Anja Hohmann, Ke Zhang, Christoph M Mooshage, Johann M E Jende, Lukas T Rotkopf, Heinz-Peter Schlemmer, Martin Bendszus, Wolfgang Wick, Felix T Kurz
Background and purpose: The novel MR imaging technique of vascular architecture mapping allows in vivo characterization of local changes in cerebral microvasculature, but reference ranges for vascular architecture mapping parameters in healthy brain tissue are lacking, limiting its potential applicability as an MR imaging biomarker in clinical practice. We conducted whole-brain vascular architecture mapping in a large cohort to establish vascular architecture mapping parameter references ranges and identify region-specific cortical and subcortical microvascular profiles.
Materials and methods: This was a single-center examination of adult patients with unifocal, stable low-grade gliomas with multiband spin- and gradient-echo EPI sequence at 3T using parallel imaging. Voxelwise plotting of resulting values for gradient-echo (R2*) versus spin-echo (R2) relaxation rates during contrast agent bolus administration generates vessel vortex curves that allow the extraction of vascular architecture mapping parameters representative of, eg, vessel type, vessel radius, or CBV in the underlying voxel. Averaged whole-brain parametric maps were calculated for 9 parameters, and VOI analysis was conducted on the basis of a standardized brain atlas and individual cortical GM and WM segmentation.
Results: Prevalence of vascular risk factors among subjects (n = 106; mean age, 39.2 [SD, 12.5] years; 56 women) was similar to those in the German population. Compared with WM, we found cortical GM to have larger mean vascular calibers (5.80 [SD, 0.59] versus 4.25 [SD, 0.62] P < .001), increased blood volume fraction (20.40 [SD, 4.49] s-1 versus 11.05 [SD, 2.44] s-1; P < .001), and a dominance of venous vessels. Distinct microvascular profiles emerged for cortical GM, where vascular architecture mapping vessel type indicator differed, eg, between the thalamus and cortical GM (mean, -2.47 [SD, 4.02] s-2 versus -5.41 [SD, 2.84] s-2; P < .001). Intraclass correlation coefficient values indicated overall high test-retest reliability for vascular architecture mapping parameter mean values when comparing multiple scans per subject.
Conclusions: Whole-brain vascular architecture mapping in the adult brain reveals region-specific microvascular profiles. The obtained parameter reference ranges for distinct anatomic and functional brain areas may be used for future vascular architecture mapping studies on cerebrovascular pathologies and might facilitate early discovery of microvascular changes, in, eg, neurodegeneration and neuro-oncology.
{"title":"Whole-Brain Vascular Architecture Mapping Identifies Region-Specific Microvascular Profiles In Vivo.","authors":"Anja Hohmann, Ke Zhang, Christoph M Mooshage, Johann M E Jende, Lukas T Rotkopf, Heinz-Peter Schlemmer, Martin Bendszus, Wolfgang Wick, Felix T Kurz","doi":"10.3174/ajnr.A8344","DOIUrl":"10.3174/ajnr.A8344","url":null,"abstract":"<p><strong>Background and purpose: </strong>The novel MR imaging technique of vascular architecture mapping allows in vivo characterization of local changes in cerebral microvasculature, but reference ranges for vascular architecture mapping parameters in healthy brain tissue are lacking, limiting its potential applicability as an MR imaging biomarker in clinical practice. We conducted whole-brain vascular architecture mapping in a large cohort to establish vascular architecture mapping parameter references ranges and identify region-specific cortical and subcortical microvascular profiles.</p><p><strong>Materials and methods: </strong>This was a single-center examination of adult patients with unifocal, stable low-grade gliomas with multiband spin- and gradient-echo EPI sequence at 3T using parallel imaging. Voxelwise plotting of resulting values for gradient-echo (R<sub>2</sub>*) versus spin-echo (R<sub>2</sub>) relaxation rates during contrast agent bolus administration generates vessel vortex curves that allow the extraction of vascular architecture mapping parameters representative of, eg, vessel type, vessel radius, or CBV in the underlying voxel. Averaged whole-brain parametric maps were calculated for 9 parameters, and VOI analysis was conducted on the basis of a standardized brain atlas and individual cortical GM and WM segmentation.</p><p><strong>Results: </strong>Prevalence of vascular risk factors among subjects (<i>n</i> = 106; mean age, 39.2 [SD, 12.5] years; 56 women) was similar to those in the German population. Compared with WM, we found cortical GM to have larger mean vascular calibers (5.80 [SD, 0.59] versus 4.25 [SD, 0.62] <i>P </i>< .001), increased blood volume fraction (20.40 [SD, 4.49] s<sup>-1</sup> versus 11.05 [SD, 2.44] s<sup>-1</sup>; <i>P </i>< .001), and a dominance of venous vessels. Distinct microvascular profiles emerged for cortical GM, where vascular architecture mapping vessel type indicator differed, eg, between the thalamus and cortical GM (mean, -2.47 [SD, 4.02] s<sup>-2</sup> versus -5.41 [SD, 2.84] s<sup>-2</sup>; <i>P </i>< .001). Intraclass correlation coefficient values indicated overall high test-retest reliability for vascular architecture mapping parameter mean values when comparing multiple scans per subject.</p><p><strong>Conclusions: </strong>Whole-brain vascular architecture mapping in the adult brain reveals region-specific microvascular profiles. The obtained parameter reference ranges for distinct anatomic and functional brain areas may be used for future vascular architecture mapping studies on cerebrovascular pathologies and might facilitate early discovery of microvascular changes, in, eg, neurodegeneration and neuro-oncology.</p>","PeriodicalId":93863,"journal":{"name":"AJNR. American journal of neuroradiology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11392379/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141763145","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Seyed Behnam Jazayeri, Sherief Ghozy, Lina Hemmeda, Cem Bilgin, Mohamed Elfil, Ramanathan Kadirvel, David F Kallmes
