Acute infarct segmentation on diffusion-weighted image using deep learning algorithm and RAPID DWI: a comprehensive stroke center clinical validation study

Ryu, Wi‐Sun; Kang, You-Ri; Noh, Yoon-Gon; Park, Jong-Hyeok; Kim, Dong-Min; Kim, Byeong C.; Park, Man‐Seok; Kim, Beom Joon; Kim, Joon‐Tae

doi:10.1101/2023.02.20.23286140

Cited by 3 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Areas of infarction were automatically segmented using a validated deep learning algorithm (JBS-01K, JLK Inc., Seoul, Korea). 19 Automatically segmented infarct areas underwent visual inspection by a stroke neurologist (W-S. Ryu) and were manually corrected as necessary.…”

Section: Early Follow-up Infarct Volume Measurementmentioning

confidence: 99%

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

Kim,

Ha,

Park

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Background: The analysis of computed tomography perfusion (CTP) scans plays a pivotal role in the diagnosis and management of acute ischemic stroke, aiding in extending the treatment window for endovascular therapy (EVT). This study aims to compare the ischemic core and hypoperfused tissue volumes estimated by JBS-10K, a newly developed automated CTP analysis packages, and RAPID. Method: This retrospective study analyzed data from 327 patients admitted to a single stroke center in Korea from January 2021 to May 2023, who underwent CTP scans within 24 hours of symptom onset. The concordance correlation coefficient and Bland-Altman plots were utilized to compare ischemic core volumes and hypoperfused lesion volumes between the software packages. Agreement with early (within 3 hours from CTP) follow-up infarct volumes on diffusion-weighted imaging (DWI, n = 217) was also evaluated. Results: The mean age was 70.7 (SD 13.0) and 137 (41.9%) were female. Ischemic core volumes by JBS-10K and RAPID in the threshold of relative cerebral blood flow (rCBF) < 30% had excellent agreement (ρ = 0.845 [95% CI, 0.811 to 0.874]). Excellent agreement was observed for time to maximum of the residue function (Tmax) > 6 seconds between JBS-10K and RAPID (ρ = 0.835 [95% CI, 0.806 to 0.863]). Although early follow-up infarct volume showed substantial agreement in both packages (JBS-10K ρ = 0.751 and RAPID ρ = 0.632), ischemic core volumes at the threshold of rCBF <30% tended to overestimate ischemic core volumes. Conclusion: CTP analysis using JBS-10K and RAPID demonstrated excellent agreement each other in patients undergoing CTP within 24 hours of symptom onset.

show abstract

Section: Early Follow-up Infarct Volume Measurementmentioning

confidence: 99%

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

Kim,

Ha,

Park

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Infarct volumes on DWI were calculated using a validated software package (JLK-DWI, JLK Inc., Seoul, Korea). 16,17 Segmented infarct area was meticulously supervised by an experienced vascular neurologist (W-S. Ryu).…”

Section: Image Analysismentioning

confidence: 99%

Automated detection of large vessel occlusion: a multicenter study validating efficacy and proving clinical implications

