Automated detection of large vessel occlusion using deep learning: a pivotal multicenter study and reader performance study.

BACKGROUND: To evaluate the stand-alone efficacy and improvements in diagnostic accuracy of early-career physicians of the artificial intelligence (AI) software to detect large vessel occlusion (LVO) in CT angiography (CTA). METHODS: This multicenter study included 595 ischemic stroke patients from January 2021 to September 2023. Standard references and LVO locations were determined by consensus among three experts. The efficacy of the AI software was benchmarked against standard references, and its impact on the diagnostic accuracy of four residents involved in stroke care was assessed. The area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity of the software and readers with versus without AI assistance were calculated. RESULTS: Among the 595 patients (mean age 68.5±13.4 years, 56% male), 275 (46.2%) had LVO. The median time interval from the last known well time to the CTA was 46.0 hours (IQR 11.8-64.4). For LVO detection, the software demonstrated a sensitivity of 0.858 (95% CI 0.811 to 0.897) and a specificity of 0.969 (95% CI 0.943 to 0.985). In subjects whose symptom onset to imaging was within 24 hours (n=195), the software exhibited an AUROC of 0.973 (95% CI 0.939 to 0.991), a sensitivity of 0.890 (95% CI 0.817 to 0.936), and a specificity of 0.965 (95% CI 0.902 to 0.991). Reading with AI assistance improved sensitivity by 4.0% (2.17 to 5.84%) and AUROC by 0.024 (0.015 to 0.033) (all P<0.001) compared with readings without AI assistance. CONCLUSIONS: The AI software demonstrated a high detection rate for LVO. In addition, the software improved diagnostic accuracy of early-career physicians in detecting LVO, streamlining stroke workflow in the emergency room.

Automated identification of thrombectomy amenable vessel occlusion on computed tomography angiography using deep learning.

Introduction: We developed and externally validated a fully automated algorithm using deep learning to detect large vessel occlusion (LVO) in computed tomography angiography (CTA). Method: A total of 2,045 patients with acute ischemic stroke who underwent CTA were included in the development of our model. We validated the algorithm using two separate external datasets: one with 64 patients (external 1) and another with 313 patients (external 2), with ischemic stroke. In the context of current clinical practice, thrombectomy amenable vessel occlusion (TAVO) was defined as an occlusion in the intracranial internal carotid artery (ICA), or in the M1 or M2 segment of the middle cerebral artery (MCA). We employed the U-Net for vessel segmentation on the maximum intensity projection images, followed by the application of the EfficientNetV2 to predict TAVO. The algorithm's diagnostic performance was evaluated by calculating the area under the receiver operating characteristics curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Results: The mean age in the training and validation dataset was 68.7 ± 12.6; 56.3% of participants were men, and 18.0% had TAVO. The algorithm achieved AUC of 0.950 (95% CI, 0.915-0.971) in the internal test. For the external datasets 1 and 2, the AUCs were 0.970 (0.897-0.997) and 0.971 (0.924-0.990), respectively. With a fixed sensitivity of 0.900, the specificities and PPVs for the internal test, external test 1, and external test 2 were 0.891, 0.796, and 0.930, and 0.665, 0.583, and 0.667, respectively. The algorithm demonstrated a sensitivity and specificity of approximately 0.95 in both internal and external datasets, specifically for cases involving intracranial ICA or M1-MCA occlusion. However, the diagnostic performance was somewhat reduced for isolated M2-MCA occlusion; the AUC for the internal and combined external datasets were 0.903 (0.812-0.944) and 0.916 (0.816-0.963), respectively. Conclusion: We developed and externally validated a fully automated algorithm that identifies TAVO. Further research is needed to evaluate its effectiveness in real-world clinical settings. This validated algorithm has the potential to assist early-career physicians, thereby streamlining the treatment process for patients who can benefit from endovascular treatment.

Comparison of two automated CT perfusion software packages in patients with ischemic stroke presenting within 24 h of onset.

