Steve C N Hui, Nickie Andescavage, Catherine Limperopoulos
{"title":"The Role of Proton Magnetic Resonance Spectroscopy in Neonatal and Fetal Brain Research.","authors":"Steve C N Hui, Nickie Andescavage, Catherine Limperopoulos","doi":"10.1002/jmri.29709","DOIUrl":"https://doi.org/10.1002/jmri.29709","url":null,"abstract":"<p><p>The biochemical composition and structure of the brain are in a rapid change during the exuberant stage of fetal and neonatal development. <sup>1</sup>H-MRS is a noninvasive tool that can evaluate brain metabolites in healthy fetuses and infants as well as those with neurological diseases. This review aims to provide readers with an understanding of 1) the basic principles and technical considerations relevant to <sup>1</sup>H-MRS in the fetal-neonatal brain and 2) the role of <sup>1</sup>H-MRS in early fetal-neonatal development brain research. We performed a PubMed search to identify original studies using <sup>1</sup>H-MRS in neonates and fetuses to establish the clinical applications of <sup>1</sup>H-MRS. The eligible studies for this review included original research with <sup>1</sup>H-MRS applications to the fetal-neonatal brain in healthy and high-risk conditions. We ran our search between 2000 and 2023, then added in several high-impact landmark publications from the 1990s. A total of 366 results appeared. After, we excluded original studies that did not include fetuses or neonates, non-proton MRS and non-neurological studies. Eventually, 110 studies were included in this literature review. Overall, the function of <sup>1</sup>H-MRS in healthy fetal-neonatal brain studies focuses on measuring the change of metabolite concentrations during neurodevelopment and the physical properties of the metabolites such as T<sub>1</sub>/T<sub>2</sub> relaxation times. For high-risk neonates, studies in very low birth weight preterm infants and full-term neonates with hypoxic-ischemic encephalopathy, along with examining the associations between brain biochemistry and cognitive neurodevelopment are most common. Additional high-risk conditions included infants with congenital heart disease or metabolic diseases, as well as fetuses of pregnant women with hypertensive disorders were of specific interest to researchers using <sup>1</sup>H-MRS. EVIDENCE LEVEL: 1 TECHNICAL EFFICACY: Stage 2.</p>","PeriodicalId":16140,"journal":{"name":"Journal of Magnetic Resonance Imaging","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143006340","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tania Lala, Lea Christierson, Petter Frieberg, Daniel Giese, Peter Kellman, Nina Hakacova, Pia Sjöberg, Ellen Ostenfeld, Johannes Töger
{"title":"Evaluation of Real-Time Cardiovascular Flow MRI Using Compressed Sensing in a Phantom and in Patients With Valvular Disease or Arrhythmia.","authors":"Tania Lala, Lea Christierson, Petter Frieberg, Daniel Giese, Peter Kellman, Nina Hakacova, Pia Sjöberg, Ellen Ostenfeld, Johannes Töger","doi":"10.1002/jmri.29702","DOIUrl":"https://doi.org/10.1002/jmri.29702","url":null,"abstract":"<p><strong>Background: </strong>Real-time (RT) phase contrast (PC) flow MRI can potentially be used to measure blood flow in arrhythmic patients. Undersampled RT PC has been combined with online compressed sensing (CS) reconstruction (CS RT) enabling clinical use. However, CS RT flow has not been validated in a clinical setting.</p><p><strong>Purpose: </strong>Evaluate CS RT in phantom and patients.</p><p><strong>Study type: </strong>Prospective.</p><p><strong>Population: </strong>Flow phantom (60 cycles/min: N = 10, 120 cycles/min: N = 12), sinus rhythm patients, no regurgitation (N = 20) or suspected aortic regurgitation (N = 10), arrhythmia patients (N = 10).</p><p><strong>Field strength/sequence: </strong>1.5 T, 2D gated PC, CS RT PC, RT cine with arrhythmia rejection.</p><p><strong>Assessment: </strong>Phantom experiments tested the accuracy of CS RT cardiac output and peak flow rate at 60 and 120 cycles/min against gated PC. For sinus rhythm patients, cardiac output, peak flow rate, and regurgitation fraction in the ascending aorta and/or pulmonary artery were evaluated against gated PC. Cardiac output in patients with arrythmia was evaluated against RT cine with arrhythmia rejection.