Due primarily to the excellent soft tissue contrast depictions provided by MRI, the widespread application of head and neck MRI in clinical practice serves to assess various diseases. Artificial intelligence (AI)-based methodologies, particularly deep learning analyses using convolutional neural networks, have recently gained global recognition and have been extensively investigated in clinical research for their applicability across a range of categories within medical imaging, including head and neck MRI. Analytical approaches using AI have shown potential for addressing the clinical limitations associated with head and neck MRI. In this review, we focus primarily on the technical advancements in deep-learning-based methodologies and their clinical utility within the field of head and neck MRI, encompassing aspects such as image acquisition and reconstruction, lesion segmentation, disease classification and diagnosis, and prognostic prediction for patients presenting with head and neck diseases. We then discuss the limitations of current deep-learning-based approaches and offer insights regarding future challenges in this field.

The anterior mediastinum is the most common location of mediastinal tumors, and thymic epithelial tumors are the most common mediastinal tumors. It is important to differentiate thymic epithelial tumors from malignant lymphomas and malignant germ cell tumors because of the different treatment strategies. Dynamic contrast-enhanced MRI and diffusion-weighted imaging can provide additional information on the differential diagnosis. Chemical shift imaging can detect tiny fat tissues in the lesion and is useful in differentiating thymic hyperplasia from other solid tumors such as thymomas. MRI findings reflect histopathological features of mediastinal tumors, and a comprehensive evaluation of MRI sequences is important for estimation of the histopathological features of the tumor. In this manuscript, we describe the MRI findings of anterior mediastinal solid tumors and the role of MRI in the differential diagnosis.

Viral hepatitis was previously the most common cause of chronic liver disease. However, in recent years, nonalcoholic fatty liver disease (NAFLD) cases have been increasing, especially in developed countries. NAFLD is histologically characterized by fat, fibrosis, and inflammation in the liver, eventually leading to cirrhosis and hepatocellular carcinoma. Although biopsy is the gold standard for the assessment of the liver parenchyma, quantitative evaluation methods, such as ultrasound, CT, and MRI, have been reported to have good diagnostic performances. The quantification of liver fat, fibrosis, and inflammation is expected to be clinically useful in terms of the prognosis, early intervention, and treatment response for the management of NAFLD. The aim of this review was to discuss the basics and prospects of MRI-based tissue quantifications of the liver, mainly focusing on proton density fat fraction for the quantification of fat deposition, MR elastography for the quantification of fibrosis, and multifrequency MR elastography for the evaluation of inflammation.

With the increasing use of 3-tesla MRI scanners and the development of applicable sequences, it has become possible to achieve high-resolution, good contrast imaging, which has enabled the imaging of the walls of small-diameter intracranial arteries. In recent years, the usefulness of vessel wall imaging has been reported for numerous intracranial arterial diseases, such as for the detection of vulnerable plaque in atherosclerosis, diagnosis of cerebral arterial dissection, prediction of the rupture of cerebral aneurysms, and status of moyamoya disease and cerebral vasculitis. In this review, we introduce the histological characteristics of the intracranial artery, discuss intracranial vessel wall imaging methods, and review the findings of vessel wall imaging for various major intracranial arterial diseases.

Purpose: MR parameter mapping is a technique that obtains distributions of parameters such as relaxation time and proton density (PD) and is starting to be used for disease quantification in clinical diagnoses. Quantitative susceptibility mapping is also promising for the early diagnosis of brain disorders such as degenerative neurological disorders. Therefore, we developed an MR quantitative parameter mapping (QPM) method to map four tissue-related parameters (T₁, T₂*, PD, and susceptibility) and B₁ simultaneously by using a 3D partially RF-spoiled gradient echo (pRSGE). We verified the accuracy and repeatability of QPM in phantom and volunteer experiments.

Methods: Tissue-related parameters are estimated by varying four scan parameters of the 3D pRSGE: flip angle, RF-pulse phase increment, TR and TE, performing multiple image scans, and finding a least-squares fit for an intensity function (which expresses the relationship between the scan parameters and intensity values). The intensity function is analytically complex, but by using a Bloch simulation to create it numerically, the least-squares fitting can be used to estimate the quantitative values. This has the advantage of shortening the image-reconstruction processing time needed to estimate the quantitative values than with methods using pattern matching.