Background: We compared the ischemic core and hypoperfused tissue volumes estimated by RAPID and JLK-CTP, a newly developed automated computed tomography perfusion (CTP) analysis package. We also assessed agreement between ischemic core volumes by two software packages against early follow-up infarct volumes on diffusion-weighted images (DWI). Methods: This retrospective study analyzed 327 patients admitted to a single stroke center in Korea from January 2021 to May 2023, who underwent CTP scans within 24 h of onset. The concordance correlation coefficient (ρ) and Bland-Altman plots were utilized to compare the volumes of ischemic core and hypoperfused tissue volumes between the software packages. Agreement with early (within 3 h from CTP) follow-up infarct volumes on diffusion-weighted imaging (n = 217) was also evaluated. Results: The mean age was 70.7 ± 13.0 and 137 (41.9%) were female. Ischemic core volumes by JLK-CTP and RAPID at the threshold of relative cerebral blood flow (rCBF) < 30% showed excellent agreement (ρ = 0.958 [95% CI, 0.949 to 0.966]). Excellent agreement was also observed for time to a maximum of the residue function (T max) > 6 s between JLK-CTP and RAPID (ρ = 0.835 [95% CI, 0.806 to 0.863]). Although early follow-up infarct volume showed substantial agreement in both packages (JLK-CTP, ρ = 0.751 and RAPID, ρ = 0.632), ischemic core volumes at the threshold of rCBF <30% tended to overestimate ischemic core volumes. Conclusion: JLK-CTP and RAPID demonstrated remarkable concordance in estimating the volumes of the ischemic core and hypoperfused area based on CTP within 24 h from onset.

Age-Related Variations in Patterns of Patent Foramen Ovale-Stroke versus Other Cryptogenic Stroke.

INTRODUCTION: Patent foramen ovale (PFO)-stroke, a form of cryptogenic stroke, has certain identifying clinical and imaging features. However, data describing this stroke type remain inconsistent. This study examined the potential variations in PFO-stroke features, depending on age. METHODS: From a hospital registry, cryptogenic stroke patients were retrospectively selected, and PFO-strokes were identified by the presence of >10 microembolic signals on transcranial Doppler saline agitation test. Cryptogenic strokes were grouped according to age (<70 as young, ≥70 as elderly). Clinical and imaging variables of PFO-strokes and non-PFO-strokes were compared, with and without age considered. RESULTS: Of the 462 cryptogenic patients, 30.5% (141/462) were PFO-strokes, while majority (321/462) had no PFO. When cryptogenic strokes were analyzed by age, the significant difference was noted in the lesion number, pattern, and side. A single (72.8 vs. 57.9%, p = 0.020) and a small single lesion (51.1 vs. 35.5%, p = 0.039) were frequently seen in the younger PFO-strokes than the non-PFO counterpart, while mixed territory lesions identified the elderly PFO-strokes (30.6 vs. 8.9%, p = 0.001). A multivariate logistic regression analysis of PFO-strokes further showed that age was independently associated with lesion side (OR 1.12 [1.05-1.20], p < 0.001) and lesion number (OR 1.06 [1.02-1.10], p = 0.005). CONCLUSIONS: Incorporating age-specific imaging criteria in the identification of PFO-strokes may be of additional value. Further, PFO may remain contributory to the stroke risk in the elderly, in association with vascular risk factors.

Cerebral small vessel disease as imaging biomarker predicting ocular cranial nerve palsy of presumed ischemic origin at admission.

Ocular cranial nerve palsy of presumed ischemic origin (OCNPi) is the most common type of ocular cranial nerve palsy (OCNP) in patients aged ≥ 50 years; however, no definite diagnostic test exists. As diagnostic criteria include clinical improvement, diagnoses are often delayed. Diagnostic biomarkers for OCNPi are required; we hypothesized that cerebral small vessel disease is associated with OCNPi. We analyzed 646 consecutive patients aged ≥ 50 years with isolated unilateral OCNP who underwent work-ups at two referral hospitals. White matter hyperintensities (WMHs), silent infarctions, and cerebral microbleeds (CMBs) were assessed. In multivariate analyses, mild (grades 1-3) and moderate to severe (grades 4-6) WMHs were significantly associated with OCNPi compared to OCNP of other origins (odds ratio [OR] 3.51, 95% confidence interval [CI] 1.91-6.43, P < 0.001; OR 3.47, 95% CI 1.42-8.48, P = 0.006, respectively). Silent infarction and CMBs did not remain associated (OR 0.96, 95% CI 0.54-1.70, P = 0.870; OR 0.55, 95% CI 0.28-1.08, P = 0.080, respectively). Associations between WMH and OCNPi remained after excluding patients with vascular risk factors. In conclusion, the presence of WMH could independently predict ischemic origin in patients with isolated unilateral OCNP at early stage of admission.

Current status and role of antiphospholipid antibody testing in cryptogenic stroke.