</p><p><strong>Statistical tests: </strong>Bland Altman, correlation, Mann-Whitney test, Wilcoxon signed-rank test.</p><p><strong>Results: </strong>Cardiac output bias ± SD for CS RT in the phantom was -0.0 ± 0.2 L/min (0.5 ± 3%, P = 0.76) at 60 cycles/min and 0.2 ± 0.3 L/min (4 ± 4%, P = 0.0016) at 120 cycles/min. Correspondingly, peak flow rate bias was -23 ± 6 mL/s (-7 ± 2%, P < 0.0001) and -73 ± 25 mL/s (-23 ± 4%, P < 0.0001). In patients, regurgitant fraction was -4 ± 0.5% (-23 ± 4%, P = 0.0025). Cardiac output bias in patients in sinus rhythm was -0.1 ± 0.5 L/min (-2 ± 10%, P = 0.99) (with regurgitation) and -0.3 ± 0.6 L/min (-5 ± 11%, P = 0.035) (without regurgitation). Peak flow rate bias was -60 ± 31 mL/s (-13 ± 6%, P < 0.0001) (with regurgitation) and -64 ± 32 mL/s (-16 ± 8%, P < 0.0001) (without regurgitation). Cardiac output bias was -0.4 ± 0.6 L/min (-9 ± 11%, P < 0.003) in arrhythmia patients.</p><p><strong>Data conclusions: </strong>CS RT flow could potentially serve as a clinical tool for patients with or without valvular disease or arrhythmia, with accurate cardiac output and regurgitation fraction quantification.</p><p><strong>Plain language summary: </strong>Accurate flow assessment is important in clinical evaluation of cardiac patients, but in the presence of irregular heart rhythm flow assessment is challenging. We have evaluated a new method using cardiac magnetic resonance imaging and real-time flow for blood flow assessment in cardiac patients. The method was tested against a reference method in a phantom flow model in low and high heart rates, and in cardiac patients with and without irregular heart rhythm and in different vessels. We found the cardiac magnetic resonance imaging real time flow method accurate and therefore promising fo","PeriodicalId":16140,"journal":{"name":"Journal of Magnetic Resonance Imaging","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143006879","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sadegh Ghaderi, Sana Mohammadi, Amir Mahmoud Ahmadzadeh, Kimia Darmiani, Melika Arab Bafrani, Nahid Jashirenezhad, Maryam Helfi, Sanaz Alibabaei, Sareh Azadi, Sahar Heidary, Farzad Fatehi
{"title":"Thalamic Magnetic Susceptibility (χ) Alterations in Neurodegenerative Diseases: A Systematic Review and Meta-Analysis of Quantitative Susceptibility Mapping Studies.","authors":"Sadegh Ghaderi, Sana Mohammadi, Amir Mahmoud Ahmadzadeh, Kimia Darmiani, Melika Arab Bafrani, Nahid Jashirenezhad, Maryam Helfi, Sanaz Alibabaei, Sareh Azadi, Sahar Heidary, Farzad Fatehi","doi":"10.1002/jmri.29698","DOIUrl":"https://doi.org/10.1002/jmri.29698","url":null,"abstract":"<p><strong>Background: </strong>Quantitative Susceptibility Mapping (QSM) provides a non-invasive post-processing method to investigate alterations in magnetic susceptibility (χ), reflecting iron content within brain regions implicated in neurodegenerative diseases (NDDs).</p><p><strong>Purpose: </strong>To investigate alterations in thalamic χ in patients with NDDs using QSM.</p><p><strong>Study type: </strong>Systematic review and meta-analysis.</p><p><strong>Population: </strong>A total of 696 patients with NDDs and 760 healthy controls (HCs) were included in 27 studies.</p><p><strong>Field strength/sequence: </strong>Three-dimensional multi-echo gradient echo sequence for QSM at mostly 3 Tesla.</p><p><strong>Assessment: </strong>Studies reporting QSM values in the thalamus of patients with NDDs were included. Following PRISMA 2020, we searched the four major databases including PubMed, Scopus, Web of Science, and Embase for peer-reviewed studies published until October 2024.</p><p><strong>Statistical tests: </strong>Meta-analysis was conducted using a random-effects model to calculate the standardized mean difference (SMD) between patients and HCs.</p><p><strong>Results: </strong>The pooled SMD indicated a significant increase in thalamic χ in NDDs compared to HCs (SMD = 0.42, 95% CI: 0.05-0.79; k = 27). Notably, amyotrophic lateral sclerosis patients showed a significant increase in thalamic χ (1.09, 95% CI: 0.65-1.53, k = 2) compared to HCs. Subgroup analyses revealed significant χ alterations in younger patients (mean age ≤ 62 years; 0.56, 95% CI: 0.10-1.02, k = 11) and studies using greater coil channels (coil channels > 16; 0.64, 95% CI: 0.28-1.00, k = 9). Publication bias was not detected and quality assessment indicated that studies with a lower risk of bias presented more reliable findings (0.75, 95% CI: 0.32-1.18, k = 9). Disease type was the primary driver of heterogeneity, while other factors, such as coil type and geographic location, also contributed to variability.