Results: A 1.1-mm isotropic resolution scan covering the whole brain was completed with a scan time of approximately 12 minutes, and the reconstruction time using a GPU was approximately 1 minute. The phantom experiments confirmed that both the accuracy and repeatability of the quantitative values were high. The volunteer scans also confirmed that the accuracy of the quantitative values was comparable to that of conventional methods.

Conclusion: The proposed QPM method can map T₁, T₂*, PD, susceptibility, and B₁ simultaneously within a scan time that can be applied to human subjects.

Purpose: To investigate whether intravoxel incoherent motion (IVIM) and/or non-Gaussian diffusion parameters are associated with distant disease-free survival (DDFS) in patients with invasive breast cancer.

Methods: From May 2013 to March 2015, 101 patients (mean age 60.0, range 28–88) with invasive breast cancer were evaluated prospectively. IVIM parameters (flowing blood volume fraction [f_IVIM] and pseudodiffusion coefficient [D*]) and non-Gaussian diffusion parameters (theoretical apparent diffusion coefficient [ADC] at a b value of 0 s/mm² [ADC₀] and kurtosis [K]) were estimated using a diffusion-weighted imaging series of 16 b values up to 2500 s/mm². Shifted ADC values (sADC_200–1500) and standard ADC values (ADC_0–800) were also calculated. The Kaplan–Meier method was used to generate survival analyses for DDFS, which were compared using the log-rank test. Univariable Cox proportional hazards models were used to assess any associations between each parameter and distant metastasis-free survival.

Results: The median observation period was 80 months (range, 35–92 months). Among the 101 patients, 12 (11.9%) developed distant metastasis, with a median time to metastasis of 79 months (range, 10–92 months). Kaplan–Meier analysis showed that DDFS was significantly shorter in patients with K > 0.98 than in those with K ≤ 0.98 (P = 0.04). Cox regression analysis showed a marginal statistical association between K and distant metastasis-free survival (P = 0.05).

Conclusion: Non-Gaussian diffusion may be associated with prognosis in invasive breast cancer. A higher K may be a marker to help identify patients at an elevated risk of distant metastasis, which could guide subsequent treatment.

Purpose: The optimal temporal resolution for free-breathing dynamic contrast-enhanced MRI (FBDCE-MRI) of the pancreas has not been determined. This study aimed to evaluate the appropriate temporal resolution to achieve good image quality and to perform pharmacokinetic analysis in FBDCE-MRI of the pancreas using golden-angle radial sparse parallel (GRASP).

Methods: Sixteen participants (53 ± 15 years, eight females) undergoing FBDCE-MRI were included in this prospective study. Images were retrospectively reconstructed at four temporal resolutions (1.8, 3.0, 4.8, and 7.8s). Two radiologists (5 years of experience) evaluated the image quality of each reconstructed image by assessing the visualization of the celiac artery (CEA), the common hepatic artery, the splenic artery, each area of the pancreas, and artifacts using a 5-point scale. Using Tissue-4D, pharmacokinetic parameters were calculated for each area in the reconstructed images at each temporal resolution for 16 examinations, excluding two with errors in the pharmacokinetic modeling analysis. Friedman and Bonferroni tests were used for analysis. A P value < 0.05 was considered statistically significant.

Results: During vascular assessment, only scores for the CEA at 7.8s were significantly lower than the other temporal resolutions. Scores of all pancreatic regions and artifacts were significantly lower at 1.8s than at 4.8s and 7.8s. In the pharmacokinetic analysis, all volume transfer coefficients (K_trans), rate constants (K_ep), and the initial area under the concentration curve (iAUC) in the pancreatic head and tail were significantly lower at 4.8s and 7.8s than at 1.8s. iAUC in the pancreatic body and extracellular extravascular volume fraction (V_e) in the pancreatic head were significantly lower at 7.8s than at 1.8s.

Conclusion: A temporal resolution of 3.0s is appropriate to achieve image quality and perform pharmacokinetic analysis in FBDCE-MRI of the pancreas using GRASP.

Purpose: Amide proton transfer (APT) imaging may detect changes in tissues’ pH based on the chemical exchange saturation transfer (CEST) phenomenon, and thus it may be useful for identifying the penumbra in ischemic stroke patients. We investigated the effect of saturation pulse duration and power on the APT effect in phantoms with different pH values.

