Journal of Computer Assisted Tomography最新文献

{"title":"Percutaneous Lung Biopsies Aided by Artificial Intelligence: A Comparison Between Computer and Physician-Chosen Biopsy Paths.","authors":"Adrienne L Kisting, Meridith A Kisting, J Louis Hinshaw, Allison B Couillard, Giuseppe V Toia, Fred T Lee, Martin G Wagner","doi":"10.1097/RCT.0000000000001868","DOIUrl":"10.1097/RCT.0000000000001868","url":null,"abstract":"<p><strong>Objective: </strong>To compare Trajectory Recommendation Algorithm for CT-guided Biopsy (TRAX)-generated lung biopsy puncture pathways versus physician-chosen paths.</p><p><strong>Materials and methods: </strong>TRAX is an artificial intelligence (AI)-based algorithm that uses segmentation and physician-chosen logic rules to generate lung biopsy pathways. Once a target lesion is defined by the physician, TRAX generates and ranks ∼20,000 candidate pathways within an axial angle of ±20°. Blinded radiologists retrospectively rated pathways chosen by physicians (n=53) versus TRAX (n=53) from the same patients and setup scans prior to lung biopsies (scale: 1 to 3 safe, 4 to 5 unsafe). The quality and metrics of the pathways were compared.</p><p><strong>Results: </strong>All TRAX and physician-chosen pathways were determined safe by physician reviewers (rating 1 to 3). Ratings were identical in 93/159 (58%) cases; TRAX was superior in 36/159 (23%) cases, and physician paths were superior in 30/159 (19%) (no significant difference between pathways, P =0.61). TRAX pathways were shorter than physician pathways (7.2±2.5 vs. 7.8±2.1 cm, P =0.046). Most TRAX pathways were outside of the axial plane [n=27/53 (50.9%)], mean gantry angle=11.4±6.0°. The majority of physician-generated pathways were in the axial plane [n=43/53 (81.1%)], mean gantry angle=0.9±2.9° (TRAX vs. physician P <0.05 for proportion of paths in the axial plane and mean gantry angle).</p><p><strong>Conclusions: </strong>TRAX appears to be a promising AI tool to assist physicians in selecting needle trajectories for percutaneous CT-guided lung biopsies, particularly those outside the axial plane.</p>","PeriodicalId":15402,"journal":{"name":"Journal of Computer Assisted Tomography","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147772805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Whole-tumor Multiparametric MRI Histogram Analysis for Predicting Intracranial Solitary Fibrous Tumor Grades and Ki-67 Expression.","authors":"Hua Zhang, Xiaoling Li, Dairong Cao, Zhen Xing, Xingfu Wang","doi":"10.1097/RCT.0000000000001873","DOIUrl":"10.1097/RCT.0000000000001873","url":null,"abstract":"<p><strong>Purpose: </strong>Our aim was to explore the noninvasive prediction of intracranial solitary fibrous tumors (ISFTs) with World Health Organization (WHO) grade and Ki-67 expression level based on semantic and whole-tumor histogram features from multiparametric Magnetic Resonance Imaging (MRI).</p><p><strong>Methods: </strong>We retrospectively evaluated thirty-nine ISFTs with histologically proved WHO grade 1 (n=25), WHO grade 2-3 (n=14), low Ki-67 (n=31), and high Ki-67 (n=8). Clinical data, MR semantic, and whole-tumor histogram features were collected. The values between the two groups were compared with Mann-Whitney U test or Fisher's exact test. Logistic regression analysis, receiver operating characteristic curve, and integrated discrimination improvement (IDI) were applied to identify the diagnostic performance.</p><p><strong>Results: </strong>Hemorrhage and tumor-brain interface showed significant differences between WHO grade 1 and 2-3 groups (all P ＜0.05). WHO grade 1 group showed significantly higher CE-T1WI_mean (contrast-enhanced T1-weighted imaging), CE-T1WI_median, and CE-T1WI_P90 values than grade 2-3 group (all P ＜0.05). The combined model integrating tumor-brain interface and CE-T1WI_median achieved the highest area under the receiver operating characteristic curves (AUC) of 0.84, which was superior to each single model with improved IDI (IDI=0.15-0.21). Cystic degeneration and midline shift showed significant differences between high and low Ki-67 groups (all P ＜0.05). High Ki-67 group was showed lower ADC_mean (apparent diffusion coefficient), ADC_median, ADC_P90, and T2WI_skewness (T2-weighted imaging) values than low Ki-67 group (all P ＜0.05). The combined model integrating ADC_median and T2WI_skewness achieved the highest AUC of 0.94 and outperformed each single model with improved IDI (IDI=0.34-0.43).