Spontaneous rupture of a uterine leiomyoma accompanied by a hematoma appearing as a cystic lesion on imaging: A case report.

The rupture of a uterine leiomyoma is a rare complication. We report a case of ruptured leiomyoma that formed a hematoma that was initially suggestive of an ovarian origin. Magnetic resonance imaging revealed intact ovaries and a cystic lesion adjacent to leiomyomas. During surgery, the cystic lesion was found to be a hematoma caused by a rupture of the leiomyoma.

Super-resolution Deep Learning Reconstruction Cervical Spine 1.5T MRI: Improved Interobserver Agreement in Evaluations of Neuroforaminal Stenosis Compared to Conventional Deep Learning Reconstruction.

The aim of this study was to investigate whether super-resolution deep learning reconstruction (SR-DLR) is superior to conventional deep learning reconstruction (DLR) with respect to interobserver agreement in the evaluation of neuroforaminal stenosis using 1.5T cervical spine MRI. This retrospective study included 39 patients who underwent 1.5T cervical spine MRI. T2-weighted sagittal images were reconstructed with SR-DLR and DLR. Three blinded radiologists independently evaluated the images in terms of the degree of neuroforaminal stenosis, depictions of the vertebrae, spinal cord and neural foramina, sharpness, noise, artefacts and diagnostic acceptability. In quantitative image analyses, a fourth radiologist evaluated the signal-to-noise ratio (SNR) by placing a circular or ovoid region of interest on the spinal cord, and the edge slope based on a linear region of interest placed across the surface of the spinal cord. Interobserver agreement in the evaluations of neuroforaminal stenosis using SR-DLR and DLR was 0.422-0.571 and 0.410-0.542, respectively. The kappa values between reader 1 vs. reader 2 and reader 2 vs. reader 3 significantly differed. Two of the three readers rated depictions of the spinal cord, sharpness, and diagnostic acceptability as significantly better with SR-DLR than with DLR. Both SNR and edge slope (/mm) were also significantly better with SR-DLR (12.9 and 6031, respectively) than with DLR (11.5 and 3741, respectively) (p < 0.001 for both). In conclusion, compared to DLR, SR-DLR improved interobserver agreement in the evaluations of neuroforaminal stenosis using 1.5T cervical spine MRI.

Evaluation of the relations between reproduction-related pituitary and ovarian hormones and abdominal fat area-related variables determined with computed tomography in overweight or obese women who have undergone bariatric surgery: a cross-sectional study.

Background: An understanding of the associations between midregion fat depots and systemic hormone levels will be crucial for developing health-promotion messages aimed at overweight or obese women. However, related research in this area is rare. The present study was performed to identify and quantify fat-related reproduction pituitary and ovarian hormones in overweight or obese women. Methods: A total of 250 eligible overweight or obese women scheduled to undergo laparoscopic sleeve gastrectomy (LSG) from a single center were retrospectively included in this study. Computed tomography (CT) images at the level of the umbilicus were selected, and abdominal fat areas were measured and calculated. The reproduction-related pituitary and ovarian hormones were also measured. The correlations among the parameters were examined using Spearman correlation test. Multiple linear regression analysis was performed after log and ß-transformation of the hormone levels and fat area-related variables. Results: Positive correlations were detected for prolactin (PRL) with total fat area (TFA) [ß=0.045; P=0.029; 95% confidence interval (CI): 0.004-0.085] and subcutaneous fat area (SFA) (ß=0.066; P=0.023; 95% CI: 0.009-0.123), whereas estradiol showed a negative correlation with visceral fat area (VFA) (ß=-0.056, P=0.005; 95% CI: -0.096 to -0.017) and relative VFA (rVFA) (ß=-0.068; P=0.001; 95% CI: -0.109 to -0.027) and a positive correlation with SFA (ß=0.036; P=0.042; 95% CI: 0.001-0.071). Progesterone (PROG) was negatively correlated with both VFA (ß=-0.037; P=0.002; 95% CI: -0.061 to -0.013) and rVFA (ß=-0.039; P=0.002; 95% CI: -0.063 to -0.014). The final results revealed that TFA was increased by 3.1% and SFA was increased by 4.7% with a doubling of PRL concentration; VFA was reduced by 2.5% and rVFA was reduced by 2.6% with a doubling of PROG concentration; and VFA was reduced by 3.8%, rVFA was reduced by 4.6%, and SFA was increased by 2.5% with a doubling of estradiol concentration. Conclusions: There exist certain associations between some reproduction-related pituitary and ovarian hormones and fat areas. Our findings provide new insights into the associations between midregion fat depots and systemic hormone levels in overweight or obese women.