<p><strong>Background: </strong>When treating acute ischemic stroke due to large-vessel occlusion, both mechanical thrombectomy and intravenous (IV) thrombolysis carry the risk of intracerebral hemorrhage.</p><p><strong>Purpose: </strong>This study aimed to delve deeper into the risk of intracerebral hemorrhage and its subtypes associated with mechanical thrombectomy with or without IV thrombolysis to contribute to better decision-making in the treatment of acute ischemic stroke due to large-vessel occlusion.</p><p><strong>Data sources: </strong>PubMed, EMBASE, and Scopus databases were searched for relevant studies from inception to September 6, 2023.</p><p><strong>Study selection: </strong>The eligibility criteria included randomized clinical trials or post hoc analysis of randomized controlled trials that focused on patients with acute ischemic stroke in the anterior circulation. After screening 4870 retrieved records, we included 9 studies (6 randomized controlled trials and 3 post hoc analyses of randomized controlled trials) with 3241 patients.</p><p><strong>Data analysis: </strong>The interventions compared were mechanical thrombectomy + IV thrombolysis versus mechanical thrombectomy alone, with the outcome of interest being any form of intracerebral hemorrhage and symptomatic intracerebral hemorrhage after intervention. A common definition for symptomatic intracerebral hemorrhage was pooled from various classification systems, and subgroup analyses were performed on the basis of different definitions and anatomic descriptions of hemorrhage. The quality of the studies was assessed using the revised version of Cochrane Risk of Bias 2 assessment tool. Meta-analysis was performed using the random effects model.</p><p><strong>Data synthesis: </strong>Eight studies had some concerns, and 1 study was considered high risk. Overall, the risk of symptomatic intracerebral hemorrhage was comparable between mechanical thrombectomy + IV thrombolysis and mechanical thrombectomy alone (risk ratio, 1.24 [95% CI, 0.89-1.72]; <i>P</i> = .20), with no heterogeneity across studies. Subgroup analysis of symptomatic intracerebral hemorrhage showed a non-significant difference between 2 groups based on the National Institute of Neurological Disorders and Stroke (<i>P</i> = .3), the Heidelberg Bleeding Classification (<i>P</i> = .5), the Safe Implementation of Thrombolysis in Stroke-Monitoring Study (<i>P</i> = .4), and the European Cooperative Acute Stroke Study III (<i>P</i> = .7) criteria. Subgroup analysis of different anatomic descriptions of intracerebral hemorrhage showed no difference between the 2 groups. Also, we found no difference in the risk of any intracerebral hemorrhage between two groups (risk ratio, 1.10 [95% CI, 1.00-1.21]; <i>P</i> = .052) with no heterogeneity across studies.</p><p><strong>Limitations: </strong>There was a potential for performance bias in most studies.</p><p><strong>Conclusions: </strong>In this systematic review and meta-an
背景:目的:本研究旨在深入探讨机械取栓联合或不联合静脉溶栓治疗急性大血管闭塞性缺血性卒中的脑出血风险及其亚型,以便在治疗急性大血管闭塞性缺血性卒中时做出更好的决策:检索了PubMed、EMBASE和Scopus数据库中从开始到2023年9月6日的相关研究:资格标准包括针对前循环急性缺血性卒中患者的随机临床试验或随机对照试验的事后分析。在筛选了 4870 份检索记录后,我们纳入了 9 项研究(6 项随机对照试验和 3 项随机对照试验的事后分析),共 3241 名患者:数据分析:比较的干预措施是机械性血栓切除术+静脉溶栓与单纯机械性血栓切除术,关注的结果是任何形式的脑内出血和干预后的无症状脑内出血。从不同的分类系统中汇集了症状性脑出血的通用定义,并根据不同的出血定义和解剖学描述进行了亚组分析。研究质量采用 Cochrane Risk of Bias 2 评估工具的修订版进行评估。采用随机效应模型进行 Meta 分析:8项研究存在一些问题,1项研究被视为高风险研究。总体而言,机械取栓术+静脉溶栓与单纯机械取栓术的症状性脑出血风险相当(风险比为1.24 [95% CI, 0.89-1.72];P = .20),各研究间无异质性。对无症状性脑出血进行的亚组分析显示,根据美国国立神经疾病与中风研究所(National Institute of Neurological Disorders and Stroke)(P = .3)、海德堡出血分类(Heidelberg Bleeding Classification)(P = .5)、中风溶栓安全实施监测研究(Safe Implementation of Thrombolysis in Stroke-Monitoring Study)(P = .4)和欧洲急性中风合作研究 III(European Cooperative Acute Stroke Study III)(P = .7)的标准,两组之间的差异不显著。对不同解剖学描述的脑内出血进行的亚组分析表明,两组之间没有差异。此外,我们还发现两组间发生任何脑内出血的风险没有差异(风险比为 1.10 [95% CI, 1.00-1.21];P = .052),且各研究间无异质性:局限性:大多数研究可能存在表现偏倚:在这项系统回顾和荟萃分析中,机械取栓术+静脉溶栓与单纯机械取栓术发生任何脑内出血和症状性脑内出血(包括各种分类和解剖描述)的风险相当。
