Knowledge of the MRI features of borderline epithelial ovarian tumor can aid in preoperative diagnosis; however, several benign and malignant tumors can mimic borderline tumors and pose diagnostic ... Borderline epithelial ovarian tumors are a distinct pathologic entity characterized by increased epithelial proliferation and nuclear atypia, but without frank stromal invasion. Borderline tumor (B... Created with BioRender.com

Objective: This study aimed to evaluate the effects of deep learning (DL) reconstruction and a postprocessing sharpening filter on the image quality of single-shot fast spin-echo (SSFSE) T2-weighted imaging (T2WI) of the uterus. Materials and Methods: Fifty consecutive patients who underwent pelvic magnetic resonance imaging were included. Parasagittal T2WI with a slice thickness of 4 mm was obtained with the periodically rotated overlapping parallel lines with enhanced reconstruction (PROPELLER) and SSFSE sequences (mean scan time, 204 and 22 seconds, respectively). The following 3 types of SSFSE images were reconstructed, and the signal-to-noise ratio (SNR) and tissue contrast were assessed: conventional reconstruction (SSFSE-C), DL reconstruction (SSFSE-DL), and DL with a sharpening filter (SSFSE-DLF). Three radiologists independently assessed image quality, and area under the visual grading characteristics curve (AUC_VGC) analysis was performed to compare the SSFSE and PROPELLER images. Results: Compared with that of the PROPELLER images, the SNR of the SSFSE-C, SSFSE-DL, and SSFSE-DLF images was significantly lower (P < 0.05), significantly higher (P < 0.05), and equivalent, respectively. The SSFSE-DL images exhibited significantly lower contrast between the junctional zone and myometrium than those obtained with the other sequences (P < 0.05). In qualitative comparisons with the PROPELLER images, all 3 SSFSE sequences, SSFSE-DL, and SSFSE-DLF demonstrated significantly higher scores for artifacts, noise, and sharpness, respectively (P < 0.01). The overall image quality of SSFSE-C (mean AUC_VGC, 0.03; P < 0.01) and SSFSE-DL (mean AUC_VGC, 0.23; P < 0.01) was rated as significantly inferior, whereas that of SSFSE-DLF (mean AUC_VGC, 0.69) was equivalent or significantly higher (P < 0.01). Conclusion: Using a combination of DL and a sharpening filter markedly increases the image quality of SSFSE of the uterus to the level of the PROPELLER sequence.

Background: Strong correlation has been reported between tissue water diffusivity and tissue elasticity in the liver. The purpose of this study is to explore the capability of diffusion–based virtual MR elastography (VMRE) in the characterization of liver tumors by extending beyond liver fibrosis assessments. Methods: Fifty-four patients (56 liver tumors: hepatocellular carcinoma (HCC), 31; metastases, 25) who underwent MRE, diffusion-weighted imaging (DWI) (b: 0, 800 s/mm²), and VMRE (b: 200, 1500 s/mm²) were enrolled. The MRE shear modulus (µ_MRE), apparent diffusion coefficient (ADC), and shifted ADC (sADC) were obtained. Virtual stiffness (µ_diff) was estimated from the relationship between µ_MRE and sADC. A linear discriminant analysis combining VMRE and MRE to classify HCC and metastases was performed in a training cohort (thirty-two patients) to estimate a classifier (C), and evaluate its accuracy in a testing cohort (twenty-two patients). Pearson’s correlations between µ_MRE, sADC, and ADC were evaluated. In addition to the discriminant analysis, a receiver operating characteristic (ROC) curve was used to assess the discrimination capability between HCC and metastases. Results: The correlations between µ_MRE and sADC were significant for liver, HCC, and metastases (r = 0.91, 0.68, 0.71; all p < 0.05). Those between µ_MRE and ADC were weaker and significant only for metastases (r = 0.17, 0.20, 0.55). µ_diff values were not significantly different between HCC and metastases (p = 0.56). Areas under the curves (AUC) to differentiate HCC from metastases were as follows: VMRE, 0.46; MRE alone, 0.89; MRE + VMRE, 0.96. The classifier C also provided better performance than MRE alone, in terms of sensitivity (100 vs. 93.5%, respectively) and specificity (92 vs. 76%, respectively, p = 0.046). Conclusions: The correlation between sADC and µ_MRE was strong both in the liver and in tumors. However, VMRE alone could not classify HCC and metastases. The combination of MRE and VMRE, however, allowed discriminant performance between HCC and metastases.