Dataset Information

A deep-learning system to help make the surgical planning of coil embolization for unruptured intracranial aneurysms.

ABSTRACT:

Background

Coil embolization is a common method for treating unruptured intracranial aneurysms (UIAs). To effectively perform coil embolization for UIAs, clinicians must undergo extensive training with the assistance of senior physicians over an extended period. This study aimed to establish a deep-learning system for measuring the morphological features of UIAs and help the surgical planning of coil embolization for UIAs.

Methods

Preoperative computational tomography angiography (CTA) data and surgical data from UIA patients receiving coil embolization in our medical institution were retrospectively reviewed. A convolutional neural network (CNN) model was trained on the preoperative CTA data, and the morphological features of UIAs were measured automatically using this CNN model. The intraclass correlation coefficient (ICC) was utilized to examine the similarity between the morphologies measured by the CNN model and those determined by experienced clinicians. A deep neural network model to determine the diameter of first coil was further established based on the CNN model within the derivation set (75% of all patients) using neural factorization machines (NFM) model and was validated using a validation set (25% of all patients). The general match ratio (the difference was within ± 1 mm) between the predicted diameter of first coil by model and that used in practical scenario was calculated.

Results

One-hundred fifty-three UIA patients were enrolled in this study. The CNN model could diagnose UIAs with an accuracy of 0.97. The performance of this CNN model in measuring the morphological features of UIAs (i.e., size, height, neck diameter, dome diameter, and volume) was comparable to the accuracy of senior clinicians (all ICC > 0.85). The diameter of first coil predicted by the model established based on CNN model and the diameter of first coil used actually exhibited a high general match ratio (0.90) within the derivation set. Moreover, the model performed well in recommending the diameter of first coil within the validation set (general match ratio as 0.91).

Conclusion

This study presents a deep-learning system which can help to improve surgical planning of coil embolization for UIAs.

SUBMITTER: Nie X

PROVIDER: S-EPMC10494453 | biostudies-literature | 2023 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A deep-learning system to help make the surgical planning of coil embolization for unruptured intracranial aneurysms.

Nie Xin X Yang Yi Y Liu Qingyuan Q Wu Jun J Chen Jingang J Ma Xuesheng X Liu Weiqi W Wang Shuo S Chen Lei L He Hongwei H

Chinese neurosurgical journal 20230911 1

<h4>Background</h4>Coil embolization is a common method for treating unruptured intracranial aneurysms (UIAs). To effectively perform coil embolization for UIAs, clinicians must undergo extensive training with the assistance of senior physicians over an extended period. This study aimed to establish a deep-learning system for measuring the morphological features of UIAs and help the surgical planning of coil embolization for UIAs.<h4>Methods</h4>Preoperative computational tomography angiography ...[more]

PMID: 37691095

Similar Datasets

Project description:ObjectivePeriprocedural thromboembolic events are a serious complication associated with coil embolization of unruptured intracranial aneurysms. However, no established clinical rule for predicting thromboembolic events exists. This study aimed to clarify the significance of adding preoperative clopidogrel response value to clinical factors when predicting the occurrence of thromboembolic events during/after coil embolization and to develop a nomogram for thromboembolic event prediction.MethodsIn this prospective, single-center, cohort study, we included 345 patients undergoing elective coil embolization for unruptured intracranial aneurysm. Thromboembolic event was defined as the occurrence of intra-procedural thrombus formation and postprocedural symptomatic cerebral infarction within 7 days. We evaluated preoperative clopidogrel response and patients' clinical information. We developed a patient-clinical-information model for thromboembolic event using multivariate analysis and compared its efficiency with that of patient-clinical-information plus preoperative clopidogrel response model. The predictive performances of the two models were assessed using area under the receiver-operating characteristic curve (AUC-ROC) with bootstrap method and compared using net reclassification improvement (NRI) and integrated discrimination improvement (IDI).ResultsTwenty-eight patients experienced thromboembolic events. The clinical model included age, aneurysm location, aneurysm dome and neck size, and treatment technique. AUC-ROC for the clinical model improved from 0.707 to 0.779 after adding the clopidogrel response value. Significant intergroup differences were noted in NRI (0.617, 95% CI: 0.247-0.987, p < .001) and IDI (0.068, 95% CI: 0.021-0.116, p = .005).ConclusionsEvaluation of preoperative clopidogrel response in addition to clinical variables improves the prediction accuracy of thromboembolic event occurrence during/after coil embolization of unruptured intracranial aneurysm.