BACKGROUND AND PURPOSE: Although it is not recognized as essential to test for antiphospholipid antibody (aPL) in stroke of unknown cause, aPL-related stroke may account for a considerable number of cryptogenic strokes. We aimed to assess the current status and diagnostic value of aPL testing in cryptogenic stroke patients. METHODS: Consecutive patients admitted with acute ischemic stroke were examined to confirm the factors associated with performing aPL testing and with positive aPL test results in real-world practice. Cryptogenic stroke patients were separately examined in the same manner. The antibody profiles of cryptogenic stroke patients with aPL positivity were compared by age. RESULTS: Among 2947 patients, 606 (20.6%) were tested for aPLs and 129 (21.3%) were positive. Physicians tended to perform aPL testing in patients aged <50 years and in cryptogenic stroke patients. Cryptogenic stroke was a strong predictor of positive aPL results (adjusted odds ratio 3.70, 95% confidence interval 2.38-5.76). However, aPL positivity did not differ by age in stroke patients. Among 283 cryptogenic stroke patients, 136 (48.1%) were tested for aPLs and 56 (41.2%) were positive. aPL tests were performed predominantly in patients aged <50 years rather than in older patients, even among cryptogenic stroke patients. The two age groups had similar positivity rates of >40% (<50 years: 43.2%; ≥50 years: 40.4%; p = 0.92) and their antibody profiles were similar. CONCLUSIONS: A significant number of patients with cryptogenic stroke had positive aPL results regardless of age. aPL testing may offer additional diagnostic opportunities in cryptogenic stroke patients, and thus may reduce the incidence of cryptogenic stroke.

Drinking Patterns and Risk of Ischemic Stroke in Middle-Aged Adults: Do Beneficial Drinking Habits Indeed Exist?

BACKGROUND AND PURPOSE: Although it has been reported that the amount of alcohol consumption has a J-shaped association with ischemic stroke, it is unclear whether differences in drinking patterns affect this relationship. We aimed to clarify the impact of drinking patterns on ischemic stroke in midlife. METHODS: We used data from the National Health Insurance Service-National Sample Cohort, which is a large-sized, standardized population cohort in Korea. Five different drinking patterns were defined by combining the frequency of alcohol consumption and quantity of alcohol consumed per occasion, that is, abstainers, not drinking alcohol; drinker group I, ≤30 g/d and <5 d/wk; drinker group II, ≤30 g/d and ≥5 d/wk; drinker group III, >30 g/d and <5 d/wk; and drinker group IV, >30 g/d and ≥5 d/wk. The association between the drinking patterns and ischemic stroke occurrence was analyzed using the Cox proportional hazard model. RESULTS: A total of 152 469 middle-aged participants (mean age, 50.2 years; 72 285 men [47.4%]) were eligible for the analyses. The median follow-up time was 9.0 years. Compared with abstainers, those who drank <5 d/wk (drinker groups I and III) had a significantly lower risk of ischemic stroke (group I hazard ratio, 0.71 [95% CI, 0.59-0.85]; group III hazard ratio, 0.80 [95% CI, 0.68-0.93]) during the first 7 years from the baseline, while other drinker groups showed no such differences. However, the effect of drinking patterns on ischemic stroke risk was attenuated after the first 7 years. CONCLUSIONS: Reduced risk of ischemic stroke was observed in middle-aged participants with specific drinking patterns, but it was limited to the earlier period. Physicians should be cautious in educating patients on alcohol consumption, considering the long-term association between drinking patterns and ischemic stroke.

Highly unstable cervical spine injury in an infant: a case report.

UNLABELLED: Although the rate of surgical intervention for pediatric cervical spine injuries has risen, none of these instrumentation techniques has been reported in children less than 1 year of age. Additional consideration with placement of wires or cables is not safe because of the presence of cartilaginous bone and poor bone strength. The authors report a technique of internal fixation without fusion using nonabsorbable synthetic suture in an infant with unstable cervical injury. METHODS: A 5-month-old girl was transported to emergency department and computed tomography showed severe distraction injury at the C6-7 level with total disruption of the facet joints bilaterally. To improve her general condition, she was placed in a customized occipito-cervical brace until surgical stabilization could be performed. After 1 month, surgical fixation was performed. After removing all soft tissues at the appropriate level, a hole was made in the center of the superior articular process of C6. A nonabsorbable suture (2-0 Ethibond; Ethicon, Somerville, NJ, USA) was passed from the superior articular process to the facet joint. The suture was passed into the spinous process of the lower level, and it was progressively tightened and radiographs were taken until anatomic reduction was achieved. RESULTS: After surgery, solid fusion was achieved. She was able to sit up in a stroller after 6 months. CONCLUSION: As surgical treatment of pediatric cervical spine injuries is unsuitable for infants, the Ethibond sutures are strong enough to hold and stabilize the spine. This suturing technique can be used as an alternative treatment for cervical injury in infants.