Methods: Five samples were prepared from a 1:10 solution of egg-white albumin in phosphate-buffered saline at pH 6.53–7.65. The APT signal intensity (SI) was defined as asymmetry of the magnetization transfer ratio at 3.5 ppm. We measured the APT SIs in the egg-white albumin samples of different pH values with saturation pulse durations of 0.5, 1.0, 2.0, and 3.0 sec and saturation pulse powers of 0.5, 1.5, and 2.5 μT. The relative change in the APT SI in relation to the saturation duration and power at different pH values was defined as follows: (APT SI _{each saturation pulse} − APT SI _{shortest or weakest pulse})/APT SI_{shortest or weakest pulse}. The dependence of the APT SI on pH and the relative change in the APT SI were calculated as the slope of the linear regression.

Results: The lower the pH, the larger the relative change in the APT SI, due to the change in saturation pulse duration and power. The APT SI was highly correlated with the pH at all saturation pulse durations and powers.

Conclusion: The influence of saturation duration and power on the APT effect was greater at lower pH than higher pH. The combination of saturation pulse ≥ 1.0 s and power ≥ 1.5 μT was useful for the sensitive detection of changes in APT effects in the egg-white albumin samples with different pH values.

Purpose: Quantitative susceptibility mapping (QSM) is useful for obtaining biological information. To calculate susceptibility distribution, it is necessary to calculate the local field caused by the differences of susceptibility between the tissues. The local field can be obtained by removing a background field from a total field acquired by MR phase image. Conventional approaches based on spherical mean value (SMV) filtering, which are widely used for background field calculations, fail to calculate the background field of the brain surface region corresponding to the radius of the SMV kernel, and consequently cannot calculate the QSM of the brain surface region. Accordingly, a new method calculating the local field by expansively removing the background field is proposed for whole brain QSM.

Methods: The proposed method consists of two steps. First, the background field of the brain surface is calculated from the total field using a locally polynomial approximation of spherical harmonics. Second, the whole brain local field is calculated by SMV filtering with a constraint term of the background field of the brain surface. The parameters of the approximation were optimized to reduce calculation errors through simulations using both a numerical phantom and a measured human brain. Performance of the proposed method with the optimized parameters was quantitatively and visually compared with conventional methods in an experiment of five healthy volunteers.

Results: The proposed method showed the accurate local field over the expanded brain region in the simulation studies. It also showed consistent QSM with conventional methods inside of the brain surface and showed clear vein structures on the brain surface.

Conclusion: The proposed method enables accurate calculation of whole brain QSM without eroding the brain surface region while maintaining same values inside of the brain surface as the conventional methods.

Purpose: To evaluate the feasibility of folded image training strategy (FITS) and the quality of images reconstructed using the improved model-based deep learning (iMoDL) network trained with FITS (FITS-iMoDL) for abdominal MR imaging.

Methods: This retrospective study included abdominal 3D T1-weighted images of 122 patients. In the experimental analyses, peak SNR (PSNR) and structure similarity index (SSIM) of images reconstructed with FITS-iMoDL were compared with those with the following reconstruction methods: conventional model-based deep learning (conv-MoDL), MoDL trained with FITS (FITS-MoDL), total variation regularized compressed sensing (CS), and parallel imaging (CG-SENSE). In the clinical analysis, SNR and image contrast were measured on the reference, FITS-iMoDL, and CS images. Three radiologists evaluated the image quality using a 5-point scale to determine the mean opinion score (MOS).

Results: The PSNR of FITS-iMoDL was significantly higher than that of FITS-MoDL, conv-MoDL, CS, and CG-SENSE (P < 0.001). The SSIM of FITS-iMoDL was significantly higher than those of the others (P < 0.001), except for FITS-MoDL (P = 0.056). In the clinical analysis, the SNR of FITS-iMoDL was significantly higher than that of the reference and CS (P < 0.0001). Image contrast was equivalent within an equivalence margin of 10% among these three image sets (P < 0.0001). MOS was significantly improved in FITS-iMoDL (P < 0.001) compared with CS images in terms of liver edge and vessels conspicuity, lesion depiction, artifacts, blurring, and overall image quality.

Conclusion: The proposed method, FITS-iMoDL, allowed a deeper MoDL reconstruction network without increasing memory consumption and improved image quality on abdominal 3D T1-weighted imaging compared with CS images.