Feasibility of late gadolinium enhancement (LGE) in ischemic cardiomyopathy using 2D-multisegment LGE combined with artificial intelligence reconstruction deep learning noise reduction algorithm.

BACKGROUND: Despite the low spatial resolution of 2D-multisegment late gadolinium enhancement (2D-MSLGE) sequences, it may be useful in uncooperative patients instead of standard 2D single segmented inversion recovery gradient echo late gadolinium enhancement sequences (2D-SSLGE). The aim of the study is to assess the feasibility and comparison of 2D-MSLGE reconstructed with artificial intelligence reconstruction deep learning noise reduction (NR) algorithm compared to standard 2D-SSLGE in consecutive patients with ischemic cardiomyopathy (ICM). METHODS: Fifty-seven patients with known ICM referred for a clinically indicated CMR were enrolled in this study. 2D-MSLGE were reconstructed using a growing level of NR (0%,25%,50%,75%and 100%). Subjective image quality, signal to noise ratio (SNR) and contrast to noise ratio (CNR) were evaluated in each dataset and compared to standard 2D-SSLGE. Moreover, diagnostic accuracy, LGE mass and scan time were compared between 2D-MSLGE with NR and 2D-SSLGE. RESULTS: The application of NR reconstruction ≥50% to 2D-MSLGE provided better subjective image quality, CNR and SNR compared to 2D-SSLGE (p < 0.01). The best compromise in terms of subjective and objective image quality was observed for values of 2D-MSLGE 75%, while no differences were found in terms of LGE quantification between 2D-MSLGE versus 2D-SSLGE, regardless the NR applied. The sensitivity, specificity, negative predictive value, positive predictive value and accuracy of 2D-MSLGE NR 75% were 87.77%,96.27%,96.13%,88.16% and 94.22%, respectively. Time of acquisition of 2D-MSLGE was significantly shorter compared to 2D-SSLGE (p < 0.01). CONCLUSION: When compared to standard 2D-SSLGE, the application of NR reconstruction to 2D-MSLGE provides superior image quality with similar diagnostic accuracy.

Diagnostic Performance of Digital Breast Tomosynthesis, Unenhanced MRI, and Their Combination in the Preoperative Assessment of Breast Cancer: A Multi-reader Study.

RATIONALE AND OBJECTIVES: To compare the diagnostic performance of digital breast tomosynthesis (DBT) and unenhanced magnetic resonance imaging (UMRI) in the preoperative assessment of breast cancer. MATERIALS AND METHODS: We retrospectively included 59 patients with 74 pathology-proven cancers who underwent DBT and preoperative 1.5 T magnetic resonance imaging between January 2016 and February 2017. Four residents with 2-3 years of experience, blinded to pathology, independently reviewed DBT and UMRI (diffusion-weighted and unenhanced T1-weighted sequences), using the breast imaging reporting and data system (BI-RADS) and a 0-5 Likert score, respectively. We calculated per-lesion sensitivity and positive predictive value of DBT, UMRI, and combined DBT+UMRI, as well as the agreement between DBT and UMRI vs. pathology in assessing cancer size (Bland-Altman analysis). Logistic regression was performed to assess clinical features predictive of missing cancer. RESULTS: Of 74 lesions, 84% were invasive ductal carcinoma, 27% of which with an in situ component; 31% of cancers were ≤10 mm large. Sensitivity of UMRI (74-85%) was equal or higher than that of DBT (68-82%), with similar positive predictive value (93-97% vs. 98-100%, respectively). DBT+UMRI increased the sensitivity up to 88%. UMRI showed closer limits of agreement with pathological size than DBT. Missing cancer was independently predicted by size ≤10 mm on DBT, UMRI, and DBT+UMRI (odds ratio 18.7, 5.1, and 13.3, respectively), and by increased breast density on DBT alone (odds ratio 3.50). CONCLUSION: UMRI was equal or better than DBT in the preoperative assessment of breast cancer. Combined imaging achieved up to 88% per-lesion sensitivity, suggesting potential use in clinical practice.