1
|
Lim H, Choi D, Sunwoo L, Jung JH, Baik SH, Cho SJ, Jang J, Kim T, Lee KJ. Automated Detection of Steno-Occlusive Lesion on Time-of-Flight MR Angiography: An Observer Performance Study. AJNR Am J Neuroradiol 2024; 45:1253-1259. [PMID: 38719612 PMCID: PMC11392362 DOI: 10.3174/ajnr.a8334] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/23/2024] [Accepted: 04/21/2024] [Indexed: 08/03/2024]
Abstract
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.
Collapse
Affiliation(s)
- Hunjong Lim
- From the Department of Radiology (H.L., L.S., J.H.J., S.H.B., S.J.C., K.J.L.), Seoul National University Bundang Hospital, Seongnam, South Korea
| | | | - Leonard Sunwoo
- From the Department of Radiology (H.L., L.S., J.H.J., S.H.B., S.J.C., K.J.L.), Seoul National University Bundang Hospital, Seongnam, South Korea
- Center for Artificial Intelligence in Healthcare (L.S.), Seoul National University Bundang Hospital, Seongnam, South Korea
| | - Jae Hyeop Jung
- From the Department of Radiology (H.L., L.S., J.H.J., S.H.B., S.J.C., K.J.L.), Seoul National University Bundang Hospital, Seongnam, South Korea
- Remote Reading Team (J.H.J.), Korea Armed Forces Capital Hospital, Seongnam, South Korea
| | - Sung Hyun Baik
- From the Department of Radiology (H.L., L.S., J.H.J., S.H.B., S.J.C., K.J.L.), Seoul National University Bundang Hospital, Seongnam, South Korea
| | - Se Jin Cho
- From the Department of Radiology (H.L., L.S., J.H.J., S.H.B., S.J.C., K.J.L.), Seoul National University Bundang Hospital, Seongnam, South Korea
| | - Jinhee Jang
- Department of Radiology (J.J.), Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, South Korea
| | | | - Kyong Joon Lee
- From the Department of Radiology (H.L., L.S., J.H.J., S.H.B., S.J.C., K.J.L.), Seoul National University Bundang Hospital, Seongnam, South Korea
- Monitor Corp. (K.J.L.), Seoul, South Korea
| |
Collapse
|
2
|
Choi D, Kim T, Jang J, Sunwoo L, Lee KJ. Intracranial steno-occlusive lesion detection on time-of-flight MR angiography using multi-task learning. Comput Med Imaging Graph 2023; 107:102220. [PMID: 37023509 DOI: 10.1016/j.compmedimag.2023.102220] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/18/2022] [Revised: 03/04/2023] [Accepted: 03/19/2023] [Indexed: 03/28/2023]
Abstract
Steno-occlusive lesions in intracranial arteries refer to segments of narrowed or occluded blood vessels that increase the risk of ischemic strokes. Steno-occlusive lesion detection is crucial in clinical settings; however, automatic detection methods have hardly been studied. Therefore, we propose a novel automatic method to detect steno-occlusive lesions in sequential transverse slices on time-of-flight magnetic resonance angiography. Our method simultaneously detects lesions while segmenting blood vessels based on end-to-end multi-task learning, reflecting that the lesions are closely related to the connectivity of blood vessels. We design classification and localization modules that can be attached to arbitrary segmentation network. As blood vessels are segmented, both modules simultaneously predict the presence and location of lesions for each transverse slice. By combining outputs from the two modules, we devise a simple operation that boosts the performance of lesion localization. Experimental results show that lesion prediction and localization performance is improved by incorporating blood vessel extraction. Our ablation study demonstrates that the proposed operation enhances lesion localization accuracy. We also verify the effectiveness of multi-task learning by comparing our approach with those that individually detect lesions with extracted blood vessels.