Differentiation between pleomorphic adenoma and schwannoma in the parapharyngeal space: histogram analysis of apparent diffusion coefficient.

OBJECTIVES: To elucidate the differences between pleomorphic adenomas and schwannomas occurring in the parapharyngeal space by histogram analyses of apparent diffusion coefficient (ADC) values measured with diffusion-weighted MRI. METHODS: This retrospective study included 29 patients with pleomorphic adenoma and 22 patients with schwannoma arising in the parapharyngeal space or extending into the parapharyngeal space from the parotid region. Using pre-operative MR images, ADC values of tumor lesions showing the maximum diameter were measured. The regions of interest for ADC measurement were placed by contouring the tumor margin, and the histogram metrics of ADC values were compared between pleomorphic adenomas and schwannomas regarding the mean, skewness, and kurtosis by Wilcoxon's rank sum test. Subsequent to the primary analysis which included all lesions, we performed two subgroup analyses regarding b-values and magnetic field strength used for MRI. RESULTS: The mean ADC values did not show significant differences between pleomorphic adenomas and schwannomas for the primary and subgroup analyses. Schwannomas showed higher skewness (p = 0.0001) and lower kurtosis (p = 0.003) of ADC histograms compared with pleomorphic adenomas in the primary analysis. Skewness was significantly higher in schwannomas in all the subgroup analyses. Kurtosis was consistently lower in schwannomas but did not reach statistical significance in one subgroup analysis. CONCLUSIONS: Skewness and kurtosis showed significant differences between pleomorphic adenomas and schwannomas occupying the parapharyngeal space, but the mean ADC values did not. Our results suggest that the skewness and kurtosis of ADC histograms may be useful in differentiating these two parapharyngeal tumors.

Comparison of 1.5 T and 3 T magnetic resonance angiography for detecting cerebral aneurysms using deep learning-based computer-assisted detection software.

PURPOSE: To compare the diagnostic performance of 1.5 T versus 3 T magnetic resonance angiography (MRA) for detecting cerebral aneurysms with clinically available deep learning-based computer-assisted detection software (EIRL aneurysm® [EIRL_an]), which has been approved by the Japanese Pharmaceuticals and Medical Devices Agency. We also sought to analyze the causes of potential false positives. METHODS: In this single-center, retrospective study, we evaluated the MRA scans of 90 patients who underwent head MRA (1.5 T and 3 T in 45 patients each) in clinical practice. Overall, 51 patients had 70 aneurysms. We used MRI from a vendor not included in the dataset used to create the EIRL_an algorithm. Two radiologists determined the ground truth, the accuracy of the candidates noted by EIRL_an, and the causes of false positives. The sensitivity, number of false positives per case (FPs/case), and the causes of false positives were compared between 1.5 T and 3 T MRA. Pearson's χ2 test, Fisher's exact test, and the Mann‒Whitney U test were used for the statistical analyses as appropriate. RESULTS: The sensitivity was high for 1.5 T and 3 T MRA (0.875‒1), but the number of FPs/case was significantly higher with 3 T MRA (1.511 vs. 2.578, p < 0.001). The most common causes of false positives (descending order) were the origin/bifurcation of vessels/branches, flow-related artifacts, and atherosclerosis and were similar between 1.5 T and 3 T MRA. CONCLUSION: EIRL_an detected significantly more false-positive lesions with 3 T than with 1.5 T MRA in this external validation study. Our data may help physicians with limited experience with MRA to correctly diagnose aneurysms using EIRL_an.

Clinical Impact of Deep Learning Reconstruction in MRI.

