Intracranial Vascular Structure Extraction: A Machine Learning Approach

Zhao, Shu; Wang, Xuesong; Xie, Lizhi; Sun, Lingling

doi:10.1109/access.2019.2931359

Cited by 2 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mejis et al applied feature extraction and random forest classification to segment the cerebral vasculature using CTA from stroke patients (23). However, these methods have required separate vascular imaging protocols, such as MRA or CTA (20,21,24); and the lengthy pre-and post-processing steps required for these methods pose limitations on real-time clinical implementation. Deep learning, a task driven form of machine learning, has multiple advantages for clinical implementation.…”

Section: Discussionmentioning

confidence: 99%

Deep Learning for Automated Delineation of Pediatric Cerebral Arteries on Pre-operative Brain Magnetic Resonance Imaging

et al. 2020

View full text Add to dashboard Cite

Introduction: Surgical resection of brain tumors is often limited by adjacent critical structures such as blood vessels. Current intraoperative navigations systems are limited; most are based on two-dimensional (2D) guidance systems that require manual segmentation of any regions of interest (ROI; eloquent structures to avoid or tumor to resect). They additionally require time-and labor-intensive processing for any reconstruction steps. We aimed to develop a deep learning model for real-time fully automated segmentation of the intracranial vessels on preoperative non-angiogram imaging sequences. Methods: We identified 48 pediatric patients (10-months to 22-years old) with high resolution (0.5-1 mm axial thickness) isovolumetric, pre-operative T2 magnetic resonance images (MRIs). Twenty-eight patients had anatomically normal brains, and 20 patients had tumors or other lesions near the skull base. Manually segmented intracranial vessels (internal carotid, middle cerebral, anterior cerebral, posterior cerebral, and basilar arteries) served as ground truth labels. Patients were divided into 80/5/15% training/validation/testing sets. A modified 2-D Unet convolutional neural network (CNN) architecture implemented with 5 layers was trained to maximize the Dice coefficient, a measure of the correct overlap between the predicted vessels and ground truth labels. Results: The model was able to delineate the intracranial vessels in a held-out test set of normal and tumor MRIs with an overall Dice coefficient of 0.75. While manual segmentation took 1-2 h per patient, model prediction took, on average, 8.3 s per patient. Conclusions: We present a deep learning model that can rapidly and automatically identify the intracranial vessels on pre-operative MRIs in patients with normal vascular anatomy and in patients with intracranial lesions. The methodology developed can be translated to other critical brain structures. This study will serve as a foundation for automated high-resolution ROI segmentation for three-dimensional (3D) modeling and integration into an augmented reality navigation platform.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep Learning for Automated Delineation of Pediatric Cerebral Arteries on Pre-operative Brain Magnetic Resonance Imaging

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Chen et al [8] 0.7371 10 Phellan et al [7] 0.7740 5 Tetteh et al [12] 0.8668 40 Kandil et al [10] 0.8437 30 Zhao et al [11] 0.8503 30 Livne et al [23] 0.9210 66 Proposed model 0.8723 4…”

Section: Mra Volumes In Datasetmentioning

confidence: 99%

“…Taking into consideration the signal variability given by blood flow, Kandil et al [10] divide their MRA volumes into two parts, above and below the Circle of Willis (CoW), and both are fed into their 3D CNN architecture, with an 84.37% Dice score as a result. Zhao et al [11] developed a framework that extracts MRA volume structures as a preprocessing step. A fully connected neural network acts as a classifier that takes as input several properties of candidate structures and obtains the probability of being a blood vessel.…”

Section: Introductionmentioning

confidence: 99%

Dual U-Net-Based Conditional Generative Adversarial Network for Blood Vessel Segmentation with Reduced Cerebral MR Training Volumes

et al. 2022

View full text Add to dashboard Cite

Segmenting vessels in brain images is a critical step for many medical interventions and diagnoses of illnesses. Recent advances in artificial intelligence provide better models, achieving a human-like level of expertise in many tasks. In this paper, we present a new approach to segment Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) images, relying on fewer training samples than state-of-the-art methods. We propose a conditional generative adversarial network with an adapted generator based on a concatenated U-Net with a residual U-Net architecture (UUr-cGAN) to carry out blood vessel segmentation in TOF-MRA images, relying on data augmentation to diminish the drawback of having few volumes at disposal for training the model, while preventing overfitting by using regularization techniques. The proposed model achieves 89.52% precision and 87.23% in Dice score on average from the cross-validated experiment for brain blood vessel segmentation tasks, which is similar to other state-of-the-art methods while using considerably fewer training samples. UUr-cGAN extracts important features from small datasets while preventing overfitting compared to other CNN-based methods and still achieve a relatively good performance in image segmentation tasks such as brain blood vessels from TOF-MRA.

show abstract

Intracranial Vascular Structure Extraction: A Machine Learning Approach

Cited by 2 publications

References 33 publications

Deep Learning for Automated Delineation of Pediatric Cerebral Arteries on Pre-operative Brain Magnetic Resonance Imaging

Deep Learning for Automated Delineation of Pediatric Cerebral Arteries on Pre-operative Brain Magnetic Resonance Imaging

Dual U-Net-Based Conditional Generative Adversarial Network for Blood Vessel Segmentation with Reduced Cerebral MR Training Volumes

Contact Info

Product

Resources

About