Introduction: Magnetic resonance imaging (MRI) has played an increasingly major role in the evaluation of patients with prostate cancer, although prostate MRI presents several technical challenges. Newer techniques, such as deep learning (DL), have been applied to medical imaging, leading to improvements in image quality. Our goal is to evaluate the performance of a new deep learning-based reconstruction method, “DLR” in improving image quality and mitigating artifacts, which is now commercially available as AIR^TM Recon DL (GE Healthcare, Waukesha, WI). We hypothesize that applying DLR to the T2WI images of the prostate provides improved image quality and reduced artifacts. Methods: This study included 31 patients with a history of prostate cancer that had a multiparametric MRI of the prostate with an endorectal coil (ERC) at 1.5 T or 3.0 T. Four series of T2-weighted images were generated in total: one set with the ERC signal turned on (ERC) and another set with the ERC signal turned off (Non-ERC). Each of these sets then reconstructed using two different reconstruction methods: conventional reconstruction (Conv) and DL Recon (DLR): ERC_DLR, ERC_Conv, Non-ERC_DLR, and Non-ERC_Conv. Three radiologists independently reviewed and scored the four sets of images for (i) image quality, (ii) artifacts, and (iii) visualization of anatomical landmarks and tumor. Results: The Non-ERC_DLR scored as the best series for (i) overall image quality (p < 0.001), (ii) reduced artifacts (p < 0.001), and (iii) visualization of anatomical landmarks and tumor. Conclusion: Prostate imaging without the use of an endorectal coil could benefit from deep learning reconstruction as demonstrated with T2-weighted imaging MRI evaluations of the prostate.

Hepatocellular carcinoma (HCC) is the most common primary liver neoplasm, and its incidence has doubled over the past two decades owing to increasing risk factors. Despite surveillance, most HCC cases are diagnosed at advanced stages and can only be treated using transarterial chemo-embolization (TACE) or systemic therapy. TACE failure may occur with incidence reaching up to 60% of cases, leaving patients with a financial and emotional burden. Radiomics has emerged as a new tool capable of predicting tumor response to TACE from pre-procedural computed tomography (CT) studies. This data report defines the HCC-TACE data collection of confirmed HCC patients who underwent TACE and have pre- and post-procedure CT imaging studies and available treatment outcomes (time-to-progression and overall survival). Clinically curated segmentation of pre-procedural CT studies was done for the purpose of algorithm training for prediction and automatic liver tumor segmentation.

Magnetic resonance imaging (MRI) of the liver is slowly transitioning from a problem solving imaging modality to a first line imaging modality for many diseases of the liver. The well established advantages of MRI over other cross sectional imaging modalities may be the basis for this transition. Technological advancements in MRI that focus on producing high quality images and fast imaging, increasing diagnostic accuracy and developing newer function-specific contrast agents are essential in ensuring that MRI succeeds as a first line imaging modality. Newer imaging techniques, such as parallel imaging, are widely utilized to shorten scanning time. Diffusion weighted echo planar imaging, an adaptation from neuroimaging, is fast becoming a routine part of the MRI liver protocol to improve lesion detection and characterization of focal liver lesions. Contrast enhanced dynamic T1 weighted imaging is crucial in complete evaluation of diseases and the merit of this dynamic imaging relies heavily on the appropriate timing of the contrast injection. Newer techniques that include fluoro-triggered contrast enhanced MRI, an adaptation from 3D MRA imaging, are utilized to achieve good bolus timing that will allow for optimum scanning. For accurate interpretation of liver diseases, good understanding of the newer imaging techniques and familiarity with typical imaging features of liver diseases are essential. In this review, MR sequences for a time efficient liver MRI protocol utilizing newer imaging techniques are discussed and an overview of imaging features of selected common focal and diffuse liver diseases are presented.

Diffusion-weighted imaging (DWI) has become a useful tool in the detection, characterization, and evaluation of response to treatment of many cancers, including malignant liver lesions. DWI offers higher image contrast between lesions and normal liver tissue than other sequences. DWI images acquired at two or more b-values can be used to derive an apparent diffusion coefficient (ADC). DWI in the body has several technical challenges. This include ghosting artifacts, mis-registration and susceptibility artifacts. New DWI sequences have been developed to overcome some of these challenges. Our goal is to evaluate 3 new DWI sequences for liver imaging. To qualitatively and quantitatively compare 3 DWI sequences for liver imaging: free-breathing (FB), simultaneous multislice (SMS), and prospective acquisition correction (PACE). Magnetic resonance imaging (MRI) was performed in 20 patients in this prospective study. The MR study included 3 separate DWI sequences: FB-DWI, SMS-DWI, and PACE-DWI. The image quality, mean ADC, standard deviations (SD) of ADC, and ADC histogram were compared. Wilcoxon signed-rank tests were used to compare qualitative image quality. A linear mixed model was used to compare the mean ADC and the SDs of the ADC values. All tests were 2-sided and P values of < 0.05 were considered statistically significant. There were 56 lesions (50 malignant) evaluated in this study. The mean qualitative image quality score of PACE-DWI was 4.48. This was significantly better than that of SMS-DWI (4.22) and FB-DWI (3.15) (P < 0.05). Quantitatively, the mean ADC values from the 3 different sequences did not significantly differ for each liver lesion. FB-DWI had a markedly higher variation in the SD of the ADC values than did SMS-DWI and PACE-DWI. We found statistically significant differences in the SDs of the ADC values for FB-DWI vs PACE-DWI (P < 0.0001) and for FB-DWI vs SMS-DWI (P = 0.03). The SD of the ADC values was not statistically significant for PACE-DWI and SMS-DWI (P = 0.18). The quality of the PACE-DWI ADC histograms were considered better than the SMS-DWI and FB-DWI. Compared to FB-DWI, both PACE-DWI and SMS-DWI provide better image quality and decreased quantitative variability in the measurement of ADC values of liver lesions.

Purpose Our aim was to compare the interobserver and intraobserver variability for the measurement of the size of liver metastases in patients with carcinoid tumors with various magnetic resonance (MR) series. Materials and Methods In this retrospective institutional review board–approved study, 30 patients with liver metastases from a carcinoid primary had a complete MR examination of the abdomen at 1.5 T with gadolinium-ethoxybenzyl-diethylenetriamine pentaacetic acid (Gd-EOB-DTPA). The complete MR examination included T1 (in-phase [IP]/out-of-phase [OOP], T2, diffusion-weighted imaging, pre–Gd-EOB-DTPA and post–Gd-EOB-DTPA 3D gradient echo (4 phases plus 20-minute hepatobiliary phase [HBP] Gd]). Four readers reviewed each series independently. The measurement for each lesion was compared to HBP-Gd images. The sensitivity for detection of each lesion was compared to HBP-Gd. Variance component analysis was used to estimate variance due to patient, lesion within patient, and reader by sequence. Linear mixed model was used to compare lesion size between sequences. Results The HBP-Gd had the smallest interreader variability. There was no significant difference between series with respect to interreader variability. Lesion sizes measured in diffusion-weighted imaging was significantly higher. T2-weighted imaging was the closest to HBP-Gd. Lesion sizes measured with the other sequences were significantly smaller. There was significant difference in sensitivity of lesion detection of some series when compared to HBP-Gd. Conclusion The HBP-Gd series had the smallest interreader variability and is the recommended series to measure lesion size for evaluation of response to treatment.