Retinal vessel segmentation using dense U-net with multiscale inputs

Yue, Kejuan; Zou, Beiji; Chen, Zailiang; Liu, Qing

doi:10.1117/1.jmi.6.3.034004

Cited by 26 publications

(16 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CNNs and encoderdecoder Unet variations, in particular, were proven in recent years as the state-of-the-art method for semantic segmentation including medical imaging applications (Milletari et al, 2016;Badrinarayanan et al, 2017;Dong et al, 2017;Alom et al, 2018;Norman et al, 2018;Huang et al, 2020;Sinha and Jose, 2020;Zhou et al, 2020). This success was further demonstrated in vessel segmentation and specifically in brain vessel segmentation problems (Chen et al, 2017;Alom et al, 2018;Huang et al, 2018;Livne et al, 2019a;Yue et al, 2019). The utilization of the Unet as a baseline architecture was, therefore, a natural choice.…”

Section: Discussionmentioning

confidence: 99%

“…A significant amount of these small vessels lie close to the skull, i.e., has a particularly distinctive spatial context. To tackle these problems, a multiscale approach is applied (Havaei et al, 2016 ; Kamnitsas et al, 2017 ; Yue et al, 2019 ). We extend the base architecture with a context aggregation under the hypothesis that it will improve the discrimination between vessels of interest and other constructs and particularly improve the segmentation of small vessels.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

BRAVE-NET: Fully Automated Arterial Brain Vessel Segmentation in Patients With Cerebrovascular Disease

Hilbert

Madai

Akay

et al. 2020

Front. Artif. Intell.

View full text Add to dashboard Cite

Introduction: Arterial brain vessel assessment is crucial for the diagnostic process in patients with cerebrovascular disease. Non-invasive neuroimaging techniques, such as time-of-flight (TOF) magnetic resonance angiography (MRA) imaging are applied in the clinical routine to depict arteries. They are, however, only visually assessed. Fully automated vessel segmentation integrated into the clinical routine could facilitate the time-critical diagnosis of vessel abnormalities and might facilitate the identification of valuable biomarkers for cerebrovascular events. In the present work, we developed and validated a new deep learning model for vessel segmentation, coined BRAVE-NET, on a large aggregated dataset of patients with cerebrovascular diseases. Methods: BRAVE-NET is a multiscale 3-D convolutional neural network (CNN) model developed on a dataset of 264 patients from three different studies enrolling patients with cerebrovascular diseases. A context path, dually capturing high-and low-resolution volumes, and deep supervision were implemented. The BRAVE-NET model was compared to a baseline Unet model and variants with only context paths and deep supervision, respectively. The models were developed and validated using high-quality manual labels as ground truth. Next to precision and recall, the performance was assessed quantitatively by Dice coefficient (DSC); average Hausdorff distance (AVD); 95-percentile Hausdorff distance (95HD); and via visual qualitative rating. Results: The BRAVE-NET performance surpassed the other models for arterial brain vessel segmentation with a DSC = 0.931, AVD = 0.165, and 95HD = 29.153. The BRAVE-NET model was also the most resistant toward false labelings as revealed by the visual analysis. The performance improvement is primarily attributed to the integration Hilbert et al. Fully-Automated Arterial Brain Vessel Segmentation of the multiscaling context path into the 3-D Unet and to a lesser extent to the deep supervision architectural component. Discussion: We present a new state-of-the-art of arterial brain vessel segmentation tailored to cerebrovascular pathology. We provide an extensive experimental validation of the model using a large aggregated dataset encompassing a large variability of cerebrovascular disease and an external set of healthy volunteers. The framework provides the technological foundation for improving the clinical workflow and can serve as a biomarker extraction tool in cerebrovascular diseases.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

BRAVE-NET: Fully Automated Arterial Brain Vessel Segmentation in Patients With Cerebrovascular Disease

Hilbert

Madai

Akay

et al. 2020

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…CNNs and encoder-decoder Unet variations, in particular, were proven in recent years as the state-of-the-art method for semantic segmentation including medical imaging applications (Milletari et al, 2016;Badrinarayanan et al, 2017;Dong et al, 2017;Alom et al, 2018;Norman et al, 2018). This success was further demonstrated in vessel segmentation and specifically in brain vessel segmentation problems (Chen et al, 2017;Alom et al, 2018;Huang et al, 2018;Livne et al, 2019a;Yue et al, 2019). The utilization of the Unet as a baseline architecture was, therefore, a natural choice.…”