Deep learning has been recognized as a paradigm-shifting tool in radiology. Deep learning reconstruction (DLR) has recently emerged as a technology used in the image reconstruction process of MRI, which is an essential procedure in generating MR images. Denoising, which is the first DLR application to be realized in commercial MRI scanners, improves signal-to-noise ratio. When applied to lower magnetic field-strength scanners, the signal-to-noise ratio can be increased without extending the imaging time, and image quality is comparable to that of higher-field-strength scanners. Shorter imaging times decrease patient discomfort and reduce MRI scanner running costs. The incorporation of DLR into accelerated acquisition imaging techniques, such as parallel imaging or compressed sensing, shortens the reconstruction time. DLR is based on supervised learning using convolutional layers and is divided into the following three categories: image domain, k-space learning, and direct mapping types. Various studies have reported other derivatives of DLR, and several have shown the feasibility of DLR in clinical practice. Although DLR efficiently reduces Gaussian noise from MR images, denoising makes image artifacts more prominent, and a solution to this problem is desired. Depending on the training of the convolutional neural network, DLR may change the imaging features of lesions and obscure small lesions. Therefore, radiologists may need to adopt the habit of questioning whether any information has been lost on images that appear clean. ©RSNA, 2023 Quiz questions for this article are available in the supplemental material.

Value of apparent diffusion coefficient on MRI for prediction of histopathological type in anal fistula cancer.

The main histopathological types of anal fistula cancers are mucinous adenocarcinoma and tubular adenocarcinoma. The purpose of this study was to investigate the utility of the apparent diffusion coefficient (ADC) value in magnetic resonance imaging (MRI) to determine the histopathological type of an anal fistula cancer, and to investigate the relationship between ADC values and histopathological type (mucinous type or tubular carcinoma), clinical information, and surgical findings. We retrospectively identified 69 patients diagnosed with anal fistula cancer at our hospital from January 2013 to December 2021. Among them, we selected the patients diagnosed using the same 1.5-T MRI machine, underwent surgery, and a pathological sample was obtained during the operation. Finally, these 25 patients were selected for the analysis since they underwent the imaging scan using the same MRI machine. The ADC value was compared between mucinous and tubular adenocarcinomas, and between tumors at the Tis-T1-T2 and T3-T4 stages. Finally, 25 patients were selected. The mean age of the 25 patients included in the analysis was 60.8 ± 13.3 years and all were males. The median ADC of anal fistula cancers was 1.97 × 10-3 mm2/s for mucinous adenocarcinomas and 1.36 × 10-3 mm2/s for tubular adenocarcinomas; this difference was statistically significant (P < .01). Furthermore, the median ADC was 1.62 × 10-3 mm2/s for tumors in Tis-T1-T2 stages and 2.01 × 10-3 mm2/s for T3-T4 tumors (P = .02). The ADC value in MR images may predict the histopathological type and depth of anal fistula cancers. Also, the different ADC values between Tis-T1-T2 and T3-T4 tumors could help predict the classification of progression.

Pulse Sequences and Reconstruction in Fast MR Imaging of the Liver.

The liver moves with respiratory motion. Respiratory motion causes image artifacts as MRI is a motion-sensitive imaging modality; thus, MRI scan speed improvement has been an important technical development target for liver MRI for years. Recent pulse sequence and image reconstruction technology advancement has realized a fast liver MRI acquisition method. Such new technologies allow us to obtain liver MRI in a shorter time, particularly, within breath-holding time. Other benefits of new the technology and the higher spatial resolution liver MRI within a given scan time are improved slice coverage and smaller pixel size. In this review, MRI pulse sequence and reconstruction technologies to accelerate scan speed for T1- and T2-weighted liver MRI will be discussed. Technologies that reduce scan time while keeping image contrast, SNR and image spatial resolution are needed for fast MRI acquisition. We will discuss the progress of MRI acquisition methods, the enabling technology, established applications, current trends, and the future outlook.

Acceleration of knee magnetic resonance imaging using a combination of compressed sensing and commercially available deep learning reconstruction: a preliminary study.