</p><p><strong>Data conclusion: </strong>Our findings support the potential of QSM for investigating thalamic involvement in NDDs. Future research should focus on disease-specific patterns, thalamic-specific nucleus analysis, and temporal evolution.</p><p><strong>Plain language summary: </strong>Our research investigated changes in iron levels within the thalamus, a brain region crucial for motor and cognitive functions, in patients with various neurodegenerative diseases (NDDs). The study utilized a specific magnetic resonance imaging technique called Quantitative Susceptibility Mapping (QSM) to measure iron content. It identified a significant increase in thalamic iron levels in NDD patients compared to healthy individuals. This increase was particularly prominent in patients with Amyotrophic Lateral Sclerosis, younger individuals, and studies employing advanced imaging equipment.</p><p><strong>Level of evidence: </strong>2 TECHNICAL EFFICACY: Stage 2.</p>","PeriodicalId":16140,"journal":{"name":"Journal of Magnetic Resonance Imaging","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143006256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jon André Ottesen, Elizabeth Tong, Kyrre Eeg Emblem, Anna Latysheva, Greg Zaharchuk, Atle Bjørnerud, Endre Grøvik
{"title":"Semi-Supervised Learning Allows for Improved Segmentation With Reduced Annotations of Brain Metastases Using Multicenter MRI Data.","authors":"Jon André Ottesen, Elizabeth Tong, Kyrre Eeg Emblem, Anna Latysheva, Greg Zaharchuk, Atle Bjørnerud, Endre Grøvik","doi":"10.1002/jmri.29686","DOIUrl":"https://doi.org/10.1002/jmri.29686","url":null,"abstract":"<p><strong>Background: </strong>Deep learning-based segmentation of brain metastases relies on large amounts of fully annotated data by domain experts. Semi-supervised learning offers potential efficient methods to improve model performance without excessive annotation burden.</p><p><strong>Purpose: </strong>This work tests the viability of semi-supervision for brain metastases segmentation.</p><p><strong>Study type: </strong>Retrospective.</p><p><strong>Subjects: </strong>There were 156, 65, 324, and 200 labeled scans from four institutions and 519 unlabeled scans from a single institution. All subjects included in the study had diagnosed with brain metastases.</p><p><strong>Field strength/sequences: </strong>1.5 T and 3 T, 2D and 3D T1-weighted pre- and post-contrast, and fluid-attenuated inversion recovery (FLAIR).</p><p><strong>Assessment: </strong>Three semi-supervision methods (mean teacher, cross-pseudo supervision, and interpolation consistency training) were adapted with the U-Net architecture. The three semi-supervised methods were compared to their respective supervised baseline on the full and half-sized training.</p><p><strong>Statistical tests: </strong>Evaluation was performed on a multinational test set from four different institutions using 5-fold cross-validation. Method performance was evaluated by the following: the number of false-positive predictions, the number of true positive predictions, the 95th Hausdorff distance, and the Dice similarity coefficient (DSC). Significance was tested using a paired samples t test for a single fold, and across all folds within a given cohort.</p><p><strong>Results: </strong>Semi-supervision outperformed the supervised baseline for all sites with the best-performing semi-supervised method achieved an on average DSC improvement of 6.3% ± 1.6%, 8.2% ± 3.8%, 8.6% ± 2.6%, and 15.4% ± 1.4%, when trained on half the dataset and 3.6% ± 0.7%, 2.0% ± 1.5%, 1.8% ± 5.7%, and 4.7% ± 1.7%, compared to the supervised baseline on four test cohorts. In addition, in three of four datasets, the semi-supervised training produced equal or better results than the supervised models trained on twice the labeled data.</p><p><strong>Data conclusion: </strong>Semi-supervised learning allows for improved segmentation performance over the supervised baseline, and the improvement was particularly notable for independent external test sets when trained on small amounts of labeled data.