{"title":"Risk of Hemorrhagic Transformation after Mechanical Thrombectomy without versus with IV Thrombolysis for Acute Ischemic Stroke: A Systematic Review and Meta-analysis of Randomized Clinical Trials.","authors":"Seyed Behnam Jazayeri, Sherief Ghozy, Lina Hemmeda, Cem Bilgin, Mohamed Elfil, Ramanathan Kadirvel, David F Kallmes","doi":"10.3174/ajnr.A8307","DOIUrl":"10.3174/ajnr.A8307","url":null,"abstract":"<p><strong>Background: </strong>When treating acute ischemic stroke due to large-vessel occlusion, both mechanical thrombectomy and intravenous (IV) thrombolysis carry the risk of intracerebral hemorrhage.</p><p><strong>Purpose: </strong>This study aimed to delve deeper into the risk of intracerebral hemorrhage and its subtypes associated with mechanical thrombectomy with or without IV thrombolysis to contribute to better decision-making in the treatment of acute ischemic stroke due to large-vessel occlusion.</p><p><strong>Data sources: </strong>PubMed, EMBASE, and Scopus databases were searched for relevant studies from inception to September 6, 2023.</p><p><strong>Study selection: </strong>The eligibility criteria included randomized clinical trials or post hoc analysis of randomized controlled trials that focused on patients with acute ischemic stroke in the anterior circulation. After screening 4870 retrieved records, we included 9 studies (6 randomized controlled trials and 3 post hoc analyses of randomized controlled trials) with 3241 patients.</p><p><strong>Data analysis: </strong>The interventions compared were mechanical thrombectomy + IV thrombolysis versus mechanical thrombectomy alone, with the outcome of interest being any form of intracerebral hemorrhage and symptomatic intracerebral hemorrhage after intervention. A common definition for symptomatic intracerebral hemorrhage was pooled from various classification systems, and subgroup analyses were performed on the basis of different definitions and anatomic descriptions of hemorrhage. The quality of the studies was assessed using the revised version of Cochrane Risk of Bias 2 assessment tool. Meta-analysis was performed using the random effects model.</p><p><strong>Data synthesis: </strong>Eight studies had some concerns, and 1 study was considered high risk. Overall, the risk of symptomatic intracerebral hemorrhage was comparable between mechanical thrombectomy + IV thrombolysis and mechanical thrombectomy alone (risk ratio, 1.24 [95% CI, 0.89-1.72]; <i>P</i> = .20), with no heterogeneity across studies. Subgroup analysis of symptomatic intracerebral hemorrhage showed a non-significant difference between 2 groups based on the National Institute of Neurological Disorders and Stroke (<i>P</i> = .3), the Heidelberg Bleeding Classification (<i>P</i> = .5), the Safe Implementation of Thrombolysis in Stroke-Monitoring Study (<i>P</i> = .4), and the European Cooperative Acute Stroke Study III (<i>P</i> = .7) criteria. Subgroup analysis of different anatomic descriptions of intracerebral hemorrhage showed no difference between the 2 groups. Also, we found no difference in the risk of any intracerebral hemorrhage between two groups (risk ratio, 1.10 [95% CI, 1.00-1.21]; <i>P</i> = .052) with no heterogeneity across studies.</p><p><strong>Limitations: </strong>There was a potential for performance bias in most studies.</p><p><strong>Conclusions: </strong>In this systematic review and meta-an","PeriodicalId":93863,"journal":{"name":"AJNR. American journal of neuroradiology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11392354/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141725261","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Amy F Juliano, Kuei-You Lin, Nitesh Shekhrajka, Donghoon Shin, Steven D Rauch, Andreas H Eckhard
Background and purpose: Menière disease (MD) manifests in 2 major endotypes: one with a hypoplastic, underdeveloped endolymphatic sac (MD-hp) and the other with a normally developed sac that degenerates over time (MD-dg). Determining the specific endotype in patients is important for predicting disease progression, tailoring patient counseling, and optimizing treatment strategies. Endotype diagnosis involves measuring an angular trajectory of the vestibular aqueduct (ATVA), with an ATVA ≥140° indicative of MD-hp and an ATVA ≤120° of MD-dg. However, assessing the ATVA can be challenging. This study aimed to explore the link between ATVA and the thickness of the retrolabyrinthine bone as an alternative diagnostic measure that could provide differentiation between MD endotypes using CT and MR imaging.
Materials and methods: Retrospective review of CT temporal bone imaging from 32 adult patients with definite MD (60 ears) and 33 age-matched controls without MD or other inner ear symptoms (61 ears) was performed. The ATVA and retrolabyrinthine bone thickness were measured using uniform methodology on standardized axial CT images. Comparative analyses were performed to determine the correlation between ATVA and retrolabyrinthine bone thickness. Additionally, from a separate cohort of 11 patients (22 ears), CT and MR examinations of the temporal bone were retrospectively reviewed for retrolabyrinthine bone thickness measurements, to verify the correlation across the 2 modalities.
Results: The average retrolabyrinthine bone thickness was statistically significantly different between MD endotypes, being a mean of 0.8 (SD, 0.3) mm in patients with MD-hp (ATVA ≥140°) and 2.0 (SD, 0.9) mm in patients with MD-dg (ATVA ≤120°), with a consistent pattern of thin retrolabyrinthine bone in MD-hp and variable thickness in MD-dg. Receiver operating characteristic curve analysis within the MD cohort revealed that a retrolabyrinthine bone thickness ≥1.2 mm effectively rules out MD-hp. Excellent interrater reliability was noted for the retrolabyrinthine measurement, and there was near-perfect correlation between CT and MR measurements.
Conclusions: Retrolabyrinthine bone thickness proved to be a useful and straightforward alternative marker for distinguishing MD endotypes, being particularly useful for excluding MD-hp. Including information on retrolabyrinthine bone thickness should be considered a routine part of reporting in the context of MD imaging.
{"title":"Retrolabyrinthine Bone Thickness as a Radiologic Marker for the Hypoplastic Endotype in Menière Disease.","authors":"Amy F Juliano, Kuei-You Lin, Nitesh Shekhrajka, Donghoon Shin, Steven D Rauch, Andreas H Eckhard","doi":"10.3174/ajnr.A8339","DOIUrl":"10.3174/ajnr.A8339","url":null,"abstract":"<p><strong>Background and purpose: </strong>Menière disease (MD) manifests in 2 major endotypes: one with a hypoplastic, underdeveloped endolymphatic sac (MD-hp) and the other with a normally developed sac that degenerates over time (MD-dg). Determining the specific endotype in patients is important for predicting disease progression, tailoring patient counseling, and optimizing treatment strategies. Endotype diagnosis involves measuring an angular trajectory of the vestibular aqueduct (ATVA), with an ATVA ≥140° indicative of MD-hp and an ATVA ≤120° of MD-dg. However, assessing the ATVA can be challenging. This study aimed to explore the link between ATVA and the thickness of the retrolabyrinthine bone as an alternative diagnostic measure that could provide differentiation between MD endotypes using CT and MR imaging.</p><p><strong>Materials and methods: </strong>Retrospective review of CT temporal bone imaging from 32 adult patients with definite MD (60 ears) and 33 age-matched controls without MD or other inner ear symptoms (61 ears) was performed. The ATVA and retrolabyrinthine bone thickness were measured using uniform methodology on standardized axial CT images. Comparative analyses were performed to determine the correlation between ATVA and retrolabyrinthine bone thickness. Additionally, from a separate cohort of 11 patients (22 ears), CT and MR examinations of the temporal bone were retrospectively reviewed for retrolabyrinthine bone thickness measurements, to verify the correlation across the 2 modalities.</p><p><strong>Results: </strong>The average retrolabyrinthine bone thickness was statistically significantly different between MD endotypes, being a mean of 0.8 (SD, 0.3) mm in patients with MD-hp (ATVA ≥140°) and 2.0 (SD, 0.9) mm in patients with MD-dg (ATVA ≤120°), with a consistent pattern of thin retrolabyrinthine bone in MD-hp and variable thickness in MD-dg. Receiver operating characteristic curve analysis within the MD cohort revealed that a retrolabyrinthine bone thickness ≥1.2 mm effectively rules out MD-hp. Excellent interrater reliability was noted for the retrolabyrinthine measurement, and there was near-perfect correlation between CT and MR measurements.</p><p><strong>Conclusions: </strong>Retrolabyrinthine bone thickness proved to be a useful and straightforward alternative marker for distinguishing MD endotypes, being particularly useful for excluding MD-hp. Including information on retrolabyrinthine bone thickness should be considered a routine part of reporting in the context of MD imaging.</p>","PeriodicalId":93863,"journal":{"name":"AJNR. American journal of neuroradiology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11392355/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141763143","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Erik H Middlebrooks, Vivek Gupta, Amit K Agarwal, Brin E Freund, Steven A Messina, William O Tatum, David S Sabsevitz, Anteneh M Feyissa, Seyed M Mirsattari, Fernando N Galan, Alfredo Quinones-Hinojosa, Sanjeet S Grewal, John V Murray
Temporal lobe epilepsy is a common form of epilepsy that is often associated with hippocampal sclerosis (HS). Although HS is commonly considered a binary assessment in radiologic evaluation, it is known that histopathologic changes occur in distinct clusters. Some subtypes of HS only affect certain subfields, resulting in minimal changes to the overall volume of the hippocampus. This is likely a major reason why whole hippocampal volumetrics have underperformed versus expert readers in the diagnosis of HS. With recent advancements in MRI technology, it is now possible to characterize the substructure of the hippocampus more accurately. However, this is not consistently addressed in radiographic evaluations. The histologic subtype of HS is critical for prognosis and treatment decision-making, necessitating improved radiologic classification of HS. The International League Against Epilepsy (ILAE) has issued a consensus classification scheme for subtyping HS histopathologic changes. This review aims to explore how the ILAE subtypes of HS correlate with radiographic findings, introduce a grading system that integrates radiologic and pathologic reporting in HS, and outline an approach to detecting HS subtypes by using MRI. This framework will not only benefit current clinical evaluations, but also enhance future studies involving high-resolution MRI in temporal lobe epilepsy.
{"title":"Radiologic Classification of Hippocampal Sclerosis in Epilepsy.","authors":"Erik H Middlebrooks, Vivek Gupta, Amit K Agarwal, Brin E Freund, Steven A Messina, William O Tatum, David S Sabsevitz, Anteneh M Feyissa, Seyed M Mirsattari, Fernando N Galan, Alfredo Quinones-Hinojosa, Sanjeet S Grewal, John V Murray","doi":"10.3174/ajnr.A8214","DOIUrl":"10.3174/ajnr.A8214","url":null,"abstract":"<p><p>Temporal lobe epilepsy is a common form of epilepsy that is often associated with hippocampal sclerosis (HS). Although HS is commonly considered a binary assessment in radiologic evaluation, it is known that histopathologic changes occur in distinct clusters. Some subtypes of HS only affect certain subfields, resulting in minimal changes to the overall volume of the hippocampus. This is likely a major reason why whole hippocampal volumetrics have underperformed versus expert readers in the diagnosis of HS. With recent advancements in MRI technology, it is now possible to characterize the substructure of the hippocampus more accurately. However, this is not consistently addressed in radiographic evaluations. The histologic subtype of HS is critical for prognosis and treatment decision-making, necessitating improved radiologic classification of HS. The International League Against Epilepsy (ILAE) has issued a consensus classification scheme for subtyping HS histopathologic changes. This review aims to explore how the ILAE subtypes of HS correlate with radiographic findings, introduce a grading system that integrates radiologic and pathologic reporting in HS, and outline an approach to detecting HS subtypes by using MRI. This framework will not only benefit current clinical evaluations, but also enhance future studies involving high-resolution MRI in temporal lobe epilepsy.</p>","PeriodicalId":93863,"journal":{"name":"AJNR. American journal of neuroradiology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11392372/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139934604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hunjong Lim, Dongjun Choi, Leonard Sunwoo, Jae Hyeop Jung, Sung Hyun Baik, Se Jin Cho, Jinhee Jang, Tackeun Kim, Kyong Joon Lee
Background and purpose: Intracranial steno-occlusive lesions are responsible for acute ischemic stroke. However, the clinical benefits of artificial intelligence (AI)-based methods for detecting pathologic lesions in intracranial arteries have not been evaluated. We aimed to validate the clinical utility of an AI model for detecting steno-occlusive lesions in the intracranial arteries.