Section: Discussionmentioning

confidence: 99%

“…has a particularly distinctive spatial context. To tackle these problems, a multiscale approach is applied (Choi et al; Kamnitsas et al, 2017; Yue et al, 2019). We extend the base architecture with a context aggregation under the hypothesis that it will improve the discrimination between vessels of interest and other constructs and particularly improve the segmentation of small vessels.…”

Section: Methodsmentioning

confidence: 99%

“…For qualitative assessment, the predicted segmentation masks were transformed by in-house python code where true positives (TP), false positives (FP), and false negatives (FN) were assigned different voxel values (True negatives (TN) remained labeled with 0). The images were then visualized by overlaying these new masks with the original scans using ITK-Snap software (Yushkevich et al, 2006). By adjusting the opaqueness, it was possible to qualitatively assess which structures were correctly identified and which anatomical structures dominated with errors.…”

Section: Visual Assessmentmentioning

confidence: 99%

See 1 more Smart Citation

BRAVE-NET: Fully Automated Arterial Brain Vessel Segmentation In Patients with Cerebrovascular Disease

Hilbert

Madai

Akay

et al. 2020

Preprint

View full text Add to dashboard Cite

Introduction Arterial brain vessel assessment is crucial for the diagnostic process in patients with cerebrovascular disease. Noninvasive neuroimaging techniques such as time-of-flight (TOF) magnetic resonance angiography (MRA) imaging are applied in the clinical routine to depict arteries. They are, however, only visually assessed. Fully automated vessel segmentation integrated into the clinical routine could facilitate the time-critical diagnosis of vessel abnormalities and might facilitate the identification of valuable biomarkers for cerebrovascular events. In the present work, we developed and validated a new deep learning model for vessel segmentation, coined BRAVE-NET, on a large aggregated dataset of patients with cerebrovascular diseases. Methods BRAVE-NET is a multiscale 3-D convolutional neural network (CNN) model developed on a dataset of 264 patients from 3 different studies enrolling patients with cerebrovascular diseases. A context path, dually capturing high- and low-resolution volumes, and deep supervision were implemented. The BRAVE-NET model was compared to a baseline Unet model and variants with only context paths and deep supervision, respectively. The models were developed and validated using high-quality manual labels as ground truth. Next to precision and recall, the performance was assessed quantitatively by Dice coefficient (DSC); average Hausdorff distance (AVD); 95-percentile Hausdorff distance (95HD) and via visual qualitative rating. Results The BRAVE-NET performance surpassed the other models for arterial brain vessel segmentation with a DSC = 0.931, AVD = 0.165 and 95HD = 29.153. The BRAVE-NET model was also the most resistant towards false labelings as revealed by the visual analysis. The performance improvement is primarily attributed to the integration of the multiscaling context path into the 3-D Unet and to a lesser extent to the deep supervision architectural component. Discussion We present a new state-of-the-art of arterial brain vessel segmentation tailored to cerebrovascular pathology. We provide an extensive experimental validation of the model using a large aggregated dataset encompassing a large variability of cerebrovascular disease. The framework provides the technological foundation for improving the clinical workflow and can serve as a biomarker extraction tool in cerebrovascular diseases.

show abstract

Fundamentals of Deep Learning Models for Medical Image Segmentation

Rehman,

Bhat

2025

Deep Learning Applications in Medical Image Segmentation

View full text Add to dashboard Cite

Retinal vessel segmentation using dense U-net with multiscale inputs

Cited by 26 publications

References 35 publications

BRAVE-NET: Fully Automated Arterial Brain Vessel Segmentation in Patients With Cerebrovascular Disease

BRAVE-NET: Fully Automated Arterial Brain Vessel Segmentation in Patients With Cerebrovascular Disease

BRAVE-NET: Fully Automated Arterial Brain Vessel Segmentation In Patients with Cerebrovascular Disease

Fundamentals of Deep Learning Models for Medical Image Segmentation

Contact Info

Product

Resources

About