Deep Shape Features for Predicting Future Intracranial Aneurysm Growth

Bizjak, Žiga; Pernuš, Franjo; Špiclin, Žiga

doi:10.3389/fphys.2021.644349

Cited by 14 publications

(13 citation statements)

References 28 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our proposed method did not perform as well as the method using PointNet++ put forward by Bizjak [37] (accuracy = 82%). This may be for a variety of reasons.…”

Section: Discussioncontrasting

confidence: 61%

“…Based on such morphological parameters, as well as classical parameters, UIA rupture risk prediction models have been developed [155,156]. More recently, some prediction models for aneurysmal stability and growth have been proposed [36,37].…”

Section: Introductionmentioning

confidence: 99%

“…They determined flatness to be the most important morphology predictor of aneurysm stability. Bizjak et al [37] found using point clouds with PointNet++ for future UIA growth prediction had a higher accuracy than other machine learning (random forest and multi-layer perceptron) models based on classical shape parameters. The method was performed using only 44 UIAs, where 25 were considered to be growing and 19 to be stable.…”

Section: Introductionmentioning

confidence: 99%

“…In CTA, contrast agent is administered intravenously to enhance the intensity in the blood vessels. TOF-MRAs have preference 14 Chapter 1 aneurysms [34] and morphology has also been used as a predictor for the instability of unruptured intracranial aneurysms [36,37]. There is a variety of different shape/morphology measures used in these studies, which means that no standard definition of intracranial aneurysm shape or morphology has yet been established.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Image Analysis and Deep Learning Techniques for the Detection and Characterisation of Unruptured Intracranial Aneurysms

Timmins¹

View full text Add to dashboard Cite

This thesis presents image analysis techniques for the detection and characterisation of unruptured intracranial aneurysms (UIAs). Using such methods, robust and reliable growth and rupture assessment of UIAs can be made to aid in treatment decision making. The first half of this thesis consider automatic UIA detection and segmentation methods from angiographic scans (TOF-MRAs and CTAs). Chapter 2 describes the organisation of an international biomedical image analysis challenge. Teams submitted automatic UIA detection and segmentation methods, which were evaluated on a held-out test set. The winning detection method has since been developed into an open-source framework for medical image detection (nnDetection). The challenge remains as an important benchmark for UIA detection and segmentation methods. Chapter 3 describes an anomaly detection method using a variational autoencoder (VAE) trained on healthy TOF-MRAs. Reconstructed TOF-MRAs with diagnosed aneurysms had a lower Structural Similarity Index (SSIM), than TOF-MRAs of subjects with no aneurysms. Importantly, the results identified that structure and shape within the scans, and not just intensity, is important for UIA detection. The UIA detection method in Chapter 4 exploits the fact surface of a UIA is different from surrounding vessels. Vessels were segmented from TOF-MRAs and meshes were fitted to the surface. A mesh convolutional neural network was trained using the labelled vessel meshes, to detect UIAs. The modality-independent method has comparable performance for both TOF-MRAs and CTAs. Automatic UIA detection and segmentation described in Chapters 2-4 allow automatic 3D volume and morphology UIA measurements for potential growth and rupture risk assessment. Chapters 5 and 6 investigate UIA volume and morphology and their relationship to UIA growth assessment. In Chapter 5, 3D volume growth assessment was more reliable than 2D size, with smaller interobsever differences, and more consistency across location. The smallest detectable change for 2D growth was larger than the current growth definition (1mm), leading to ambiguity in the current definition. 3D UIA quantitative morphology measures, such as flatness and shape index, were introduced in Chapter 6 and their relationship with UIA growth investigated. Even in non-growing (stable) aneurysms, morphology changed, suggesting that non-growing aneurysms could still be unstable. Quantified morphologic change should be considered for UIA growth and rupture risk assessment. Finally, in Chapter 7, a UIA growth prediction model using a vessel surface mesh convolutional neural network was developed. The model had comparable performance to patient demographic growth prediction models (ELAPSS). Mesh/morphology and patient models could be combined to provide a complete UIA growth prediction model. In conclusion, this thesis provides complete UIA characterisation from TOF-MRAs using computer-aided techniques. The automatic UIA detection and segmentation allows reliable, automatic UIA volume and morphology measurements. Such measurements aid in UIA growth assessment and formal UIA growth definitions including these measures should be investigated. As the accuracy of automatic UIA segmentation methods and growth prediction models increase, these will become more commonplace in clinical workflows. This could result in a fully automatic UIA characterisation tool, determining UIA volume, morphology and growth prediction scores to aid in treatment decision and improve patient outcome.

