Prediction of Obliteration After the Gamma Knife Radiosurgery of Arteriovenous Malformations Using Hand-Crafted Radiomics and Deep-Learning Methods
- PMID: 38784357
- PMCID: PMC11114484
- DOI: 10.7759/cureus.58835
Prediction of Obliteration After the Gamma Knife Radiosurgery of Arteriovenous Malformations Using Hand-Crafted Radiomics and Deep-Learning Methods
Abstract
Introduction: Brain arteriovenous malformations (bAVMs) are vascular abnormalities that can be treated with embolization or radiotherapy to prevent the risk of future rupture. In this study, we use hand-crafted radiomics and deep learning techniques to predict favorable vs. unfavorable outcomes following Gamma Knife radiosurgery (GKRS) of bAVMs and compare their prediction performances.
Methods: One hundred twenty-six patients seen at one academic medical center for GKRS obliteration of bAVMs over 15 years were retrospectively reviewed. Forty-two patients met the inclusion criteria. Favorable outcomes were defined as complete nidus obliteration demonstrated on cerebral angiogram and asymptomatic recovery. Unfavorable outcomes were defined as incomplete obliteration or complications relating to the AVM that developed after GKRS. Outcome predictions were made using a random forest model with hand-crafted radiomic features and a fine-tuned ResNet-34 convolutional neural network (CNN) model. The performance was evaluated by using a ten-fold cross-validation technique.
Results: The average accuracy and area-under-curve (AUC) values of the Random Forest Classifier (RFC) with radiomics features were 68.5 ±9.80% and 0.705 ±0.086, whereas those of the ResNet-34 model were 60.0 ±11.9% and 0.694 ±0.124. Four radiomics features used with RFC discriminated unfavorable response cases from favorable response cases with statistical significance. When cropped images were used with ResNet-34, the accuracy and AUC decreased to 59.3 ± 14.2% and 55.4 ±10.4%, respectively.
Conclusions: A hand-crafted radiomics model and a pre-trained CNN model can be fine-tuned on pre-treatment MRI scans to predict clinical outcomes of AVM patients undergoing GKRS with equivalent prediction performance. The outcome predictions are promising but require further external validation on more patients.
Keywords: avm; convolutional neural network; gamma knife; predictive models; radiomics; radiosurgery.
Copyright © 2024, Wu et al.
Conflict of interest statement
The authors have declared that no competing interests exist.
Figures
![Figure 1](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/11114484/bin/cureus-0016-00000058835-i01.gif)
![Figure 2](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/11114484/bin/cureus-0016-00000058835-i02.gif)
![Figure 3](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/11114484/bin/cureus-0016-00000058835-i03.gif)
![Figure 4](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/11114484/bin/cureus-0016-00000058835-i04.gif)
![Figure 5](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/11114484/bin/cureus-0016-00000058835-i05.gif)
![Figure 6](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/11114484/bin/cureus-0016-00000058835-i06.gif)
Similar articles
-
Gamma Knife Radiosurgery in Partially Embolised Arteriovenous Malformations: Management Dilemmas and Outcomes.Neurol India. 2023 Mar-Apr;71(Supplement):S90-S99. doi: 10.4103/0028-3886.373655. Neurol India. 2023. PMID: 37026339
-
Long-term outcome of a tailored embolization strategy with Gamma Knife radiosurgery for high-grade brain arteriovenous malformations: a single-center experience.J Neurosurg. 2022 Dec 30;139(1):176-183. doi: 10.3171/2022.11.JNS221363. Print 2023 Jul 1. J Neurosurg. 2022. PMID: 36585868
-
Assessment of gamma knife radiosurgery for unruptured cerebral arterioveneus malformations based on multi-parameter radiomics of MRI.Magn Reson Imaging. 2022 Oct;92:251-259. doi: 10.1016/j.mri.2022.07.008. Epub 2022 Jul 20. Magn Reson Imaging. 2022. PMID: 35870722
-
Gamma Knife Radiosurgery of Arteriovenous Malformations: Long-Term Outcomes and Late Effects.Prog Neurol Surg. 2019;34:238-247. doi: 10.1159/000493070. Epub 2019 May 16. Prog Neurol Surg. 2019. PMID: 31096248 Review.
-
Seizure outcomes following radiosurgery for cerebral arteriovenous malformations.Neurosurg Focus. 2014 Sep;37(3):E17. doi: 10.3171/2014.6.FOCUS1454. Neurosurg Focus. 2014. PMID: 25175436 Review.
References
-
- Bokhari MR, Bokhari SRA. StatPearls. Treasure Island, FL: StatPearls Publishing; 2023. Arteriovenous malformation of the brain. - PubMed
-
- Endovascular treatment of arteriovenous malformations. Diaz O, Scranton R. Handb Clin Neurol. 2016;136:1311–1317. - PubMed
-
- Long-term excess mortality in 623 patients with brain arteriovenous malformations. Laakso A, Dashti R, Seppänen J, et al. Neurosurgery. 2008;63:244–255. - PubMed
-
- Intervening nidal brain parenchyma and risk of radiation-induced changes after radiosurgery for brain arteriovenous malformation: A study using an unsupervised machine learning algorithm. Lee CC, Yang HC, Lin CJ, et al. World Neurosurg. 2019;125:0–8. - PubMed
-
- Gamma knife radiosurgery for arteriovenous malformations: Long-term follow-up results focusing on complications occurring more than 5 years after irradiation. Yamamoto M, Jimbo M, Hara M, Saito I, Mori K. https://journals.lww.com/neurosurgery/abstract/1996/05000/gamma_knife_ra.... Neurosurgery. 1996;38:906–914. - PubMed
LinkOut - more resources
Full Text Sources
Miscellaneous