Materials and methods: Overall, 138 TOF-MRA images were collected from 2 institutions, which served as internal (n = 62) and external (n = 76) test sets, respectively. Each study was reviewed by 5 radiologists (2 neuroradiologists and 3 radiology residents) to compare the usage and nonusage of our proposed AI model for TOF-MRA interpretation. They identified the steno-occlusive lesions and recorded their reading time. Observer performance was assessed by using the area under the jackknife free-response receiver operating characteristic curve (AUFROC) and reading time for comparison.
Results: The average AUFROC for the 5 radiologists demonstrated an improvement from 0.70 without AI to 0.76 with AI (P = .027). Notably, this improvement was most pronounced among the 3 radiology residents, whose performance metrics increased from 0.68 to 0.76 (P = .002). Despite an increased reading time by using AI, there was no significant change among the readings by radiology residents. Moreover, the use of AI resulted in improved interobserver agreement among the reviewers (the intraclass correlation coefficient increased from 0.734 to 0.752).
Conclusions: Our proposed AI model offers a supportive tool for radiologists, potentially enhancing the accuracy of detecting intracranial steno-occlusion lesions on TOF-MRA. Less experienced readers may benefit the most from this model.
{"title":"Automated Detection of Steno-Occlusive Lesion on Time-of-Flight MR Angiography: An Observer Performance Study.","authors":"Hunjong Lim, Dongjun Choi, Leonard Sunwoo, Jae Hyeop Jung, Sung Hyun Baik, Se Jin Cho, Jinhee Jang, Tackeun Kim, Kyong Joon Lee","doi":"10.3174/ajnr.A8334","DOIUrl":"10.3174/ajnr.A8334","url":null,"abstract":"<p><strong>Background and purpose: </strong>Intracranial steno-occlusive lesions are responsible for acute ischemic stroke. However, the clinical benefits of artificial intelligence (AI)-based methods for detecting pathologic lesions in intracranial arteries have not been evaluated. We aimed to validate the clinical utility of an AI model for detecting steno-occlusive lesions in the intracranial arteries.</p><p><strong>Materials and methods: </strong>Overall, 138 TOF-MRA images were collected from 2 institutions, which served as internal (<i>n</i> = 62) and external (<i>n</i> = 76) test sets, respectively. Each study was reviewed by 5 radiologists (2 neuroradiologists and 3 radiology residents) to compare the usage and nonusage of our proposed AI model for TOF-MRA interpretation. They identified the steno-occlusive lesions and recorded their reading time. Observer performance was assessed by using the area under the jackknife free-response receiver operating characteristic curve (AUFROC) and reading time for comparison.</p><p><strong>Results: </strong>The average AUFROC for the 5 radiologists demonstrated an improvement from 0.70 without AI to 0.76 with AI (<i>P </i>= .027). Notably, this improvement was most pronounced among the 3 radiology residents, whose performance metrics increased from 0.68 to 0.76 (<i>P </i>= .002). Despite an increased reading time by using AI, there was no significant change among the readings by radiology residents. Moreover, the use of AI resulted in improved interobserver agreement among the reviewers (the intraclass correlation coefficient increased from 0.734 to 0.752).</p><p><strong>Conclusions: </strong>Our proposed AI model offers a supportive tool for radiologists, potentially enhancing the accuracy of detecting intracranial steno-occlusion lesions on TOF-MRA. Less experienced readers may benefit the most from this model.</p>","PeriodicalId":93863,"journal":{"name":"AJNR. American journal of neuroradiology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11392362/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140893116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lauren A Beslow, Andrew J White, Timo Krings, Adrienne M Hammill, Shih Shan Lang, Atsuko Baba, Marianne S Clancy, Scott E Olitsky, Steven W Hetts
Background: Hereditary hemorrhagic telangiectasia is an autosomal dominant vascular dysplasia characterized by mucocutaneous telangiectasias, recurrent epistaxis, and organ vascular malformations including in the brain, which occur in about 10% of patients. These brain vascular malformations include high-flow AVMs and AVFs as well as low-flow capillary malformations. High-flow lesions can rupture, causing neurologic morbidity and mortality.
State of practice: International guidelines for the diagnosis and management of hereditary hemorrhagic telangiectasia recommend screening children for brain vascular malformations with contrast enhanced MR imaging at hereditary hemorrhagic telangiectasia diagnosis. Screening has not been uniformly adopted by some practitioners who contend that screening is not justified. Arguments against screening include application of short-term data from the adult A Randomized Trial of Unruptured Brain Arteriovenous Malformations (ARUBA) trial of unruptured sporadic brain AVMs to children with hereditary hemorrhagic telangiectasia as well as concerns about administration of sedation or IV contrast and causing patients or families increased anxiety.
Analysis: In this article, a multidisciplinary group of experts on hereditary hemorrhagic telangiectasia reviewed data that support screening guidelines and counter arguments against screening. Children with hereditary hemorrhagic telangiectasia have a preponderance of high-flow lesions including AVFs, which have the highest rupture risk. The rupture risk among children is estimated at about 0.7% per lesion per year and is additive across lesions and during a lifetime. ARUBA, an adult clinical trial of expectant medical management versus treatment of unruptured brain AVMs, favored medical management at 5 years but is not applicable to pediatric patients with hereditary hemorrhagic telangiectasia given the life expectancy of a child. Additionally, interventional, radiosurgical, and surgical techniques have improved with time. Experienced neurovascular experts can prospectively determine the best treatment for each child on the basis of local resources. The "watch and wait" approach to imaging means that children with brain vascular malformations will not be identified until a potentially life-threatening and deficit-producing intracerebral hemorrhage occurs. This expert group does not deem this to be an acceptable trade-off.