PURPOSE: To evaluate whether deep learning reconstruction (DLR) accelerates the acquisition of 1.5-T magnetic resonance imaging (MRI) knee data without image deterioration. MATERIALS AND METHODS: Twenty-one healthy volunteers underwent MRI of the right knee on a 1.5-T MRI scanner. Proton-density-weighted images with one or four numbers of signal averages (NSAs) were obtained via compressed sensing, and DLR was applied to the images with 1 NSA to obtain 1NSA-DLR images. The 1NSA-DLR and 4NSA images were compared objectively (by deriving the signal-to-noise ratios of the lateral and the medial menisci and the contrast-to-noise ratios of the lateral and the medial menisci and articular cartilages) and subjectively (in terms of the visibility of the anterior cruciate ligament, the medial collateral ligament, the medial and lateral menisci, and bone) and in terms of image noise, artifacts, and overall diagnostic acceptability. The paired t-test and Wilcoxon signed-rank test were used for statistical analyses. RESULTS: The 1NSA-DLR images were obtained within 100 s. The signal-to-noise ratios (lateral: 3.27 ± 0.30 vs. 1.90 ± 0.13, medial: 2.71 ± 0.24 vs. 1.80 ± 0.15, both p < 0.001) and contrast-to-noise ratios (lateral: 2.61 ± 0.51 vs. 2.18 ± 0.58, medial 2.19 ± 0.32 vs. 1.97 ± 0.36, both p < 0.001) were significantly higher for 1NSA-DLR than 4NSA images. Subjectively, all anatomical structures (except bone) were significantly clearer on the 1NSA-DLR than on the 4NSA images. Also, in the former images, the noise was lower, and the overall diagnostic acceptability was higher. CONCLUSION: Compared with the 4NSA images, the 1NSA-DLR images exhibited less noise, higher overall image quality, and allowed more precise visualization of the menisci and ligaments.

Commercially Available Deep-learning-reconstruction of MR Imaging of the Knee at 1.5T Has Higher Image Quality Than Conventionally-reconstructed Imaging at 3T: A Normal Volunteer Study.

PURPOSE: This study aimed to evaluate whether the image quality of 1.5T magnetic resonance imaging (MRI) of the knee is equal to or higher than that of 3T MRI by applying deep learning reconstruction (DLR). METHODS: Proton density-weighted images of the right knee of 27 healthy volunteers were obtained by 3T and 1.5T MRI scanners using similar imaging parameters (21 for high resolution image and 6 for normal resolution image). Commercially available DLR was applied to the 1.5T images to obtain 1.5T/DLR images. The 3T and 1.5T/DLR images were compared subjectively for visibility of structures, image noise, artifacts, and overall diagnostic acceptability and objectively. One-way ANOVA and Friedman tests were used for the statistical analyses. RESULTS: For the high resolution images, all of the anatomical structures, except for bone, were depicted significantly better on the 1.5T/DLR compared with 3T images. Image noise scored statistically lower and overall diagnostic acceptability scored higher on the 1.5T/DLR images. The contrast between lateral meniscus and articular cartilage of the 1.5T/DLR images was significantly higher (5.89 ± 1.30 vs. 4.34 ± 0.87, P < 0.001), and also the contrast between medial meniscus and articular cartilage of the 1.5T/DLR images was significantly higher (5.12 ± 0.93 vs. 3.87 ± 0.56, P < 0.001). Similar image quality improvement by DLR was observed for the normal resolution images. CONCLUSION: The 1.5T/DLR images can achieve less noise, more precise visualization of the meniscus and ligaments, and higher overall image quality compared with the 3T images acquired using a similar protocol.

The contralateral effects of anticipated stimuli on brain activity measured by ERP and fMRI.

The present study examined the effects of unilateral stimulus presentation on the right hemisphere preponderance of the stimulus-preceding negativity (SPN) in the event-related potential (ERP) experiment, and aimed to elucidate whether unilateral stimulus presentation affected activations in the bilateral anterior insula in the functional magnetic resonance imaging (fMRI) experiment. Separate fMRI and ERP experiments were conducted using visual and auditory stimuli by manipulating the position of stimulus presentation (left side or right side) with the time estimation task. The ERP experiment revealed a significant right hemisphere preponderance during left stimulation and no laterality during the right stimulation. The fMRI experiment revealed that the left anterior insula was activated only in the right stimulation of auditory and visual stimuli whereas the right anterior insula was activated by both left and right stimulations. The visual condition retained a contralateral dominance, but the auditory condition showed a right hemisphere dominance in a localized area. The results of this study indicate that the SPN reflects perceptual anticipation, and also that the anterior insula is involved in its occurrence.

Radiation Protection of the Eye Lens in Fluoroscopy-guided Interventional Procedures.