Collapse
|
3
|
Taylor JM, Chang M, Vaughan J, Horn PS, Zhang B, Leach JL, Vadivelu S, Abruzzo T. Cerebral Arterial Growth in Childhood. Pediatr Neurol 2022; 134:59-66. [PMID: 35839526 DOI: 10.1016/j.pediatrneurol.2022.06.017] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/08/2021] [Revised: 05/22/2022] [Accepted: 06/19/2022] [Indexed: 10/17/2022]
Abstract
BACKGROUND Improved understanding of cerebral arterial growth in children may lead to advances in the diagnosis and treatment of pediatric cerebrovascular disease. We correlated cross-sectional diameters of major cerebral arterial structures with age, sex, head circumference, weight, and height in children without cerebrovascular disease. METHODS Children with normal brain magnetic resonance imaging (MRI) were retrospectively identified and stratified into 23 age cohorts from birth to age 18 years. Absence of vascular disease was verified by medical record review. Demographic and biometric data were obtained from medical records. Intracranial arterial diameter (IAD) was measured on T2-weighted fast spin echo brain MRI of vertebral, basilar, internal carotid artery, and circle of Willis arterial segments. RESULTS A total of 307 subjects are included in the analysis, including 5833 vessel segments (mean age 8.4 years, 53% female). Indications for imaging were headache (73%), seizure (26%) and concussion (1%). IAD rapidly increased during the first year of life (mean growth velocity 0.064 to 0.213 mm/month) and then plateaued or slightly decreased between age one and 18 years (mean growth velocity -0.002 to 0.003 mm/month). Multivariable analysis shows strongest correlation with head circumference as a predictor of IAD. Weaker correlations are associated with weight and age. Height and sex are not well correlated with IAD. CONCLUSIONS Intracranial arteries grow rapidly during the first year of life and then sharply plateau or slightly decrease in luminal diameter between infancy and early adulthood. IAD is more closely correlated with head circumference than age.
Collapse
Affiliation(s)
- J Michael Taylor
- Division of Neurology, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio; University of Cincinnati, College of Medicine, Cincinnati, Ohio.
| | - Michael Chang
- Division of Ophthalmology, West Virginia University, School of Medicine, Morgantown, West Virginia
| | - Jessica Vaughan
- Division of Neurology, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio
| | - Paul S Horn
- Division of Neurology, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio; University of Cincinnati, College of Medicine, Cincinnati, Ohio; Division of Biostatistics and Epidemiology, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio
| | - Bin Zhang
- University of Cincinnati, College of Medicine, Cincinnati, Ohio; Division of Biostatistics and Epidemiology, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio
| | - James L Leach
- University of Cincinnati, College of Medicine, Cincinnati, Ohio; Department of Radiology, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio
| | - Sudhakar Vadivelu
- University of Cincinnati, College of Medicine, Cincinnati, Ohio; Department of Radiology, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio; Division of Neurosurgery, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio
| | - Todd Abruzzo
- Department of Radiology, Phoenix Children's Medical Group, Phoenix, Arizona; Mayo Clinic College of Medicine, Phoenix, Arizona; University of Arizona, College of Medicine, Phoenix, Arizona
| |
Collapse
|
4
|
Visualization of basilar artery atherosclerotic plaques by conventional T2-weighted magnetic resonance imaging: A case-control study. PLoS One 2019; 14:e0212570. [PMID: 30807597 PMCID: PMC6391016 DOI: 10.1371/journal.pone.0212570] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/22/2018] [Accepted: 02/05/2019] [Indexed: 11/19/2022] Open
Abstract
Objective In vivo visualization of intracranial atherosclerotic plaque has been performed only with high-resolution magnetic resonance imaging (HRMR). We investigated whether atherosclerotic plaque of the basilar artery (BA) can be identified in conventional magnetic resonance imaging (MRI). Methods Patients with acute ischemic stroke who had BA stenosis (“symptomatic BAA”) were retrospectively recruited using the prospective stroke registry. In the HRMR databank, subjects without BA stenosis were recruited and classified as those with silent plaque (“silent BAA”) and without any plaque (“normal controls”). Outer diameter of the BA and T2 plaque sign (an eccentric or complete obscuration of normal flow-void) within the BA were assessed by two blinded raters using conventional T2 MRI. Results Seventy-five patients with symptomatic BAA, 40 with asymptomatic BAA, and 36 normal controls were included in the study. Maximal BA diameter was significantly larger in symptomatic BAA patients with <30%, 30–50%, 50–70%, and >70% stenosis (all p<0.01 in each subgroup) and silent BAA subjects (p = 0.018) than controls. T2 plaque signs were present in 46 (61.3%) patients with symptomatic BAA and 6 (14.6%) subjects with asymptomatic BAA, while none in normal controls (p <0.001 and 0.057, respectively). Detection rates were increased with an increase in stenosis degree (25.0% in <30% stenosis, 57.9% in 30–50% stenosis, 38.5% in 50–70% stenosis, 92.3% in 70–99% stenosis, and 100.0% in occlusion). Conclusions Our data suggest that BA atherosclerosis can be detected by conventional MRI. When the use of HRMR is limited, conventional MR imaging may give additive information to clinicians.