</p><p><strong>Plain language summary: </strong>Artificial intelligence requires extensive datasets with large amounts of annotated data from medical experts which can be difficult to acquire due to the large workload. To compensate for this, it is possible to utilize large amounts of un-annotated clinical data in addition to annotated data. However, this method has not been widely tested for the most common intracranial brain tumor, brain metastases. This study shows that this approach allows for data efficient deep learning models across ","PeriodicalId":16140,"journal":{"name":"Journal of Magnetic Resonance Imaging","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142962161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Editorial for \"Morphological Study on Lenticulostriate Arteries in Patients With Middle Cerebral Artery Stenosis at 7 T MRI\".","authors":"Hossam Youseff, Rodolfo G Gatto","doi":"10.1002/jmri.29692","DOIUrl":"https://doi.org/10.1002/jmri.29692","url":null,"abstract":"","PeriodicalId":16140,"journal":{"name":"Journal of Magnetic Resonance Imaging","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142962158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Dong Sun, Gang Wu, Wei Zhang, Nadeer M Gharaibeh, Xiaoming Li
{"title":"Visualizing Preosteoarthritis: Updates on UTE-Based Compositional MRI and Deep Learning Algorithms.","authors":"Dong Sun, Gang Wu, Wei Zhang, Nadeer M Gharaibeh, Xiaoming Li","doi":"10.1002/jmri.29710","DOIUrl":"https://doi.org/10.1002/jmri.29710","url":null,"abstract":"<p><p>Osteoarthritis (OA) is heterogeneous and involves structural changes in the whole joint, such as cartilage, meniscus/labrum, ligaments, and tendons, mainly with short T2 relaxation times. Detecting OA before the onset of irreversible changes is crucial for early proactive management and limit growing disease burden. The more recent advanced quantitative imaging techniques and deep learning (DL) algorithms in musculoskeletal imaging have shown great potential for visualizing \"pre-OA.\" In this review, we first focus on ultrashort echo time-based magnetic resonance imaging (MRI) techniques for direct visualization as well as quantitative morphological and compositional assessment of both short- and long-T2 musculoskeletal tissues, and second explore how DL revolutionize the way of MRI analysis (eg, automatic tissue segmentation and extraction of quantitative image biomarkers) and the classification, prediction, and management of OA. PLAIN LANGUAGE SUMMARY: Detecting osteoarthritis (OA) before the onset of irreversible changes is crucial for early proactive management. OA is heterogeneous and involves structural changes in the whole joint, such as cartilage, meniscus/labrum, ligaments, and tendons, mainly with short T2 relaxation times. Ultrashort echo time-based magnetic resonance imaging (MRI), in particular, enables direct visualization and quantitative compositional assessment of short-T2 tissues. Deep learning is revolutionizing the way of MRI analysis (eg, automatic tissue segmentation and extraction of quantitative image biomarkers) and the detection, classification, and prediction of disease. They together have made further advances toward identification of imaging biomarkers/features for pre-OA. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 2.</p>","PeriodicalId":16140,"journal":{"name":"Journal of Magnetic Resonance Imaging","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142950204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Junyeon Won, Tsubasa Tomoto, Kevin Shan, Takashi Tarumi, Rong Zhang