The medical staff involved in fluoroscopy-guided procedures are at potential risks of radiation-induced cataract. Therefore, proper monitoring of the lens doses is critical, and radiation protection should be provided to the maximum extent that is reasonably achievable. The collar dosimeter is necessary to avoid underestimation of the lens dose, and the third dosimeter behind the protective eyewear would be helpful for those who are likely to exceed the dose limit. The reduction of the patient doses will correspondingly reduce the staff doses. Proper placement of the ceiling-mounted shields and minimization of the face-to-glass gap are the keys to effective shielding. The optimization of procedures and devices that help maintain a distance from the irradiated area and to prevent the looking-up posture will substantially reduce the lens dose.

Deep learning reconstruction for the evaluation of neuroforaminal stenosis using 1.5T cervical spine MRI: comparison with 3T MRI without deep learning reconstruction.

PURPOSE: To compare image quality and interobserver agreement in evaluations of neuroforaminal stenosis between 1.5T cervical spine magnetic resonance imaging (MRI) with deep learning reconstruction (DLR) and 3T MRI without DLR. METHODS: In this prospective study, 21 volunteers (mean age: 42.4 ± 11.9 years; 17 males) underwent cervical spine T2-weighted sagittal 1.5T and 3T MRI on the same day. The 1.5T and 3T MRI data were used to reconstruct images with (1.5T-DLR) and without (3T-nonDLR) DLR, respectively. Regions of interest were marked on the spinal cord to calculate non-uniformity (NU; standard deviation/signal intensity × 100), as an indicator of image noise. Two blinded radiologists evaluated the images in terms of the depiction of structures, artifacts, noise, overall image quality, and neuroforaminal stenosis. The NU value and the subjective image quality scores were compared between 1.5T-DLR and 3T-nonDLR using the Wilcoxon signed-rank test. Interobserver agreement in evaluations of neuroforaminal stenosis for 1.5T-DLR and 3T-nonDLR was evaluated using Cohen's weighted kappa analysis. RESULTS: The NU value for 1.5T-DLR was 8.4, which was significantly better than that for 3T-nonDLR (10.3; p < 0.001). Subjective image scores were significantly better for 1.5T-DLR than 3T-nonDLR images (p < 0.037). Interobserver agreement (95% confidence intervals) in the evaluations of neuroforaminal stenosis was significantly superior for 1.5T-DLR (0.920 [0.916-0.924]) than 3T-nonDLR (0.894 [0.889-0.898]). CONCLUSION: By using DLR, image quality and interobserver agreement in evaluations of neuroforaminal stenosis on 1.5T cervical spine MRI could be improved compared to 3T MRI without DLR.

Feasibility of accelerated whole-body diffusion-weighted imaging using a deep learning-based noise-reduction technique in patients with prostate cancer.

PURPOSE: To assess the possibility of reducing the image acquisition time for diffusion-weighted whole-body imaging with background body signal suppression (DWIBS) by denoising with deep learning-based reconstruction (dDLR). METHODS: Seventeen patients with prostate cancer who underwent DWIBS by 1.5 T magnetic resonance imaging with a number of excitations of 2 (NEX2) and 8 (NEX8) were prospectively enrolled. The NEX2 image data were processed by dDLR (dDLR-NEX2), and the NEX2, dDLR-NEX2, and NEX8 image data were analyzed. In qualitative analysis, two radiologists rated the perceived coarseness, conspicuity of metastatic lesions (lymph nodes and bone), and overall image quality. The contrast-to-noise ratios (CNRs), contrast ratios, and mean apparent diffusion coefficients (ADCs) of metastatic lesions were calculated in a quantitative analysis. RESULTS: The image acquisition time of NEX2 was 2.8 times shorter than that of NEX8 (3 min 30 s vs 9 min 48 s). The perceived coarseness and overall image quality scores reported by both readers were significantly higher for dDLR-NEX2 than for NEX2 (P = 0.005-0.040). There was no significant difference between dDLR-NEX2 and NEX8 in the qualitative analysis. The CNR of bone metastasis was significantly greater for dDLR-NEX2 than for NEX2 and NEX8 (P = 0.012 for both comparisons). The contrast ratios and mean ADCs were not significantly different among the three image types. CONCLUSIONS: dDLR improved the image quality of DWIBS with NEX2. In the context of lymph node and bone metastasis evaluation with DWIBS in patients with prostate cancer, dDLR-NEX2 has potential to be an alternative to NEX8 and reduce the image acquisition time.

MDS cells impair osteolineage differentiation of MSCs via extracellular vesicles to suppress normal hematopoiesis.