</p><p><strong>Conclusion: </strong>The combination of MR semantic and whole-tumor histogram features can predict ISFT grades and Ki-67 expression with favorable predictive performance.</p>","PeriodicalId":15402,"journal":{"name":"Journal of Computer Assisted Tomography","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147772771","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction of Ki-67 Status in Breast Cancer Using a Habitat-Guided 2.5D Multiparametric MRI Deep Learning Model.","authors":"Zeyang Miao, Run Xu, Mengyao Guo, Hong Chen, Xuting Fang, Qiong Li, Peng Luo, Guanwu Li","doi":"10.1097/RCT.0000000000001923","DOIUrl":"https://doi.org/10.1097/RCT.0000000000001923","url":null,"abstract":"<p><strong>Objective: </strong>Intratumoral heterogeneity may limit the representativeness of biopsy-based Ki-67 assessment in breast cancer. We therefore developed and validated a habitat-guided 2.5D deep learning (DL) model based on multiparametric MRI for noninvasive preoperative prediction of high versus low Ki-67 expression.</p><p><strong>Methods: </strong>This retrospective study enrolled 333 patients with invasive breast carcinoma from 2 distinct MRI vendor cohorts (Siemens, training set, n=233; United Imaging, independent test set, n=100). All patients underwent preoperative multiparametric MRI, including DCE-MRI and DWI. Hemodynamic parametric maps (wash-in, wash-out) and ADC maps were generated and subsequently clustered using a K-means algorithm (k=3) to create a functional habitat mask that quantitatively encodes intratumoral heterogeneity. A 7-channel 2.5D input tensor was then constructed by concatenating the central habitat-guided slice with its 6 adjacent anatomic slices. A ResNet18 backbone was trained to classify high (≥20%) versus low Ki-67 expression. The model's performance was rigorously evaluated against conventional 2D DL, clinical, and combined (DL+clinical) models using AUC, the DeLong test, and decision curve analysis (DCA).</p><p><strong>Results: </strong>In the challenging independent cross-vendor test set, our habitat-guided DL25D model demonstrated superior performance, achieving an AUC of 0.821 (95% CI: 0.736-0.906) and a sensitivity of 0.804. It significantly outperformed both the conventional DL2D model (AUC: 0.654, P=0.002) and the clinical model (AUC: 0.686, P=0.019). The incorporation of clinical variables failed to yield further improvement (combined model AUC: 0.837, P=0.483 vs. DL25D; NRI=0.021, P>0.05). DCA confirmed the superior net clinical benefit of our approach across a wide spectrum of threshold probabilities. Importantly, Grad-CAM visualizations revealed that the habitat-guided model strategically focused its attention on intratumoral core regions, whereas the conventional 2D model was distracted by tumor margins and background tissue.</p><p><strong>Conclusions: </strong>The habitat-guided 2.5D deep learning model showed potential as a noninvasive imaging adjunct for preoperative Ki-67 status prediction in breast cancer. Multicenter prospective validation is required before clinical use.</p>","PeriodicalId":15402,"journal":{"name":"Journal of Computer Assisted Tomography","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148864974","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prevalence of Meniscal Ramp Lesions According to the Type of Anterior Cruciate Ligament Tear: A Magnetic Resonance Imaging Study.","authors":"Ji N Kim, Hee J Park, Do Y Ahn, Myung S Kim, Seok W Hong","doi":"10.1097/RCT.0000000000001864","DOIUrl":"10.1097/RCT.0000000000001864","url":null,"abstract":"<p><strong>Purpose: </strong>Meniscal ramp lesions are frequently associated with anterior cruciate ligament (ACL) injuries but may be overlooked during arthroscopy, potentially affecting surgical planning and outcomes. This study aimed to evaluate the prevalence and types of meniscal ramp lesions on magnetic resonance (MR) imaging and to assess the relationship with ACL tear patterns and clinical variables.</p><p><strong>Methods: </strong>This retrospective study included 122 patients who underwent knee MR imaging before arthroscopic ACL reconstruction. ACL tears were classified as both-bundle or selective bundle tears based on arthroscopic findings. Meniscal ramp lesions were classified into 5 subtypes on MR imaging. Associations among meniscal ramp lesion prevalence, lesion subtype, ACL tear pattern, and clinical variables, including body mass index, were analyzed.