加藤 扶美

PURPOSE: To evaluate the effect of model-based deep-learning reconstruction (DLR) compared with that of compressed sensing-sensitivity encoding (CS) on cine cardiac magnetic resonance (CMR). METHODS: Cine CMR images of 10 healthy volunteers were obtained with reduction factors of 2, 4, 6, and 8 and reconstructed using CS and DLR. The visual image quality scores assessed sharpness, image noise, and artifacts. Left-ventricular (LV) end-diastolic volume (EDV), end-systolic volume (ESV), stroke volume (SV), and ejection fraction (EF) were manually measured. LV global circumferential strain (GCS) was automatically measured using the software. The precision of EDV, ESV, SV, EF, and GCS measurements was compared between CS and DLR using Bland-Altman analysis with full-sampling data as the gold standard. RESULTS: Compared with CS, DLR significantly improved image quality with reduction factors of 6 and 8. The precision of EDV and ESV with a reduction factor of 8, and GCS with reduction factors of 6 and 8 measurements improved with DLR compared with CS, whereas those of SV and EF measurements were not different between DLR and CS. CONCLUSION: The effect of DLR on cine CMR's image quality and precision in evaluating quantitative volume and strain was equal or superior to that of CS. DLR may replace CS for cine CMR.

BACKGROUND: Conventional ultrasonography (cUS) and contrast-enhanced ultrasonography (CEUS) are used to evaluate breast cancer tumors and axillary lymph nodes (ALN), by which the treatment strategy for breast cancer is determined. A breast tumor size discrepancy on CEUS compared with cUS is often observed, for which the reasons are unclear. We hypothesized that this discrepancy reflects the metastatic potential, and this study investigated the association between size discrepancies on cUS and CEUS in relation to ALN metastasis in breast cancer. METHODS: This retrospective study enrolled 259 patients who underwent surgery for breast cancer after preoperative cUS and CEUS examinations. Patients were grouped into a DISCR (i.e., tumor size discrepancy ≥ 4.0 mm between CEUS and cUS measurements) and non-DISCR group. The primary outcome was ALN metastasis, defined by pathological evaluation. Secondary outcomes were the 5-year recurrence-free survival rates. RESULTS: There were 94 patients in the DISCR and 165 in the non-DISCR groups. No tumor size differences measured by cUS were observed between two groups (p = 0.82), whereas the DISCR group had a significantly higher rate of ALN metastasis (p < 0.01). Multivariate analyses showed a discrepancy of ≥ 4.0 mm was a risk for ALN metastasis (odds ratio: 5.838, 95% confidence interval [CI]: 2.408-14.155). The 5-year recurrence-free survival rate was lower in the DISCR (0.750, 95% CI: 0.632-0.868) than in the non-DISCR (0.924, 95% CI; 0.870-0.978) group. CONCLUSION: An increase in contrast-enhanced ultrasonography tumor size is helpful for assessing axillary lymph node metastasis and prognosis.

Contrast-enhanced ultrasound (CEUS) plays a pivotal role in the diagnosis of primary breast cancer and in axillary lymph node (ALN) metastasis. However, the imaging features that are clinically crucial for lymph node metastasis have not been fully elucidated. Hence, we developed a bimodal model to predict ALN metastasis in patients with early breast cancer by integrating CEUS images with the annotated imaging features. The model adopted a light-gradient boosting machine to produce feature importance, enabling the extraction of clinically crucial imaging features. In this retrospective study, the diagnostic performance of the model was investigated using 788 CEUS images of ALNs obtained from 788 patients who underwent breast surgery between 2013 and 2021, with the ground truth defined by the pathological diagnosis. The results indicated that the test cohort had an area under the receiver operating characteristic curve (AUC) value of 0.93 (95% confidence interval: 0.88, 0.98). The model had an accuracy of 0.93, which was higher than the radiologist's diagnosis (accuracy of 0.85). The most important imaging features were heterogeneous enhancement, diffuse cortical thickening, and eccentric cortical thickening. Our model has an excellent diagnostic performance, and the extracted imaging features could be crucial for confirming ALN metastasis in clinical settings.