Myelodysplastic syndrome (MDS) is a clonal disorder of hematopoietic stem cells (HSCs), characterized by ineffective hematopoiesis and frequent progression to leukemia. It has long remained unresolved how MDS cells, which are less proliferative, inhibit normal hematopoiesis and eventually dominate the bone marrow space. Despite several studies implicating mesenchymal stromal or stem cells (MSCs), a principal component of the HSC niche, in the inhibition of normal hematopoiesis, the molecular mechanisms underlying this process remain unclear. Here, we demonstrate that both human and mouse MDS cells perturb bone metabolism by suppressing the osteolineage differentiation of MSCs, which impairs the ability of MSCs to support normal HSCs. Enforced MSC differentiation rescues the suppressed normal hematopoiesis in both in vivo and in vitro MDS models. Intriguingly, the suppression effect is reversible and mediated by extracellular vesicles (EVs) derived from MDS cells. These findings shed light on the novel MDS EV-MSC axis in ineffective hematopoiesis.

Clinical feasibility of an abdominal thin-slice breath-hold single-shot fast spin echo sequence processed using a deep learning-based noise-reduction approach.

BACKGROUND: T2-weighted imaging (T2WI) is a key sequence of MRI studies of the pancreas. The single-shot fast spin echo (single-shot FSE) sequence is an accelerated form of T2WI. We hypothesized that denoising approach with deep learning-based reconstruction (dDLR) could facilitate accelerated breath-hold thin-slice single-shot FSE MRI, and reveal the pancreatic anatomy in detail. PURPOSE: To assess the image quality of thin-slice (3 mm) respiratory-triggered FSE T2WI (Resp-FSE) and breath-hold fast advanced spin echo with and without dDLR (BH-dDLR-FASE and BH-FASE, respectively) at 1.5 T. MATERIALS AND METHODS: MR images of 42 prospectively enrolled patients with suspected pancreaticobiliary disease were obtained at 1.5 T. We qualitatively and quantitatively evaluated image quality of BH-dDLR-FASE related to BH-FASE and Resp-FSE. RESULTS: The scan time of BH-FASE was significantly shorter than that of Resp-FSE (30 ± 4 s and 122 ± 25 s, p < 0.001). Qualitatively, dDLR significantly improved BH-FASE image quality, and the image quality of BH-dDLR-FASE was significantly better than that of Resp-FSE; as quantitative parameters, the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of BH-dDLR-FASE were also significantly better than those of Resp-FSE. The BH-dDLR-FASE sequence covered the entire pancreas and liver and provided overall image quality rated close to excellent. CONCLUSIONS: The dDLR technique enables accelerated thin-slice single-shot FSE, and BH-dDLR-FASE seems to be clinically feasible.

Whole-lesion histogram analysis of apparent diffusion coefficient for the assessment of non-mass enhancement lesions on breast MRI.

Objectives: To investigate the application of apparent diffusion coefficient (ADC) histogram analysis in differentiating between benign and malignant breast lesions detected as non-mass enhancement on MRI. Materials and Methods: A retrospective study was conducted for 25 malignant and 26 benign breast lesions showing non-mass enhancement on breast MRI. An experienced radiologist without prior knowledge of the pathological results drew a region of interest (ROI) outlining the periphery of each lesion on the ADC map. A histogram was then made for each lesion. Following a univariate analysis of 18 summary statistics values, we conducted statistical discrimination after hierarchical clustering using Ward's method. A comparison between the malignant and the benign groups was made using multiple logistic regression analysis and the Mann-Whitney U test. A P -value of less than 0.05 was considered statistically significant. Results: Univariate analysis for the 18 summary statistics values showed the malignant group had greater entropy (P < 0.001) and lower uniformity (P < 0.001). While there was no significant difference in mean and skewness values, the malignant group tended to show a lower mean (P = 0.090) and a higher skewness (P = 0.065). Hierarchical clustering of the 18 summary statistics values identified four values (10th percentile, entropy, skewness, and uniformity) of which the 10th percentile values were significantly lower for the malignant group (P = 0.035). Conclusions: Whole-lesion ADC histogram analysis may be useful for differentiating malignant from benign lesions which show non-mass enhancement on breast MRI.

Deep learning reconstruction for 1.5 T cervical spine MRI: effect on interobserver agreement in the evaluation of degenerative changes.