{"title":"Associations of Central Arterial Stiffness With Brain White Matter Integrity and Gray Matter Volume in MRI Across the Adult Lifespan.","authors":"Junyeon Won, Tsubasa Tomoto, Kevin Shan, Takashi Tarumi, Rong Zhang","doi":"10.1002/jmri.29713","DOIUrl":"10.1002/jmri.29713","url":null,"abstract":"<p><strong>Background: </strong>Central arterial stiffening is associated with brain white matter (WM) damage and gray matter (GM) volume loss in older adults, but little is known about this association from an adult lifespan perspective.</p><p><strong>Purpose: </strong>To investigate the associations of central arterial stiffness with WM microstructural organization, WM lesion load, cortical thickness, and GM volume in healthy adults across the lifespan.</p><p><strong>Study type: </strong>This is a cross-sectional study.</p><p><strong>Subjects: </strong>A total of 173 healthy adults (22-81 years) were included in this study.</p><p><strong>Field strength/sequence: </strong>3-T, T1-weighted magnetization prepared rapid gradient echo (MPRAGE), single-shot echo-planar imaging diffusion-weighted, and T2-weighted fluid-attenuated inversion recovery (FLAIR) sequences.</p><p><strong>Assessment: </strong>The participants underwent measurements of central arterial stiffness using carotid-femoral pulse wave velocity (cfPWV), diffusion tensor imaging (DTI) to measure whole-brain WM microstructural organization with free water (FW) and FW-corrected fractional anisotropy (FA<sub>COR</sub>), FLAIR to measure whole-brain WM hyperintensities (WMH), and MPRAGE to measure whole-brain cortical thickness and GM volume. The associations of age and cfPWV with MRI measures were assessed.</p><p><strong>Statistical tests: </strong>Linear regression models to examine the associations of brain WM and GM measures with age, cfPWV, and age × cfPWV interaction after adjusting for sex, education, and intracranial volume (ICV) (voxel-wise and cluster threshold P < 0.05). To understand the direction of the interaction result, the sample was stratified into lower and higher cfPWV groups using a median split of cfPWV.</p><p><strong>Results: </strong>Age × cfPWV interactions were observed in WM FW, WMH volume, cortical thickness, and GM volume (P < 0.01) such that the positive regression slopes between age, FW, and WMH volume were higher, while the negative regression slopes between age, cortical thickness, and GM volume were lower in those who had higher cfPWV relative to those who had lower cfPWV.</p><p><strong>Data conclusion: </strong>Central arterial stiffening may accelerate the age-related deteriorations in GM and WM structure across the adult lifespan.</p><p><strong>Plain language summary: </strong>Central arterial stiffening is associated with brain white matter (WM) damage and gray matter (GM) volume loss in older adults. We extended this investigation into an adult lifespan perspective by examining the associations of central arterial stiffening with brain structure in adults across age. A total of 172 healthy adults (22-81 years) underwent central arterial stiffening measure using applanation tonometry and brain measurement using MRI. We observed that higher central arterial stiffening may accelerate the age-related deterioration in brain WM and GM structure. These resul","PeriodicalId":16140,"journal":{"name":"Journal of Magnetic Resonance Imaging","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142962155","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ben Zhao, Buyue Cao, Tianyi Xia, Liwen Zhu, Yaoyao Yu, Chunqiang Lu, Tianyu Tang, Yuancheng Wang, Shenghong Ju
{"title":"Multiparametric MRI for Assessment of the Biological Invasiveness and Prognosis of Pancreatic Ductal Adenocarcinoma in the Era of Artificial Intelligence.","authors":"Ben Zhao, Buyue Cao, Tianyi Xia, Liwen Zhu, Yaoyao Yu, Chunqiang Lu, Tianyu Tang, Yuancheng Wang, Shenghong Ju","doi":"10.1002/jmri.29708","DOIUrl":"https://doi.org/10.1002/jmri.29708","url":null,"abstract":"<p><p>Pancreatic ductal adenocarcinoma (PDAC) is the deadliest malignant tumor, with a grim 5-year overall survival rate of about 12%. As its incidence and mortality rates rise, it is likely to become the second-leading cause of cancer-related death. The radiological assessment determined the stage and management of PDAC. However, it is a highly heterogeneous disease with the complexity of the tumor microenvironment, and it is challenging to adequately reflect the biological aggressiveness and prognosis accurately through morphological evaluation alone. With the dramatic development of artificial intelligence (AI), multiparametric magnetic resonance imaging (mpMRI) using specific contrast media and special techniques can provide morphological and functional information with high image quality and become a powerful tool in quantifying intratumor characteristics. Besides, AI