</p><p><strong>Results: </strong>Meniscal ramp lesions were detected in 74.6% and 77.0% of patients by reader 1 and reader 2, respectively. Meniscal ramp lesions were significantly more frequent in both-bundle ACL tears than in selective bundle tears (84.0% vs. 56.1% for reader 1; 84.0% vs. 63.4% for reader 2; P <0.05). There was no significant difference in ramp lesion prevalence between anteromedial and posterolateral bundle tears or in ramp lesion subtype distribution according to ACL tear pattern.</p><p><strong>Conclusions: </strong>Meniscal ramp lesions are highly prevalent in patients with ACL tears and occur more frequently in both-bundle tears. MR imaging plays a critical role in detecting ramp lesions and may improve preoperative assessment and surgical planning.</p>","PeriodicalId":15402,"journal":{"name":"Journal of Computer Assisted Tomography","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147673806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Role of Low-Field Magnetic Resonance Imaging in the Lungs: Opportunities and Challenges.","authors":"Lea Azour, Shu-Fu Shih, William H Moore, Jeanne B Ackman","doi":"10.1097/RCT.0000000000001883","DOIUrl":"10.1097/RCT.0000000000001883","url":null,"abstract":"<p><p>Clinical utilization of lung MRI has not kept pace with MRI of other body regions. This is due to a combination of technical and perceptual factors related to lung imaging. With increasing access to and application of low-field MRI, there are unique opportunities for lung imaging. This review will first explain the role of conventional lung MRI, next delineate the opportunities afforded by low-field lung MRI and clinical knowledge to date, and third, address remaining challenges and future directions.</p>","PeriodicalId":15402,"journal":{"name":"Journal of Computer Assisted Tomography","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147948331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Timing and Energy Optimization of Dual-Energy CT for Brain Metastasis Conspicuity: A Prospective 24-Patient Study.","authors":"Jason M Johnson, Abhi Rashiwala, Apollo Krayyem, Ethan Wang, Hana Farzaneh, Halyna Pokhylevych, Ahmad Amer, Rick Layman, Dawid Schellingerhout, Chirag B Patel","doi":"10.1097/RCT.0000000000001870","DOIUrl":"10.1097/RCT.0000000000001870","url":null,"abstract":"<p><strong>Background: </strong>Brain metastases are frequently encountered and typically evaluated by MRI, but MRI is not always available or feasible. Dual-energy CT (DECT) with virtual monochromatic reconstructions (VMRs) may offer a rapid, accessible alternative. We aimed to determine the optimal post-contrast timing and VMR energy for visualizing brain metastases using DECT.</p><p><strong>Materials and methods: </strong>This prospective study enrolled 24 patients with known brain metastases. DECT head scans were acquired at 90 seconds, 5 minutes, 10 minutes, and 20 minutes post-contrast using a dual-source scanner. VMR images were generated from 40 to 190 keV. For each time point, we measured lesion and background attenuation across keV, and calculated signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). Friedman and Wilcoxon tests were used to compare timing and energy effects.</p><p><strong>Results: </strong>Lesion conspicuity declined after the vascular phase. At 90 seconds, average CNR and SNR were 2.22 ± 0.39 (95% CI: 1.83-2.62) and 8.19 ± 0.67 (7.52-8.85), respectively. These values at 20 minutes measured 1.85 ± 0.33 and 8.34 ± 0.64. CNR peaked consistently at 40 keV, whereas SNR peaked between 70 and 100 keV depending on phase. Statistical tests confirmed significant variation across both time and energy ( P  < 0.001).</p><p><strong>Conclusions: </strong>Optimal visualization of brain metastases on DECT is achieved at 90 seconds post-contrast using low-to-mid keV reconstructions. Although 40 keV maximized contrast, 70 to 85 keV offered a favorable balance of contrast and noise, supporting its use for interpretation and radiosurgical planning.</p>","PeriodicalId":15402,"journal":{"name":"Journal of Computer Assisted Tomography","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147772762","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ability of Deep Learning Image Reconstruction to Preserve Detail and Remove Noise in Coronary Computed Tomography Angiography: A Clinical Analysis.","authors":"Aria M Salyapongse, Prashant Nagpal, Martin G Wagner, Sarv Priya, Jakub Siembida, Timothy P Szczykutowicz","doi":"10.1097/RCT.0000000000001866","DOIUrl":"10.1097/RCT.0000000000001866","url":null,"abstract":"<p><strong>Purpose: </strong>To analyze image quality over 3 levels (low, medium, and high) of deep learning image reconstruction (DLIR), evaluate whether edge detail is lost with higher denoising levels.