Collapse
|
5
|
Park JH, Kim DH, Sung JM, Kim CW. A Case of Medullary Infarction Presented Initial Symptoms Similar to Meniere's Disease. J Audiol Otol 2017; 22:48-52. [PMID: 29036757 PMCID: PMC5784363 DOI: 10.7874/jao.2017.00143] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/07/2017] [Revised: 06/27/2017] [Accepted: 06/28/2017] [Indexed: 11/22/2022] Open
Abstract
Fluctuating hearing loss and vertigo are the typical presentations of Meniere’s disease. However, it is unusual that fluctuating hearing loss and vertigo are caused by vertebral artery occlusion or cerebral infarction. Here, we described the case of a 54-year-old male patient with hypertension and diabetes mellitus who presented with fluctuating hearing loss in his left ear and severe whirling-type dizziness without associated neurological signs or symptoms. Temporal magnetic resonance imaging (MRI) was normal. He was diagnosed with a possible Meniere’s disease and started conservative treatment. Eight years later, the patient developed dysarthria and left-side weakness. Brain MRI revealed right anterior medullary infarction, and cerebral angiography showed occlusion of the right vertebral artery. In this case, we attempted to review the initial imaging study and reported the characteristics of the case.
Collapse
Affiliation(s)
- Jang Hee Park
- Department of Otorhinolaryngology-Head and Neck Surgery, Hallym University College of Medicine, Seoul, Korea
| | - Dong Hyun Kim
- Department of Otorhinolaryngology-Head and Neck Surgery, Hallym University College of Medicine, Seoul, Korea
| | - Jae Moon Sung
- Department of Otorhinolaryngology-Head and Neck Surgery, Hallym University College of Medicine, Seoul, Korea
| | - Chang Woo Kim
- Department of Otorhinolaryngology-Head and Neck Surgery, Hallym University College of Medicine, Seoul, Korea
| |
Collapse
|
6
|
Adams LC, Böker SM, Bender YY, Fallenberg EM, Wagner M, Liebig T, Hamm B, Makowski MR. Detection of vessel wall calcifications in vertebral arteries using susceptibility weighted imaging. Neuroradiology 2017; 59:861-872. [PMID: 28730268 DOI: 10.1007/s00234-017-1878-z] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/13/2017] [Accepted: 06/30/2017] [Indexed: 01/01/2023]
Abstract
PURPOSE Calcification of the brain supplying arteries has been linked to an increased risk for cerebrovascular disease. The purpose of this study was to test the potential of susceptibility weighted MR imaging (SWMR) for the detection of vertebral artery calcifications, based on CT as a reference standard. METHODS Four hundred seventy-four patients, who had received head CT and 1.5 T MR scans with SWMR, including the distal vertebral artery, between January 2014 and December 2016, were retrospectively evaluated and 389 patients were included. Sensitivity and specificity for the detection of focal calcifications and intra- and interobserver agreement were calculated for SWMR and standard MRI, using CT as a standard of reference. The diameter of vertebral artery calcifications was used to assess correlations between imaging modalities. Furthermore, the degree of vessel stenosis was determined in 30 patients, who had received an additional angiography. RESULTS On CT scans, 40 patients showed a total of 52 vertebral artery calcifications. While SWMR reached a sensitivity of 94% (95% CI 84-99%) and a specificity of 97% (95% CI 94-98%), standard MRI yielded a sensitivity of 33% (95% CI 20-46%), and a specificity of 93% (95% CI 90-96%). Linear regression analysis of size measurements confirmed a close correlation between SWMR and CT measurements (R 2 = 0.74, p < 0.001). Compared to standard MRI (ICC = 0.52; CI 0.45-0.59), SWMR showed a higher interobserver agreement for calcification measurements (ICC = 0.84; CI 0.81-0.87). CONCLUSIONS For detection of distal vertebral artery calcifications, SWMR demonstrates a performance comparable to CT and considerably higher than conventional MRI.