{"title":"Current Practice: Rationale for Screening Children with Hereditary Hemorrhagic Telangiectasia for Brain Vascular Malformations.","authors":"Lauren A Beslow, Andrew J White, Timo Krings, Adrienne M Hammill, Shih Shan Lang, Atsuko Baba, Marianne S Clancy, Scott E Olitsky, Steven W Hetts","doi":"10.3174/ajnr.A8195","DOIUrl":"10.3174/ajnr.A8195","url":null,"abstract":"<p><strong>Background: </strong>Hereditary hemorrhagic telangiectasia is an autosomal dominant vascular dysplasia characterized by mucocutaneous telangiectasias, recurrent epistaxis, and organ vascular malformations including in the brain, which occur in about 10% of patients. These brain vascular malformations include high-flow AVMs and AVFs as well as low-flow capillary malformations. High-flow lesions can rupture, causing neurologic morbidity and mortality.</p><p><strong>State of practice: </strong>International guidelines for the diagnosis and management of hereditary hemorrhagic telangiectasia recommend screening children for brain vascular malformations with contrast enhanced MR imaging at hereditary hemorrhagic telangiectasia diagnosis. Screening has not been uniformly adopted by some practitioners who contend that screening is not justified. Arguments against screening include application of short-term data from the adult A Randomized Trial of Unruptured Brain Arteriovenous Malformations (ARUBA) trial of unruptured sporadic brain AVMs to children with hereditary hemorrhagic telangiectasia as well as concerns about administration of sedation or IV contrast and causing patients or families increased anxiety.</p><p><strong>Analysis: </strong>In this article, a multidisciplinary group of experts on hereditary hemorrhagic telangiectasia reviewed data that support screening guidelines and counter arguments against screening. Children with hereditary hemorrhagic telangiectasia have a preponderance of high-flow lesions including AVFs, which have the highest rupture risk. The rupture risk among children is estimated at about 0.7% per lesion per year and is additive across lesions and during a lifetime. ARUBA, an adult clinical trial of expectant medical management versus treatment of unruptured brain AVMs, favored medical management at 5 years but is not applicable to pediatric patients with hereditary hemorrhagic telangiectasia given the life expectancy of a child. Additionally, interventional, radiosurgical, and surgical techniques have improved with time. Experienced neurovascular experts can prospectively determine the best treatment for each child on the basis of local resources. The \"watch and wait\" approach to imaging means that children with brain vascular malformations will not be identified until a potentially life-threatening and deficit-producing intracerebral hemorrhage occurs. This expert group does not deem this to be an acceptable trade-off.</p>","PeriodicalId":93863,"journal":{"name":"AJNR. American journal of neuroradiology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11392374/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141181509","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cheng-Chun Liu, Yi Yang, Jun Dong, Zhi-Qiang Sun, Qi-Sheng Ran, Wei Li, Wang-Sheng Jin, Meng Zhang
Basi-parallel anatomic scanning has been widely used for assessing the vascular morphology of vertebral basilar arteries. Previous studies have demonstrated its efficacy in evaluating the morphology of the MCA, which we refer to as MCA parallel anatomic scanning MR imaging (MCPAS). In this study, we present our experience with the application of MCPAS in patients with MCA occlusion. Endovascular treatment was performed on the patients with intact MCA morphology visible in on MCPAS, with no intracranial hemorrhage, occlusion, or other complications observed. No severe stenosis or re-occlusion was observed at the 12-month postoperative follow-up. In conclusion, MCPAS is an effective method for assessing the outer contour of an occlusive MCA. Endovascular treatment can be considered a safe and efficient option for patients who show a favorable MCA through MCPAS assessment.
{"title":"MCA Parallel Anatomic Scanning MR Imaging-Guided Recanalization of a Chronic Occluded MCA by Endovascular Treatment.","authors":"Cheng-Chun Liu, Yi Yang, Jun Dong, Zhi-Qiang Sun, Qi-Sheng Ran, Wei Li, Wang-Sheng Jin, Meng Zhang","doi":"10.3174/ajnr.A8303","DOIUrl":"10.3174/ajnr.A8303","url":null,"abstract":"<p><p>Basi-parallel anatomic scanning has been widely used for assessing the vascular morphology of vertebral basilar arteries. Previous studies have demonstrated its efficacy in evaluating the morphology of the MCA, which we refer to as MCA parallel anatomic scanning MR imaging (MCPAS). In this study, we present our experience with the application of MCPAS in patients with MCA occlusion. Endovascular treatment was performed on the patients with intact MCA morphology visible in on MCPAS, with no intracranial hemorrhage, occlusion, or other complications observed. No severe stenosis or re-occlusion was observed at the 12-month postoperative follow-up. In conclusion, MCPAS is an effective method for assessing the outer contour of an occlusive MCA. Endovascular treatment can be considered a safe and efficient option for patients who show a favorable MCA through MCPAS assessment.</p>","PeriodicalId":93863,"journal":{"name":"AJNR. American journal of neuroradiology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11392368/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141592345","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abhinav Patel, Ramez N Abdalla, Sammy Allaw, Donald R Cantrell, Ali Shaibani, Frances Caprio, David M Hasan, Ali Alaraj, Sean P Polster, Timothy J Carroll, Sameer A Ansari