</p><p><strong>Materials and methods: </strong>Nineteen subjects scanned with the institute's clinical coronary CT angiography (CCTA) protocols were retrospectively reconstructed with low, medium, and high levels of DLIR. Two readers assessed image quality on a 5-point Likert scale for structural confidence in relevant structures, low contrast detectability, noise, spatial resolution, artifacts, and overall diagnostic quality. The noise texture of images was also assessed using a non-Likert 5-point scale of \"plastic\" to \"sandy.\" Reader agreement was assessed with pairwise linearly weighted Cohen Kappa. Objective analysis was performed with contrast-to-noise (CNR) measurements of the aorta, left main artery, and right coronary artery. Friedman and Dunnett tests were used to assess statistical differences in image quality and CNR. To assess detail loss, edge detail preservation was assessed with different images between DLIR levels.</p><p><strong>Results: </strong>Observations of the difference images between DLIR images and the histograms of edge and nonedge pixels demonstrated that negligible edge detail was lost between the DLIR reconstructions. High DLIR CNR was significantly ( P ≤0.006) higher than low and medium DLIR CNR. Medium DLIR CNR was significantly ( P ≤0.02) higher than low DLIR CNR. Reader agreement was moderate ( κ =0.42). High DLIR scores were significantly superior ( P ≤0.002) to low DLIR scores for most structural confidence structures, low contrast detectability, noise, spatial resolution, artifacts, and overall diagnostic quality, and significantly superior ( P ≤0.03) to medium DLIR scores for all categories except spatial resolution ( P =0.66).</p><p><strong>Conclusion: </strong>By both objective and subjective measures, the higher levels of DLIR resulted in improved image quality without loss of edge details.</p>","PeriodicalId":15402,"journal":{"name":"Journal of Computer Assisted Tomography","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13574356/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147673780","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparison Between Weight-Based Variable-Voltage and Fixed Volume-Voltage Protocols in Cancer Surveillance Computed Tomography.","authors":"Joseph J Ipsen, Kirsten Richards, James H Seow, Alexander Diamant, Alvin Tanaya, Arathy Harikumar, Eric Williams, Angela Kilcoyne, Ashik Amlani, Christopher J Welman","doi":"10.1097/RCT.0000000000001865","DOIUrl":"10.1097/RCT.0000000000001865","url":null,"abstract":"<p><strong>Objective: </strong>This study assessed whether the weight-based, variable tube voltage (Bayer MEDRAD Centargo SMART) protocol compared with a fixed contrast, fixed tube voltage (referred to as the 'OLD') protocol for cancer patients undergoing CT chest, abdomen, and pelvis (CAP) scans could reduce contrast dose, without a reduction in contrast enhancement.</p><p><strong>Methods: </strong>A total of 149 oncology patients, each underwent 2 surveillance CT CAP scans using both the OLD and SMART protocols, typically with a 3-month interval between scans. Contrast volume was recorded for each protocol as well as the CT attenuation measurement Hounsfield unit (HU) at the ascending aorta, pulmonary trunk, right atrial appendage, middle hepatic vein, main portal vein, and renal cortex, as well as dose-length product (DLP, mGy/cm) and CT Dose Index volume (CTDIvol, mGy).</p><p><strong>Results: </strong>The SMART protocol used less contrast per patient with a median volume of 80 versus 100 mL representing a 20% absolute reduction. Quantitative contrast enhancement measurements demonstrated non-inferior HU values in the SMART protocol at all sites. This was achieved with a 19% DLP and 9% CTDIvol decrease in radiation exposure.</p><p><strong>Conclusions: </strong>The weight-based contrast, variable tube voltage protocol effectively reduces contrast volume without increasing radiation dose and does not reduce contrast enhancement.</p>","PeriodicalId":15402,"journal":{"name":"Journal of Computer Assisted Tomography","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13574349/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147690273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing the Reliability of MRI and CT Scans for Liver Volume Estimation in Patients Undergoing Liver Transplantation.","authors":"Vahid Bazojoo, Arman Sharbatdaran, Andrea S Kierans, Steven Salvatore, Xinzi He, Chady Atallah, Martin R Prince","doi":"10.1097/RCT.0000000000001869","DOIUrl":"10.1097/RCT.0000000000001869","url":null,"abstract":"<p><strong>Objective: </strong>Magnetic resonance imaging (MRI) and computed tomography (CT) are commonly used to measure organ volumes, but accuracy has not been methodically confirmed. This research seeks to fill this gap by comparing preoperative MRI and CT for liver volumetric characterization to surgical specimen weights as a reference standard.