has been widespread in the field of medical imaging analysis. Radiomics is the high-throughput mining of quantitative image features from medical imaging that enables data to be extracted and applied for better decision support. Deep learning is a subset of artificial neural network algorithms that can automatically learn feature representations from data. AI-enabled imaging biomarkers of mpMRI have enormous promise to bridge the gap between medical imaging and personalized medicine and demonstrate huge advantages in predicting biological characteristics and the prognosis of PDAC. However, current AI-based models of PDAC operate mainly in the realm of a single modality with a relatively small sample size, and the technical reproducibility and biological interpretation present a barrage of new potential challenges. In the future, the integration of multi-omics data, such as radiomics and genomics, alongside the establishment of standardized analytical frameworks will provide opportunities to increase the robustness and interpretability of AI-enabled image biomarkers and bring these biomarkers closer to clinical practice. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 4.</p>","PeriodicalId":16140,"journal":{"name":"Journal of Magnetic Resonance Imaging","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142950073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"MRI Signs Associated With Bladder Injury During Cesarean Delivery in Severe Placenta Accreta Spectrum Disorders.","authors":"Xin Chen, Xiaohan Zheng, Xianyun Cai, Huiwen Wang, Ruiqin Shan, Yongzhong Gu, Xietong Wang, Guangbin Wang","doi":"10.1002/jmri.29703","DOIUrl":"https://doi.org/10.1002/jmri.29703","url":null,"abstract":"<p><strong>Background: </strong>Bladder injury during cesarean delivery (CD) in pregnant women with severe placenta accreta spectrum (PAS) disorders mostly occurs in the dissection of vesico-uterine space. Placental MRI may help to assess the risk of bladder injury preoperatively.</p><p><strong>Purpose: </strong>To identify the high-risk MRI signs of bladder injury during CD in women with severe PAS.</p><p><strong>Study type: </strong>Retrospective.</p><p><strong>Subjects: </strong>One hundred sixty-seven women with surgically confirmed severe PAS, defined as to increta or percreta, who underwent planned CD and available placental MRI.</p><p><strong>Field strength/sequence: </strong>1.5 Tesla, half-Fourier single-shot turbo spin echo sequence and true fast imaging with steady state free precession sequence.</p><p><strong>Assessment: </strong>Presence of following imaging features of the vesico-uterine region were independently evaluated by three radiologists (with 8, 8, and 15 years of experience, respectively): vesico-uterine space hypervascularity, vesico-uterine space without chemical shift line, bladder wall interruption with hyperintense nodularity, bladder tenting, and uterine-placental bulge.</p><p><strong>Statistical tests: </strong>Univariable analyses (Chi-square or Fisher's exact test) and multivariable regression analyses were used. A P value <0.05 was considered significant.</p><p><strong>Results: </strong>Thirty-three of the women (19.8%) experienced bladder injury during CD. MRI features were significantly more frequent in the bladder injury group compared with the no bladder injury group: 69.7% vs. 26.9% in vesico-uterine space hypervascularity, 57.6% vs. 21.6% in absent chemical shift line in the vesico-uterine space, 18.2% vs. 1.5% in bladder wall interruption with hyperintense nodularity, 39.4% vs. 14.9% in bladder tenting, and 78.8% vs. 39.6% in uterine-placental bulging. Vesico-uterine space hypervascularity, absent chemical shift line, and uterine-placental bulge were independently associated with the risk of bladder injury (odds ratios: 4.190, 3.555, and 3.569, respectively).</p><p><strong>Data conclusion: </strong>Vesico-uterine space hypervascularity, vesico-uterine space without chemical shift line and uterine-placental bulge were associated with bladder injury during CD in women with severe PAS.