<p><strong>Background and purpose: </strong>Analysis of vessel wall contrast kinetics (ie, wash-in/washout) is a promising method for the diagnosis and risk-stratification of intracranial atherosclerotic disease plaque (ICAD-P) and the intracranial aneurysm walls (IA-W). We used black-blood MR imaging or MR vessel wall imaging to evaluate the temporal relationship of gadolinium contrast uptake kinetics in ICAD-Ps and IA-Ws compared with normal anatomic reference structures.</p><p><strong>Materials and methods: </strong>Patients with ICAD-Ps or IAs who underwent MR vessel wall imaging with precontrast, early postcontrast (5-15 minutes), and delayed postcontrast (20-30 minutes) 3D T1-weighted TSE sequences were retrospectively studied. ROIs of a standardized diameter (2 mm) were used to measure the signal intensities of the cavernous sinus, pituitary infundibulum, temporalis muscle, and choroid plexus. Point ROIs were used for ICAD-Ps and IA-Ws. All ROI signal intensities were normalized to white matter signal intensity obtained using ROIs of 10-mm diameter. Measurements were acquired on precontrast, early postcontrast, and delayed postcontrast 3D T1 TSE sequences for each patient.ajnr;45/9/1206/T1T1T1Table 1:MR-VWI parameters for ICAD-Ps and IAsParameterValueSequence3D TSEScan planeAxialFOV (mm)160TR/TE (ms)800/28-32BW (Hx/pixel)370θ120Acceleration2ETL42Matrix acquisition0.5 mm ×0.5 mmMatrix recon0.5 mm ×0.5 mmNo. of slices/thick120/0.5<b>Note:</b>-FOV indicates field of view; TR, the repetition time; TE, the echo time; BW, bandwidth; ETL, echo train length; Matrix recon, matrix reconstruction.</p><p><strong>Results: </strong>Ten patients with 17 symptomatic ICAD-Ps and 30 patients with 34 IA-Ws were included and demonstrated persisting contrast uptake (<i>P </i>< .001) of 7.21% and 10.54% beyond the early phase (5-15 minutes postcontrast) and in the delayed phase (20-30 minutes postcontrast) on postcontrast MR vessel wall imaging. However, normal anatomic reference structures including the pituitary infundibulum and cavernous sinus demonstrated a paradoxical contrast washout in the delayed phase. In both ICAD-Ps and IA-Ws, the greatest percentage of quantitative enhancement (>70%-90%) occurred in the early phase of postcontrast imaging, consistent with the rapid contrast uptake kinetics of neurovascular pathology.</p><p><strong>Conclusions: </strong>Using standard MR vessel wall imaging techniques, our results demonstrate the effects of gadolinium contrast uptake kinetics in ICAD-Ps and IA-Ws with extended accumulating enhancement into the delayed phase (> 15 minutes) as opposed to normal anatomic reference structures that conversely exhibit decreasing enhancement. Because these relative differences are used to assess qualitative patterns of ICAD-P and IA-W enhancement, our findings highlight the importance of standardizing acquisition time points and MR vessel wall imaging protocols to interpret pathologic enhancement for the risk stratification
{"title":"Temporal Changes on Postgadolinium MR Vessel Wall Imaging Captures Enhancement Kinetics of Intracranial Atherosclerotic Plaques and Aneurysms.","authors":"Abhinav Patel, Ramez N Abdalla, Sammy Allaw, Donald R Cantrell, Ali Shaibani, Frances Caprio, David M Hasan, Ali Alaraj, Sean P Polster, Timothy J Carroll, Sameer A Ansari","doi":"10.3174/ajnr.A8370","DOIUrl":"10.3174/ajnr.A8370","url":null,"abstract":"<p><strong>Background and purpose: </strong>Analysis of vessel wall contrast kinetics (ie, wash-in/washout) is a promising method for the diagnosis and risk-stratification of intracranial atherosclerotic disease plaque (ICAD-P) and the intracranial aneurysm walls (IA-W). We used black-blood MR imaging or MR vessel wall imaging to evaluate the temporal relationship of gadolinium contrast uptake kinetics in ICAD-Ps and IA-Ws compared with normal anatomic reference structures.</p><p><strong>Materials and methods: </strong>Patients with ICAD-Ps or IAs who underwent MR vessel wall imaging with precontrast, early postcontrast (5-15 minutes), and delayed postcontrast (20-30 minutes) 3D T1-weighted TSE sequences were retrospectively studied. ROIs of a standardized diameter (2 mm) were used to measure the signal intensities of the cavernous sinus, pituitary infundibulum, temporalis muscle, and choroid plexus. Point ROIs were used for ICAD-Ps and IA-Ws. All ROI signal intensities were normalized to white matter signal intensity obtained using ROIs of 10-mm diameter. Measurements were acquired on precontrast, early postcontrast, and delayed postcontrast 3D T1 TSE sequences for each patient.ajnr;45/9/1206/T1T1T1Table 1:MR-VWI parameters for ICAD-Ps and IAsParameterValueSequence3D TSEScan planeAxialFOV (mm)160TR/TE (ms)800/28-32BW (Hx/pixel)370θ120Acceleration2ETL42Matrix acquisition0.5 mm ×0.5 mmMatrix recon0.5 mm ×0.5 mmNo. of slices/thick120/0.5<b>Note:</b>-FOV indicates field of view; TR, the repetition time; TE, the echo time; BW, bandwidth; ETL, echo train length; Matrix recon, matrix reconstruction.</p><p><strong>Results: </strong>Ten patients with 17 symptomatic ICAD-Ps and 30 patients with 34 IA-Ws were included and demonstrated persisting contrast uptake (<i>P </i>< .001) of 7.21% and 10.54% beyond the early phase (5-15 minutes postcontrast) and in the delayed phase (20-30 minutes postcontrast) on postcontrast MR vessel wall imaging. However, normal anatomic reference structures including the pituitary infundibulum and cavernous sinus demonstrated a paradoxical contrast washout in the delayed phase. In both ICAD-Ps and IA-Ws, the greatest percentage of quantitative enhancement (>70%-90%) occurred in the early phase of postcontrast imaging, consistent with the rapid contrast uptake kinetics of neurovascular pathology.</p><p><strong>Conclusions: </strong>Using standard MR vessel wall imaging techniques, our results demonstrate the effects of gadolinium contrast uptake kinetics in ICAD-Ps and IA-Ws with extended accumulating enhancement into the delayed phase (> 15 minutes) as opposed to normal anatomic reference structures that conversely exhibit decreasing enhancement. Because these relative differences are used to assess qualitative patterns of ICAD-P and IA-W enhancement, our findings highlight the importance of standardizing acquisition time points and MR vessel wall imaging protocols to interpret pathologic enhancement for the risk stratification","PeriodicalId":93863,"journal":{"name":"AJNR. American journal of neuroradiology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11392371/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141763144","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Real-World Adoption of Artificial Intelligence in Radiology: Opportunities and Barriers.","authors":"Reza Forghani","doi":"10.3174/ajnr.A8422","DOIUrl":"10.3174/ajnr.A8422","url":null,"abstract":"","PeriodicalId":93863,"journal":{"name":"AJNR. American journal of neuroradiology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11392376/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141914816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Alexandre Boutet, Samuel S Haile, Andrew Z Yang, Hyo Jin Son, Mikail Malik, Vivek Pai, Mehran Nasralla, Jurgen Germann, Artur Vetkas, Farzad Khalvati, Birgit B Ertl-Wagner
Background and purpose: Interest in artificial intelligence (AI) and machine learning (ML) has been growing in neuroradiology, but there is limited knowledge on how this interest has manifested into research and specifically, its qualities and characteristics. This study aims to characterize the emergence and evolution of AI/ML articles within neuroradiology and provide a comprehensive overview of the trends, challenges, and future directions of the field.