</p><p><strong>Methods: </strong>In this cross-sectional study, we retrospectively enrolled subjects who underwent liver explant and had MRI or CT scans within 1 month preoperatively. Organs' labels were corrected by physicians after deep learning model inferences using ITK-SNAP software. Liver surgical weights were collected from pathology reports. Liver volume was estimated as liver weight (g)×a conversion factor (1.2 mL/g), taking into account density, blood loss, and post-explant changes. We excluded subjects who had gallbladder weight reported together with liver weight. For assessing the accuracy of MRI and CT scan volume measurement, we reported the average volume of all available axial, coronal, and sagittal sequences.</p><p><strong>Results: </strong>For MRI, there was no significant difference in the liver volume between sequences; the average volume over all sequences was used as the MRI measurement. There was good agreement between liver explant volume measurements on MRI [23 subjects, 26 exams, 1730 mL (1195, 2108) compared with pathology 1760 mL (1206, 2337); P =0.71] as well as between CT measurements [16 subjects, 23 exams, 1754 mL (1175, 2558) and pathology 1776 mL (1211, 2820); P =0.37]. In 5 subjects who had both MRI and CT (MRI: 1657±533  mL, CT: 1745​​​​​​±591 mL, surgical reference: 1750±679 mL; P =0.96), MRI and CT scans have similar high accuracy. There was a trend toward contrast-enhanced CT scans having greater volume accuracy compared with CT without contrast, with a mean error=6%±4% versus 11%±11%; P =0.29, respectively.</p><p><strong>Conclusions: </strong>Our study shows that MRI and CT scans both have high accuracy for liver volume measurements compared with surgical specimen weights. CT and MRI both accurately measured liver volume before liver explant evaluation.</p>","PeriodicalId":15402,"journal":{"name":"Journal of Computer Assisted Tomography","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147868686","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Low-Field Neuroimaging: Opportunities and Limitations.","authors":"Bradley N Delman, Daniel R Lefton, Mark Finkelstein, Amish H Doshi","doi":"10.1097/RCT.0000000000001906","DOIUrl":"10.1097/RCT.0000000000001906","url":null,"abstract":"<p><p>Magnetic resonance imaging (MRI) at low magnetic field strengths (under 1 T) has seen renewed interest, driven by technological advances that enhance accessibility, affordability, and versatility. Improvements in design, gradient performance, and artificial intelligence (AI)-assisted reconstruction enable diagnostic-quality neuroimaging at well under 1 T, disrupting the once-peerless dominance of high-field imaging. Modern low-field systems offer advantages in patient comfort, siting flexibility, and/or portability. Reduced infrastructure and safety constraints enable scanning in diverse settings, including outpatient, emergency, and intensive care environments. Lower susceptibility improves imaging near air-bone interfaces, metallic implants, and the skull base, while markedly lowering specific absorption rate (SAR) and acoustic noise. Clinical neurological applications extend across the brain, spine, and skull base and include pediatric or fetal imaging, where improved tolerance and reduced motion artifacts are particularly useful. Lower signal-to-noise ratio (SNR) and limited spatial resolution remain challenges. AI-enhanced reconstruction, optimized pulse sequences, and higher relaxivity of contrast agents help mitigate these drawbacks. Portable low-field MRI also enables point-of-care neuroimaging and intraoperative use, offering real-time insights to expedite diagnosis. However, it is critical to acknowledge that, while low-field applications have found important roles in terms of quality, speed, and performance, higher-field-strength scanners will remain the diagnostic standard for the foreseeable future.</p>","PeriodicalId":15402,"journal":{"name":"Journal of Computer Assisted Tomography","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148368620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}