</p><p><strong>Plain language summary: </strong>Bladder injury is a serious complication of cesarean delivery in pregnant women with severe placenta accreta spectrum, frequently resulting in massive hemorrhage, bladder dysfunction and severe infection. Accurate prenatal assessment is important to minimize these adverse consequences. This study showed that MRI features, including vesico-uterine space hypervascularity, vesico-uterine space without chemical shift line and uterine-placental bulge, were independently associated with bladder injury. These high-risk MRI signs may serve as effective means for prenatal assessment of bladd","PeriodicalId":16140,"journal":{"name":"Journal of Magnetic Resonance Imaging","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142950159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Presence of Fragmented Intratumoral Thrombosed Microvasculature in the Necrotic and Peri-Necrotic Regions on SWI Differentiates IDH Wild-Type Glioblastoma From IDH Mutant Grade 4 Astrocytoma.","authors":"Virendra Kumar Yadav, Shalini Sharma, Satyajit Maurya, Rakesh K Singh, Jitendra Saini, Preeti Jain, Rana Patir, Sunita Ahlawat, Sumanta Das, Sandeep Vaishya, Sumeet Agarwal, Anup Singh, Rakesh K Gupta","doi":"10.1002/jmri.29695","DOIUrl":"https://doi.org/10.1002/jmri.29695","url":null,"abstract":"<p><strong>Background: </strong>Isocitrate dehydrogenase (IDH) wild-type (IDH<sub>wt</sub>) glioblastomas (GB) are more aggressive and have a poorer prognosis than IDH mutant (IDH<sub>mt</sub>) tumors, emphasizing the need for accurate preoperative differentiation. However, a distinct imaging biomarker for differentiation mostly lacking. Intratumoral thrombosis has been reported as a histopathological biomarker for GB.</p><p><strong>Purpose: </strong>To evaluate the fragmented intratumoral thrombosed microvasculature (FTV) signs on susceptibility-weighted imaging (SWI) for distinguishing IDH<sub>wt</sub> and IDH<sub>mt</sub> tumors.</p><p><strong>Study type: </strong>Retrospective.</p><p><strong>Subjects: </strong>Ninety-seven treatment-naïve patients with histopathologically confirmed IDH<sub>wt</sub> GB (54 males, 26 females) and IDH<sub>mt</sub> grade 4 astrocytoma (13 males, 4 females).</p><p><strong>Field strength/sequence: </strong>3-T, SWI, fluid-attenuated-inversion-recovery (FLAIR), T<sub>1</sub>-weighted, T<sub>2</sub>-weighted, PD-weighted, post-contrast T<sub>1</sub>-weighted and dynamic-contrast-enhanced (DCE)-MRI.</p><p><strong>Assessment: </strong>SWI data were evaluated by three experienced neuroradiologists (S.S., 11 years; J.S., 15 years; R.K.G., 40 years of experience), who assessed FTV presence in necrotic and peri-necrotic regions. FTV was identified as intratumoral susceptibility signal having minimal or no interslice connections. Quantitative DCE-MRI parameters were derived using first-pass-analysis and extended Tofts model. FLAIR abnormal, contrast-enhancing, and necrotic regions were segmented using in-house developed U-Net architecture.</p><p><strong>Statistical tests: </strong>Fleiss' Kappa, Cohen's Kappa, Shapiro-Wilk test, t tests or Mann-Whitney U test, receiver-operating characteristic (ROC) analysis, confusion matrix. A P-value <0.05 was considered statistically significant.</p><p><strong>Results: </strong>Fleiss' kappa test provided 91% inter-rater agreement, and Cohen's kappa provided intrarater agreement ranged from 81% to 97%. The raters' accuracy in distinguishing IDH<sub>wt</sub> from IDH<sub>mt</sub> ranged from 92% to 94%. Some of the quantitative DCE-MRI parameters (CBV, Ve, and K<sup>trans</sup>) provided statistically significant differences in differentiating IDH<sub>wt</sub> and IDH<sub>mt</sub>. K<sup>trans</sup> demonstrated 80.3% sensitivity and 81.2% specificity, with ROC analysis showing an AUC of 0.77.</p><p><strong>Data conclusion: </strong>FTV signs in necrotic and peri-necrotic regions on SWI demonstrated a high accuracy in distinguishing IDH<sub>wt</sub> from IDH<sub>mt</sub>. Qualitative assessment of FTV signs showed almost perfect inter-rater and intrarater agreement. Quantitative DCE-MRI metrics also showed statistically significant differentiation of IDH<sub>wt</sub> and IDH<sub>mt</sub>.</p><p><strong>Plain language summary: </strong>This study demonstrates that preoperative imaging, pa","PeriodicalId":16140,"journal":{"name":"Journal of Magnetic Resonance Imaging","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142950077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}