Materials and methods: We performed a bibliometric analysis of the American Journal of Neuroradiology; the journal was queried for original research articles published since inception (January 1, 1980) to December 3, 2022 that contained any of the following key terms: "machine learning," "artificial intelligence," "radiomics," "deep learning," "neural network," "generative adversarial network," "object detection," or "natural language processing." Articles were screened by 2 independent reviewers, and categorized into statistical modeling (type 1), AI/ML development (type 2), both representing developmental research work but without a direct clinical integration, or end-user application (type 3), which is the closest surrogate of potential AI/ML integration into day-to-day practice. To better understand the limiting factors to type 3 articles being published, we analyzed type 2 articles as they should represent the precursor work leading to type 3.
Results: A total of 182 articles were identified with 79% being nonintegration focused (type 1 n = 53, type 2 n = 90) and 21% (n = 39) being type 3. The total number of articles published grew roughly 5-fold in the last 5 years, with the nonintegration focused articles mainly driving this growth. Additionally, a minority of type 2 articles addressed bias (22%) and explainability (16%). These articles were primarily led by radiologists (63%), with most (60%) having additional postgraduate degrees.
Conclusions: AI/ML publications have been rapidly increasing in neuroradiology with only a minority of this growth being attributable to end-user application. Areas identified for improvement include enhancing the quality of type 2 articles, namely external validation, and addressing both bias and explainability. These results ultimately provide authors, editors, clinicians, and policymakers important insights to promote a shift toward integrating practical AI/ML solutions in neuroradiology.
{"title":"Assessing the Emergence and Evolution of Artificial Intelligence and Machine Learning Research in Neuroradiology.","authors":"Alexandre Boutet, Samuel S Haile, Andrew Z Yang, Hyo Jin Son, Mikail Malik, Vivek Pai, Mehran Nasralla, Jurgen Germann, Artur Vetkas, Farzad Khalvati, Birgit B Ertl-Wagner","doi":"10.3174/ajnr.A8252","DOIUrl":"10.3174/ajnr.A8252","url":null,"abstract":"<p><strong>Background and purpose: </strong>Interest in artificial intelligence (AI) and machine learning (ML) has been growing in neuroradiology, but there is limited knowledge on how this interest has manifested into research and specifically, its qualities and characteristics. This study aims to characterize the emergence and evolution of AI/ML articles within neuroradiology and provide a comprehensive overview of the trends, challenges, and future directions of the field.</p><p><strong>Materials and methods: </strong>We performed a bibliometric analysis of the <i>American Journal of Neuroradiology</i>; the journal was queried for original research articles published since inception (January 1, 1980) to December 3, 2022 that contained any of the following key terms: \"machine learning,\" \"artificial intelligence,\" \"radiomics,\" \"deep learning,\" \"neural network,\" \"generative adversarial network,\" \"object detection,\" or \"natural language processing.\" Articles were screened by 2 independent reviewers, and categorized into statistical modeling (type 1), AI/ML development (type 2), both representing developmental research work but without a direct clinical integration, or end-user application (type 3), which is the closest surrogate of potential AI/ML integration into day-to-day practice. To better understand the limiting factors to type 3 articles being published, we analyzed type 2 articles as they should represent the precursor work leading to type 3.</p><p><strong>Results: </strong>A total of 182 articles were identified with 79% being nonintegration focused (type 1 <i>n</i> = 53, type 2 <i>n</i> = 90) and 21% (<i>n</i> = 39) being type 3. The total number of articles published grew roughly 5-fold in the last 5 years, with the nonintegration focused articles mainly driving this growth. Additionally, a minority of type 2 articles addressed bias (22%) and explainability (16%). These articles were primarily led by radiologists (63%), with most (60%) having additional postgraduate degrees.</p><p><strong>Conclusions: </strong>AI/ML publications have been rapidly increasing in neuroradiology with only a minority of this growth being attributable to end-user application. Areas identified for improvement include enhancing the quality of type 2 articles, namely external validation, and addressing both bias and explainability. These results ultimately provide authors, editors, clinicians, and policymakers important insights to promote a shift toward integrating practical AI/ML solutions in neuroradiology.</p>","PeriodicalId":93863,"journal":{"name":"AJNR. American journal of neuroradiology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11392363/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140195289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}