OBJECTIVES: To investigate whether deep learning reconstruction (DLR) provides improved cervical spine MR images using a 1.5 T unit in the evaluation of degenerative changes without increasing imaging time. METHODS: This study included 21 volunteers (age 42.4 ± 11.9 years; 17 males) who underwent 1.5 T cervical spine sagittal T2-weighted MRI. From the imaging data with number of acquisitions (NAQ) of 1 or 2, images were reconstructed with DLR (NAQ1-DLR) and without DLR (NAQ1) or without DLR (NAQ2), respectively. Two readers evaluated the images for depiction of structures, artifacts, noise, overall image quality, spinal canal stenosis, and neuroforaminal stenosis. The two readers read studies blinded and randomly. Values were compared between NAQ1-DLR and NAQ1 and between NAQ1-DLR and NAQ2 using the Wilcoxon signed-rank test. RESULTS: The analyses showed significantly better results for NAQ1-DLR compared with NAQ1 and NAQ2 (p < 0.023), except for depiction of disc and foramina by one reader and artifacts by both readers in the comparison between NAQ1-DLR and NAQ2. Interobserver agreements (Cohen's weighted kappa [97.5% confidence interval]) in the evaluation of spinal canal stenosis for NAQ1-DLR/NAQ1/NAQ2 were 0.874 (0.866-0.883)/0.778 (0.767-0.789)/0.818 (0.809-0.827), respectively, and those in the evaluation of neuroforaminal stenosis were 0.878 (0.872-0.883)/0.855 (0.849-0.860)/0.852 (0.845-0.860), respectively. CONCLUSIONS: DLR improved the 1.5 T cervical spine MR images in the evaluation of degenerative spine changes. KEY POINTS: • Two radiologists demonstrated that deep learning reconstruction reduced the noise in cervical spine sagittal T2-weighted MR images obtained using a 1.5 T unit. • Reduced noise in deep learning reconstruction images resulted in a clearer depiction of structures, such as the spinal cord, vertebrae, and zygapophyseal joint. • Interobserver agreement in the evaluation of spinal canal stenosis and foraminal stenosis on cervical spine MR images was significantly improved using deep learning reconstruction (0.874 and 0.878, respectively) versus without deep learning (0.778-0.818 and 0.852-0.855, respectively).

Radiomics with 3-dimensional magnetic resonance fingerprinting: influence of dictionary design on repeatability and reproducibility of radiomic features.

OBJECTIVES: We aimed to investigate the influence of magnetic resonance fingerprinting (MRF) dictionary design on radiomic features using in vivo human brain scans. METHODS: Scan-rescans of three-dimensional MRF and conventional T1-weighted imaging were performed on 21 healthy volunteers (9 males and 12 females; mean age, 41.3 ± 14.6 years; age range, 22-72 years). Five patients with multiple sclerosis (3 males and 2 females; mean age, 41.2 ± 7.3 years; age range, 32-53 years) were also included. MRF data were reconstructed using various dictionaries with different step sizes. First- and second-order radiomic features were extracted from each dataset. Intra-dictionary repeatability and inter-dictionary reproducibility were evaluated using intraclass correlation coefficients (ICCs). Features with ICCs > 0.90 were considered acceptable. Relative changes were calculated to assess inter-dictionary biases. RESULTS: The overall scan-rescan ICCs of MRF-based radiomics ranged from 0.86 to 0.95, depending on dictionary step size. No significant differences were observed in the overall scan-rescan repeatability of MRF-based radiomic features and conventional T1-weighted imaging (p = 1.00). Intra-dictionary repeatability was insensitive to dictionary step size differences. MRF-based radiomic features varied among dictionaries (overall ICC for inter-dictionary reproducibility, 0.62-0.99), especially when step sizes were large. First-order and gray level co-occurrence matrix features were the most reproducible feature classes among different step size dictionaries. T1 map-derived radiomic features provided higher repeatability and reproducibility among dictionaries than those obtained with T2 maps. CONCLUSION: MRF-based radiomic features are highly repeatable in various dictionary step sizes. Caution is warranted when performing MRF-based radiomics using datasets containing maps generated from different dictionaries. KEY POINTS: • MRF-based radiomic features are highly repeatable in various dictionary step sizes. • Use of different MRF dictionaries may result in variable radiomic features, even when the same MRF acquisition data are used. • Caution is needed when performing radiomic analysis using data reconstructed from different dictionaries.