Assessment of gamma knife radiosurgery for unruptured cerebral arterioveneus malformations based on multi-parameter radiomics of MRI

Gao, Dingshan; Meng, Xiangyu; Jin, Hengwei; Liu, Ali; Sun, Shibin

doi:10.1016/j.mri.2022.07.008

Cited by 6 publications

(6 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Comparing our results with other studies, we achieved a post-treatment AVM control rate of 59.5%. This result aligns with other studies, such as the 63.6% success rate of the Gao et al study [ 16 ], which did linear accelerator-based AVM radiosurgery, as well as the 58% obliteration rate for medium volume sizes, 4-13.9 cm 3 found in Miyawaki et al’s study [ 6 ]. However, some groups had higher success rates, indicating obliteration rates as high as 79% [ 26 ].…”

Section: Discussionsupporting

confidence: 91%

“…They found that their selected predictive features resulted in a better performance than the standard parameters of SM, BRAS, and VRAS, demonstrating the importance of well-selected hand-crafted features for outcome predictions of AVM after radiosurgery. Recently, Gao et al used radiomics for outcome predictions of AVM treated by GKRS using the data of 88 patients [ 16 ]. Their study used only the random forest model and did not use deep learning tools and achieved an impressive AUC of 0.88 using 12 selected radiomics features.…”

Section: Discussionmentioning

confidence: 99%

“…They found that their selected predictive features resulted in a better performance than the standard parameters of SM, BRAS, and VRAS, demonstrating the importance of well-selected hand-crafted features for outcome predictions of AVM after radiosurgery. Recently, [16], which did linear accelerator-based AVM radiosurgery, as well as the 58% obliteration rate for medium volume sizes, 4-13.9 cm 3 found in Miyawaki et al's study [6]. However, some groups had higher success rates, indicating obliteration rates as high as 79% [26].…”

Section: Radiomics Modelmentioning

confidence: 93%

“…Radiological images can be used as biomarkers in addition to standard clinical prognostic factors to improve the outcome prediction performance for SRS of bAVM. Radiomics using hand-crafted features has been used to build outcome prediction models of bAVM SRS by several groups [12,[14][15][16]. However, deep learning approaches have not been used previously as a prediction model for this disease type.…”

Section: Introductionmentioning

confidence: 99%

“…Gao et al used radiomics for outcome predictions of AVM treated by GKRS using the data of 88 patients[16]. Their study used only the random forest model and did not use deep learning tools and achieved an impressive AUC of 0.88 using 12 selected radiomics features.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Prediction of Obliteration After the Gamma Knife Radiosurgery of Arteriovenous Malformations Using Hand-Crafted Radiomics and Deep-Learning Methods

Wu,

Kollitz,

Ward

et al. 2024

Cureus

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionsupporting

confidence: 91%

Section: Discussionmentioning

confidence: 99%

“…They found that their selected predictive features resulted in a better performance than the standard parameters of SM, BRAS, and VRAS, demonstrating the importance of well-selected hand-crafted features for outcome predictions of AVM after radiosurgery. Recently, [16], which did linear accelerator-based AVM radiosurgery, as well as the 58% obliteration rate for medium volume sizes, 4-13.9 cm 3 found in Miyawaki et al's study [6]. However, some groups had higher success rates, indicating obliteration rates as high as 79% [26].…”

Section: Radiomics Modelmentioning

confidence: 93%