Project description:Background and purposeThis study arose from a need to systematically evaluate the clinical and angiographic outcomes of intracranial aneurysms treated with modified coils. We report the procedural safety and clinical outcomes in a prospective randomized controlled trial of endovascular coiling for ruptured and unruptured intracranial aneurysms, comparing polymer-loaded Cerecyte coils with bare platinum coils in 23 centers worldwide.Materials and methodsFive hundred patients between 18 and 70 years of age with a ruptured or unruptured target aneurysm planning to undergo endovascular coiling were randomized to receive Cerecyte or bare platinum coils. Analysis was by intention to treat.ResultsTwo hundred forty-nine patients were allocated to Cerecyte coils and 251 to bare platinum coils. Baseline characteristics were balanced. For ruptured aneurysms, in-hospital mortality was 2/114 (1.8%) with Cerecyte versus 0/119 (0%) bare platinum coils. There were 8 (3.4%) adverse procedural events resulting in neurological deterioration: 5/114 (4.4%) with Cerecyte versus 3/119 (2.5%) with bare platinum coils (P = .22). The 6-month mRS score of ≤2 was not significantly different in 103/109 (94.5%) patients with Cerecyte and 110/112 (98.2%) patients with bare platinum coils. Poor outcome (mRS score of ≥3 or death) was 6/109 (5.5%) with Cerecyte versus 2/112 (1.8%) with bare platinum coils (P = .070). For UIAs, there was no in-hospital mortality. There were 7 (2.7%) adverse procedural events with neurological deterioration, 5/133 (3.8%) with Cerecyte versus 2/131 (1.5%) with bare platinum coils (P = .13). There was a 6-month mRS score of ≤2 in 114/119 (95.8%) patients with Cerecyte versus 123/123 (100%) patients with bare platinum coils. There was poor outcome (mRS ≥3 and 1 death) in 5/119 (4.2%) patients with Cerecyte versus 0/123 (0%) patients with bare platinum coils (P = .011).ConclusionsThere was a statistical excess of poor outcomes in the Cerecyte arm at discharge in the ruptured aneurysm group and at 6-month follow-up in the unruptured group. Overall adverse clinical outcomes and in-hospital mortality were exceptionally low in both groups.

Project description:ObjectivesArterial calcification is thought to protect against rupture of intracranial aneurysms, but studies in a representative population of intracranial aneurysm patients have not yet been performed. The aim was to compare the prevalence of aneurysm wall calcification and intracranial carotid artery calcification (ICAC) between patients with an unruptured intracranial aneurysm (UIA) and a ruptured intracranial aneurysm (RIA).Materials and methodsWe matched 150 consecutive UIA patients to 150 RIA patients on age and sex. Aneurysm wall calcification and ICAC were quantified on non-contrast enhanced computed tomography images with the modified Agatston score. We compared the prevalence of aneurysm wall calcification, ICAC, and severe ICAC (defined as a modified Agatston score in the fourth quartile) between UIA and RIA patients using univariate and multivariate conditional logistic regression models adjusted for aneurysm characteristics and cardiovascular risk factors.ResultsAneurysm wall calcification was more prevalent in UIA compared to RIA patients (OR 5.2, 95% CI: 2.0-13.8), which persisted after adjustment (OR 5.9, 95% CI: 1.7-20.2). ICAC prevalence did not differ between the two groups (crude OR 0.9, 95% CI: 0.5-1.8). Severe ICAC was more prevalent in UIA patients (OR 2.0, 95% CI: 1.1-3.6), but not after adjustment (OR 1.0, 95% CI: 0.5-2.3).ConclusionsAneurysm wall calcification but not ICAC was more prevalent in UIAs than in RIAs, which corresponds to the hypothesis that calcification may protect against aneurysmal rupture. Aneurysm wall calcification should be further assessed as a predictor of aneurysm stability in prospective cohort studies.Clinical relevance statementCalcification of the intracranial aneurysm wall was more prevalent in unruptured than ruptured intracranial aneurysms after adjustment for cardiovascular risk factors. Calcification may therefore protect the aneurysm against rupture, and aneurysm wall calcification is a candidate predictor of aneurysm stability.Key pointsAneurysm wall calcification was more prevalent in patients with unruptured than ruptured aneurysms, while internal carotid artery calcification was similar. Aneurysm wall calcification but not internal carotid artery calcification is a candidate predictor of aneurysm stability. Cohort studies are needed to assess the predictive value of aneurysm wall calcification for aneurysm stability.

Dataset Information

A deep-learning system to help make the surgical planning of coil embolization for unruptured intracranial aneurysms.

Background

Methods

Results

Conclusion

Publications

A deep-learning system to help make the surgical planning of coil embolization for unruptured intracranial aneurysms.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets