Dilated Deeply Supervised Networks for Hippocampus Segmentation in MRI

Folle, Lukas; Vesal, Sulaiman; Ravikumar, Nishant; Maier, Andreas

doi:10.1007/978-3-658-25326-4_18

Cited by 12 publications

(15 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Stawiaski ( 2017 ) implemented deep supervision by down-sampling ground truth segmentations and weighting each coefficient equally in the loss function. Other implementations aggregated the coarse, low-resolution feature maps into the final convolutional layers and thus incorporated different features in a single loss coefficient (Chen et al, 2014 ; Long et al, 2014 ; Folle et al, 2019 ). In contrast, we aim to facilitate the convergence of intermediate layers by direct supervision.…”

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

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: 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

“…The properties of the 3D U‐Net has previously been discussed elsewhere, 34 from which we implemented the standard model. Folle et al 67 proposed the D‐3D U‐Net for hippocampal segmentation on MR images. This modification replaces the lowest U‐Net layer with a summation of four dilated convolutions, adds short residual connections in encoding blocks, transpose convolutions are replaced with 2D upsampling operations, and a cascaded summation of upsampled outputs from each decoding layer is used to generate the final prediction.…”

Section: Methodsmentioning

confidence: 99%

Hippocampus segmentation on noncontrast CT using deep learning

et al. 2020

View full text Add to dashboard Cite

Purpose: Accurate segmentation of the hippocampus for hippocampal avoidance whole-brain radiotherapy currently requires high-resolution magnetic resonance imaging (MRI) in addition to neuroanatomic expertise for manual segmentation. Removing the need for MR images to identify the hippocampus would reduce planning complexity, the need for a treatment planning MR imaging session, potential uncertainties associated with MRI-computed tomography (CT) image registration, and cost. Three-dimensional (3D) deep convolutional network models have the potential to automate hippocampal segmentation. In this study, we investigate the accuracy and reliability of hippocampal segmentation by automated deep learning models from CT alone and compare the accuracy to experts using MRI fusion. Methods: Retrospectively, 390 Gamma Knife patients with high-resolution CT and MR images were collected. Following the RTOG 0933 guidelines, images were rigidly fused, and a neuroanatomic expert contoured the hippocampus on the MR, then transferred the contours to CT. Using a calculated cranial centroid, the image volumes were cropped to 200 9 200 9 35 voxels, which were used to train four models, including our proposed Attention-Gated 3D ResNet (AG-3D ResNet). These models were then compared with results from a nested tenfold validation. From the predicted test set volumes, we calculated the 100% Hausdorff distance (HD). Acceptability was assessed using the RTOG 0933 protocol criteria, and contours were considered passing with HD ≤ 7 mm. Results: The bilateral hippocampus passing rate across all 90 models trained in the nested cross-fold validation was 80.2% for AG-3D ResNet, which performs with a comparable pass rate (P = 0.3345) to physicians during centralized review for the RTOG 0933 Phase II clinical trial. Conclusions: Our proposed AG-3D ResNet's segmentation of the hippocampus from noncontrast CT images alone are comparable to those obtained by participating physicians from the RTOG 0933 Phase II clinical trial.

show abstract

“…Stawiaski (Stawiaski, 2017) implemented deep supervision by down-sampling ground truth segmentations and weighting each coefficient equally in the loss function. Other implementations aggregated the coarse, low-resolution feature maps into the final convolutional layers and thus incorporated different features in a single loss coefficient (Chen et al, 2014; Long et al, 2014; Folle et al, 2019). In contrast, we aim to facilitate the convergence of intermediate layers by direct supervision.…”

Section: Methodsmentioning

confidence: 99%

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

Dilated Deeply Supervised Networks for Hippocampus Segmentation in MRI

Cited by 12 publications

References 9 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

Hippocampus segmentation on noncontrast CT using deep learning

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

Contact Info

Product

Resources

About