show abstract

“…Our proposed method did not perform as well as the method using PointNet++ put forward by Bizjak [37] (accuracy = 82%). This may be for a variety of reasons.…”

Section: Discussioncontrasting

confidence: 61%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Image Analysis and Deep Learning Techniques for the Detection and Characterisation of Unruptured Intracranial Aneurysms

Timmins¹

View full text Add to dashboard Cite

show abstract

“…Liu et al ( 18 ) applied a feed-forward artificial neural network to morphological features, demographic factors, and hypertension and smoking histories for the assessment of rupture risk of communicating artery aneurysms, achieving the highest AUC of 0.95. Bizjak et al ( 19 ) applied univariate thresholding, multivariate random forest and multilayer perceptron (MLP) learning, and deep shape learning on morphological features and deep shape features to predict IA growth. The deep shape learning method could achieve the highest accuracy of 0.82.…”

Section: Introductionmentioning

confidence: 99%

An Integrated Model Combining Machine Learning and Deep Learning Algorithms for Classification of Rupture Status of IAs

Chen

et al. 2022

Front. Neurol.

View full text Add to dashboard Cite

BackgroundThe rupture risk assessment of intracranial aneurysms (IAs) is clinically relevant. How to accurately assess the rupture risk of IAs remains a challenge in clinical decision-making.PurposeWe aim to build an integrated model to improve the assessment of the rupture risk of IAs.Materials and MethodsA total of 148 (39 ruptured and 109 unruptured) IA subjects were retrospectively computed with computational fluid dynamics (CFDs), and the integrated models were proposed by combining machine learning (ML) and deep learning (DL) algorithms. ML algorithms that include random forest (RF), k-nearest neighbor (KNN), XGBoost (XGB), support vector machine (SVM), and LightGBM were, respectively, adopted to classify ruptured and unruptured IAs. A Pointnet DL algorithm was applied to extract hemodynamic cloud features from the hemodynamic clouds obtained from CFD. Morphological variables and hemodynamic parameters along with the extracted hemodynamic cloud features were acted as the inputs to the classification models. The classification results with and without hemodynamic cloud features are computed and compared.ResultsWithout consideration of hemodynamic cloud features, the classification accuracy of RF, KNN, XGB, SVM, and LightGBM was 0.824, 0.759, 0.839, 0.860, and 0.829, respectively, and the AUCs of them were 0.897, 0.584, 0.892, 0.925, and 0.890, respectively. With the consideration of hemodynamic cloud features, the accuracy successively increased to 0.908, 0.873, 0.900, 0.926, and 0.917. Meanwhile, the AUCs reached 0.952, 0.881, 0.950, 0.969, and 0.965 eventually. Adding consideration of hemodynamic cloud features, the SVM could perform best with the highest accuracy of 0.926 and AUC of 0.969, respectively.ConclusionThe integrated model combining ML and DL algorithms could improve the classification of IAs. Adding consideration of hemodynamic cloud features could bring more accurate classification, and hemodynamic cloud features were important for the discrimination of ruptured IAs.

show abstract

Future Unruptured Intracranial Aneurysm Growth Prediction Using Mesh Convolutional Neural Networks

Timmins

Kamphuis

Vos

et al. 2022

Ethical and Philosophical Issues in Medical Imaging, Multimodal Learning and Fusion Across Scales for Clinical Decision Support

View full text Add to dashboard Cite

Deep Shape Features for Predicting Future Intracranial Aneurysm Growth

Cited by 14 publications

References 28 publications

Image Analysis and Deep Learning Techniques for the Detection and Characterisation of Unruptured Intracranial Aneurysms

Image Analysis and Deep Learning Techniques for the Detection and Characterisation of Unruptured Intracranial Aneurysms

An Integrated Model Combining Machine Learning and Deep Learning Algorithms for Classification of Rupture Status of IAs

Future Unruptured Intracranial Aneurysm Growth Prediction Using Mesh Convolutional Neural Networks

Contact Info

Product

Resources

About