aided detection synthesized mammograms (AI CAD SM) with that of digital mammograms (DM) when used alone or in combination with digital breast tomosynthesis (DBT) images. MATERIALS AND METHODS: This retrospective multireader (n = 4) study compared the reader performances in 388 cases (84 cancer, 83 benign, and 221 normal or benign cases). The overall accuracy of the breast-based assessment was determined by four radiologists using two sequential reading modes: DM followed by DM + DBT; and AI CAD SM followed by AI CAD SM + DBT. Each breast was rated by each reader using five-category ratings, where 3 or higher was considered positive. The area under the receiver-operating characteristic curve (AUC) and reading time were evaluated. RESULTS: The mean AUC values for DM, AI CAD SM, DM + DBT, and AI CAD SM + DBT were 0.863, 0.895, 0.886, and 0.902, respectively. The mean AUC of AI CAD SM was significantly higher (P < 0.0001) than that of DM. The mean AUC of AI CAD SM + DBT was higher than that of DM + DBT (P = 0.094). A significant reduction in the reading time was observed after using AI CAD SM + DBT when compared with that after using DM + DBT (P < 0.001). CONCLUSION: AI CAD SM + DBT might prove more effective than DM + DBT in a screening setting because of its lower radiation dose, noninferiority, and shorter reading time compared to DM + DBT.

Use of Gadoxetic Acid-enhanced MRI to Predict the Development of Postoperative Pancreatic Fistulas by Estimating the Degree of Pancreatic Fibrosis.

BACKGROUND: Post-operative pancreatic fistula (POPF) can be life-threatening, and gadoxetic acid-enhanced MRI is routinely performed in patients undergoing pancreatic surgery. However, previous reports have not investigated if gadoxetic acid-enhanced MRI can be used to predict POPF risk. OBJECTIVE: This study aims to explore if gadoxetic acid-enhanced MRI can predict pancreatic fibrosis and the need for POPF treatment before surgery. METHODS: We retrospectively analyzed gadoxetic acid-enhanced MR images from 142 patients who underwent pancreatic surgery between January 1, 2011, and April 30, 2018. Pre-dynamic signal intensity (SI) and values for the portal, transitional, and hepatobiliary phase standardized based on pre-dynamic study values were analyzed. The diameter of the main pancreatic duct (DMPD) was measured, and the degree of pancreatic fibrosis was classified as F0 - F3. We defined POPF higher than grade B as significant. RESULTS: Odds ratios for combinations that led to any degree of fibrosis higher than grade B were defined as significant risk factors. The highest odds ratio was obtained for F0 vs. F1 - F3 (p = 0.038). DMPD (p < 0.001), pre-SI (p = 0.008), portal-SI/pre-SI (p < 0.001), transitional-SI/pre-SI (p < 0.001), and hepatobiliary-SI/pre-SI (p = 0.012) were significantly correlated with the presence of fibrosis. Moreover, the presence of fibrosis was best detected by DMPD (AUC = 0.777). Individual specificity values of transitional-SI/pre-SI and DMPD were 95.5% and 86.6%, respectively, and their combined specificity was 97.7%. CONCLUSION: The absence of pancreatic fibrosis is a risk factor for developing POPF higher than grade B. DMPD was the most useful diagnostic indicator for the presence of fibrosis among our analysis, and its specificity increased when combined with transitional-SI/pre-SI.

Evaluation of Breast Edema Findings at T2-weighted Breast MRI Is Useful for Diagnosing Occult Inflammatory Breast Cancer and Can Predict Prognosis after Neoadjuvant Chemotherapy.

Background Prediction of occult inflammatory breast cancer (IBC) and breast cancer prognosis based on breast edema findings on T2-weighted MRI scans, even for patients without clinical signs of IBC, would be useful in both pretreatment planning and prognosis and may elucidate the underlying biologic mechanisms. Purpose To evaluate whether classification of breast edema on T2-weighted MRI scans is useful for predicting the prognosis of patients with breast cancer treated with neoadjuvant chemotherapy (NAC). Materials and Methods A retrospective evaluation was performed of women with breast cancer who underwent breast MRI and were treated with NAC between January 2011 and December 2018. Breast edema on T2-weighted images was scored on a scale of 1 to 4, as follows: (a) breast edema score (BES) 1, no edema; (b) BES 2, peritumoral edema; (c) BES 3, prepectoral edema; and (d) BES 4, subcutaneous edema (suspicious for occult IBC). Clinically evident IBC was classified as BES 5 (without MRI). The log-rank test was performed, and hazard ratios were calculated using the Cox hazard model to evaluate associations between BES and progression-free survival (PFS) and overall survival (OS). PFS rate at 100 months after initiation of therapy was also evaluated. Results Of 408 patients (median age, 53 years; range, 28-80 years), 65 (16%) had a recurrence and 27 (7%) died. The log-rank test revealed differences in PFS for BES 4 versus 1, BES 5 versus 1, BES 5 versus 2, and BES 5 versus 3 (adjusted P < .05 for all). PFS rates for BES 1-5 were 0.92, 0.85, 0.80, 0.62, and 0.58, respectively, and the corresponding OS rates at 100 months were 0.98, 0.91, 0.92, 0.77, 0.86, respectively. Conclusion Classification of breast edema findings on T2-weighted MRI scans using a breast edema score was related to the prognosis of patients after neoadjuvant chemotherapy. © RSNA, 2021 Online supplemental material is available for this article.