Collapse
Affiliation(s)
- Lisa C Adams
- Department of Radiology, Charité, Charitéplatz 1, 10117, Berlin, Germany.
| | - Sarah M Böker
- Department of Radiology, Charité, Charitéplatz 1, 10117, Berlin, Germany
| | - Yvonne Y Bender
- Department of Radiology, Charité, Charitéplatz 1, 10117, Berlin, Germany
| | - Eva M Fallenberg
- Department of Radiology, Charité, Augustenburger Platz 1, 13353, Berlin, Germany
| | - Moritz Wagner
- Department of Radiology, Charité, Charitéplatz 1, 10117, Berlin, Germany
| | - Thomas Liebig
- Department of Neuroradiology, Charité, Charitéplatz 1, 10117, Berlin, Germany
| | - Bernd Hamm
- Department of Radiology, Charité, Charitéplatz 1, 10117, Berlin, Germany
| | - Marcus R Makowski
- Department of Radiology, Charité, Charitéplatz 1, 10117, Berlin, Germany
| |
Collapse
|
7
|
Liu Y, Jia L, Liu B, Meng X, Yang J, Li J, Zhou Y, Jiao L, Hua Y. Evaluation of Endarterectomy Recanalization under Ultrasound Guidance in Symptomatic Patients with Carotid Artery Occlusion. PLoS One 2015; 10:e0144381. [PMID: 26636827 PMCID: PMC4670099 DOI: 10.1371/journal.pone.0144381] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/31/2015] [Accepted: 11/17/2015] [Indexed: 11/18/2022] Open
Abstract
Rigorous screening and good imaging would help perform surgery on carotid artery occlusion CAO safely and effectively. The purpose of this study was to retrospectively evaluate carotid endarterectomy (CEA) recanalization in patients with common carotid artery occlusion (CCAO) or internal carotid artery occlusion (ICAO) with color Doppler flow imaging (CDFI). A total of 59 patients undergoing CEA were enrolled. According to the results of CEA, the patients were divided into successful recanalization (group A) and unsuccessful recanalization (group B) groups. The original diameter, lesion length, proximal-to-distal diameter ratio and echo characteristics of the lesion within the lumen of the carotid artery were recorded before CEA and compared between the two groups. In regards to the achievement of repatency by CEA, the overall success rate was 74.6% (44/59), the success rate in CCAO patients was 75.9% (22/29) and the success rate in ICAO patients was 73.3% (22/30). There was no significant difference in the success rates between the CCAO and ICAO patients (χ2 = 0.050, P = 0.824). The overall rate of stroke and death within 30 postoperative days was 5.1% (3/59). For the CCAO patients, the lesion length in group A was shorter than that in group B (t = 3.221, P = 0.004). For the ICAO patients, the original diameter of the distal ICA was broader (t = 6.254, P = 0.000) and the proximal-to-distal ICA diameter ratio was smaller (t = 8.036, P = 0.000) in group A than in group B. The rate of recanalization for lumens with a homogeneous echo pattern (hypoecho or isoecho) was significantly higher than that for lumens with echo heterogeneity for both the CCAO and ICAO patients (χ2 = 14.477, P = 0.001; χ2 = 10.519, P = 0.003). However, for both the CCAO and ICAO patients, there was no difference in the rate of recanalization between patients with hypoecho and isoecho lesions (χ2 = 0.109, P = 0.742; χ2 = 0.836, P = 0.429). The original diameter, proximal-to-distal ICA diameter ratio, lesion length and echo characteristics may affect the success of CEA recanalization in patients with CCAO and ICAO. CDFI is helpful in screening patients with carotid artery occlusion and may improve the success rate of CEA.
Collapse
Affiliation(s)
- Yumei Liu
- Department of Vascular Ultrasonography, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Lingyun Jia
- Department of Vascular Ultrasonography, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Beibei Liu
- Department of Vascular Ultrasonography, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Xiufeng Meng
- Department of Vascular Ultrasonography, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Jie Yang
- Department of Vascular Ultrasonography, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Jingzhi Li
- Department of Vascular Ultrasonography, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Yinghua Zhou
- Department of Vascular Ultrasonography, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Liqun Jiao
- Department of Neurosurgery, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Yang Hua
- Department of Vascular Ultrasonography, Xuanwu Hospital, Capital Medical University, Beijing, China
- * E-mail:
| |
Collapse
|