Yum,

Chung,

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Objective: We aimed to validate a software, JLK LVO, that automatically detects large vessel occlusion (LVO) on computed tomography angiography (CTA) using deep learning, within a prospective multicenter dataset. In addition, we calibrated the predicted probability of LVO against observed frequency and assessed the clinical implications of LVO probability in terms of follow up infarct volume and functional outcome. Method: From 2021 to 2023, we prospectively collected data from patients who underwent CTA within 24 hours of symptom onset at six university hospitals in Korea. The diagnostic performance of the software was evaluated using the area under the curve (AUC), sensitivity, and specificity across the entire study population and specifically in patients with isolated middle cerebral artery (MCA) M2 occlusion. In addition, we compared LVO probabilities after stratifying patient into acute LVO, chronic LVO, isolated MCA M2 occlusion, relevant MCA stenosis, and without stenoocclusion of MCA groups. We calibrated LVO probabilities in two ways: through mathematical calibration using logistic regression, and by refining LVO probabilities based on the observed frequency of LVO. We then assessed the association of LVO probability categories with infarct volume on follow up diffusion weighted imaging (DWI) and modified Rankin Scale (mRS) scores three months poststroke, using ANOVA and the Cochran Armitage test. Results: After excluding 168 patients, 796 remained; the mean (SD) age was 68.9 (13.7) years, and 57.7% were men. LVO was present in 193 (24.3%) of these patients, and the median interval from last known well to CTA was 5.7 hours (IQR 2.5 to 12.1 hours). At default threshold of 0.5, the software achieved an AUC of 0.944 (95% CI 0.926 to 0.960), with a sensitivity of 0.896 (0.845 to 0.936) and a specificity of 0.904 (0.877 to 0.926). In isolated MCA M2 occlusion, the AUROC was 0.880 (95% CI 0.824 to 0.921). Compared to the without stenoocclusion of MCA groups (median LVO probability 0.5, interquartile range 0.1 to 6.5), relevant stenosis (median 15.3, 2.4 to 77.4) and isolated MCA M2 occlusion (82.1, 40.9 to 98.2) groups had significantly higher LVO probability. Due to sparse data between 20 to 60% of LVO probabilities, recategorization into unlikely (0 to 20% LVO scores), less likely (20 to 60%), possible (60 to 90%), and suggestive (90 to 100%) provided a reliable estimation of LVO compared with mathematical calibration. The category of LVO probabilities was significantly associated with follow up infarct volumes on DWI and 3 months mRS scores. Conclusion: In this multicenter validation study, we proved the clinical efficacy of the software in detecting LVO on CTA. Additionally, using large scale real world data, we calibrated the LVO probabilities, which may provide a more confident estimation of LVO for practicing physicians.

show abstract

“…Infarct volumes on DWI were calculated using a validated software package (JLK-DWI, JLK Inc., Seoul, Korea). [13][14][15] The segmentation of the infarct area was carefully overseen by an experienced vascular neurologist (J-W. C). In cases where automated segmentation was inaccurate, manual corrections were applied to ensure precise segmentation.…”

Section: Follow-up Imaging Analysismentioning

confidence: 99%

Multicenter validation of artificial intelligence software predicting large vessel occlusion using noncontrast brain CT

Chung,

Lee,

et al. 2024

Preprint

View full text Add to dashboard Cite

Background: To validate JLK-CTL, an artificial intelligence (AI) software developed to predict large vessel occlusion (LVO) using non-contrast CT (NCCT) scans, and to investigate its clinical implications regarding both infarct volume and functional outcomes. Methods: Between January-2021 and April-2023, a consecutive series of patients who concurrently underwent CT angiography and NCCT within 24 hours of last-known-well (LKW) were collected. LVO was confirmed through consensus among three experts reviewing CT angiography. Infarct volumes were quantified using diffusion-weighted imaging (DWI) conducted within seven days of the NCCT. The performance of the JLK-CTL was evaluated based on the area under the receiver operating characteristic curve (AUROC), as well as its sensitivity and specificity. The association of JLK-CTL LVO scores with infarct volumes and functional outcomes was assessed using Pearson correlation and logistic regression analyses, respectively. Results: Of 1,391 screened patients, 774 (mean age 69.0 ± 13.6 years, 57.6% men) were included. The median time from LKW to NCCT was 3.1 hours (IQR 1.5-7.4), with 24.2% (n=187) presenting LVO. The JLK-CTL demonstrated AUROC of 0.832 (95% CI 0.804-0.858), with a sensitivity of 0.711 (95% CI 0.641-0.775) and a specificity of 0.830 (95% CI 0.797-0.859) at the predefined threshold. Incorporating the National Institute of Health Stroke Scale into the model increased the AUROC to 0.872 (95% CI 0.846-0.894; p<0.001). The LVO scores showed a significant correlation with infarct volumes on follow-up DWI (r=0.53; p<0.001). When JLK-CTL LVO scores were categorized based on observed frequency of LVO, the highest JLK-CTL LVO scores (51-100) group showed an independent association with unfavorable functional outcomes (adjusted odds ratio 9.48; 95% CI 3.98-22.55). Conclusion: The performance of the AI software in predicting LVO was validated across multiple centers. This tool has the potential to assist physicians in optimizing stroke management workflows, especially in resource-limited settings.

show abstract

Acute infarct segmentation on diffusion-weighted image using deep learning algorithm and RAPID DWI: a comprehensive stroke center clinical validation study

Cited by 3 publications

References 30 publications

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

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

Automated detection of large vessel occlusion: a multicenter study validating efficacy and proving clinical implications

Multicenter validation of artificial intelligence software predicting large vessel occlusion using noncontrast brain CT

Contact Info

Product

Resources

About