OFF-eNET: An Optimally Fused Fully End-to-End Network for Automatic Dense Volumetric 3D Intracranial Blood Vessels Segmentation

Nazir, Abdul; Cheema, Muhammad Nadeem; Sheng, Bin; Li, Huating; Li, Ping; Yang, Po; Jung, Younhyun; Qin, Jing; Feng, David Dagan

doi:10.1109/tip.2020.2999854

Cited by 90 publications

(26 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite the difficulty to segment the vessel tree on CTA data alone, an early feasibility study [Manniesing et al, 2008] has shown a segmentation of the cerebral arterial tree with no additional NCCT is possible. As a successor Nazir et al [2020] proposed a patch-wise segmentation network similar to a ResNet consisting of Inception modules [Szegedy et al, 2015]. In a cross-validation on 70 data sets their approach achieved a Dice score of 89.46%.…”

Section: Segmentationmentioning

confidence: 99%

“…In a cross-validation on 70 data sets their approach achieved a Dice score of 89.46%. Still, the development of supervised segmentation networks is compounded by the fact that the labeling itself requires an extraordinary effort, as Nazir et al [2020] reported. The labeling of one data set took 6 hours, resulting in roughly a month of work required to annotate 20 cases [Nazir et al, 2020].…”

Section: Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

An Algorithm for the Labeling and Interactive Visualization of the Cerebrovascular System of Ischemic Strokes

Thamm¹,

Jürgens²,

Taubmann³

et al. 2022

Preprint

View full text Add to dashboard Cite

During the diagnosis of ischemic strokes, the Circle of Willis and its surrounding vessels are the arteries of interest. Their visualization in case of an acute stroke is often enabled by Computed Tomography Angiography (CTA). Still, the identification and analysis of the cerebral arteries remain time consuming in such scans due to a large number of peripheral vessels which may disturb the visual impression. In previous work we proposed VirtualDSA++, an algorithm designed to segment and label the cerebrovascular tree on CTA scans. Especially with stroke patients, labeling is a delicate procedure, as in the worst case whole hemispheres may not be present due to impeded perfusion. Hence, we extended the labeling mechanism for the cerebral arteries to identify occluded vessels. In the work at hand, we place the algorithm in a clinical context by evaluating the labeling and occlusion detection on stroke patients, where we have achieved labeling sensitivities comparable to other works between 92 % and 95 %. To the best of our knowledge, ours is the first work to address labeling and occlusion detection at once, whereby a sensitivity of 67 % and a specificity of 81 % were obtained for the latter. VirtualDSA++ also automatically segments and models the intracranial system, which we further used in a deep learning driven follow up work. We present the generic concept of iterative systematic search for pathways on all nodes of said model, which enables new interactive features. Exemplary, we derive in detail, firstly, the interactive planning of vascular interventions like the mechanical thrombectomy and secondly, the interactive suppression of vessel structures that are not of interest in diagnosing strokes (like veins). We discuss both features as well as further possibilities emerging from the proposed concept.

show abstract

Section: Segmentationmentioning

confidence: 99%

Section: Segmentationmentioning

confidence: 99%

An Algorithm for the Labeling and Interactive Visualization of the Cerebrovascular System of Ischemic Strokes

Thamm¹,

Jürgens²,

Taubmann³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Consequently, local vessels were enhanced and small vessels were better captured. Furthermore, Nazir et al 42 proposed an end‐to‐end Network named OFF‐eNET for automatic segmentation of the volumetric 3D intracranial vascular structures. It enhanced information flow and preserved multiscale features by using up‐skip connections and dilated convolution separately, whereas the up‐skip connections only transferred features locally.…”

Section: Related Workmentioning

confidence: 99%

A nested parallel multiscale convolution for cerebrovascular segmentation

et al. 2021

View full text Add to dashboard Cite

Purpose: Cerebrovascular segmentation in magnetic resonance imaging (MRI) plays an important role in the diagnosis and treatment of cerebrovascular diseases. Many segmentation frameworks based on convolutional neural networks (CNNs) or U‐Net‐like structures have been proposed for cerebrovascular segmentation. Unfortunately, the segmentation results are still unsatisfactory, particularly in the small/thin cerebrovascular due to the following reasons: (1) the lack of attention to multiscale features in encoder caused by the convolutions with single kernel size; (2) insufficient extraction of shallow and deep‐seated features caused by the depth limitation of transmission path between encoder and decoder; (3) insufficient utilization of the extracted features in decoder caused by less attention to multiscale features. Methods: Inspired by U‐Net++, we propose a novel 3D U‐Net‐like framework termed Usception for small cerebrovascular. It includes three blocks: Reduction block, Gap block, and Deep block, aiming to: (1) improve feature extraction ability by grouping different convolution sizes; (2) increase the number of multiscale features in different layers by grouping paths of different depths between encoder and decoder; (3) maximize the ability of decoder in recovering multiscale features from Reduction and Gap block by using convolutions with different kernel sizes. Results: The proposed framework is evaluated on three public and in‐house clinical magnetic resonance angiography (MRA) data sets. The experimental results show that our framework reaches an average dice score of 69.29%, 87.40%, 77.77% on three data sets, which outperform existing state‐of‐the‐art methods. We also validate the effectiveness of each block through ablation experiments. Conclusions: By means of the combination of Inception‐ResNet and dimension‐expanded U‐Net++, the proposed framework has demonstrated its capability to maximize multiscale feature extraction, thus achieving competitive segmentation results for small cerebrovascular.

show abstract

“…In terms of the segmentation under supervised setting, among the current SOTA methods, the most popular framework is the fully convolutional network (FCN) [35] based encoder-decoder architecture with the representative model like U-Net [45]. So far, to make the conventional encoder-decoder architecture more effective and robust, researchers have made great efforts in the following three directions: 1) developing novel structures, including the 3D structure, recurrent neural network (RNN) based model and cascaded framework [39] [7] [4] [48] [12] [62], 2) designing novel network blocks, including attention mechanism, dense connection, inception or multi-scale fusion [8] [65] [11] [57] [41], and 3) utilizing sophisticated loss functions [58] [10] [26] [61], significantly improving segmentation accuracy.…”

Section: A Medical Image Segmentationmentioning

confidence: 99%

Inconsistency-aware Uncertainty Estimation for Semi-supervised Medical Image Segmentation

Shi¹,

Zhang²,

Tong³

et al. 2021

Preprint

View full text Add to dashboard Cite

In semi-supervised medical image segmentation, most previous works draw on the common assumption that higher entropy means higher uncertainty. In this paper, we investigate a novel method of estimating uncertainty. We observe that, when assigned different misclassification costs in a certain degree, if the segmentation result of a pixel becomes inconsistent, this pixel shows a relative uncertainty in its segmentation. Therefore, we present a new semi-supervised segmentation model, namely, conservative-radical network (CoraNet in short) based on our uncertainty estimation and separate self-training strategy. In particular, our CoraNet model consists of three major components: a conservative-radical module (CRM), a certain region segmentation network (C-SN), and an uncertain region segmentation network (UC-SN) that could be alternatively trained in an end-to-end manner. We have extensively evaluated our method on various segmentation tasks with publicly available benchmark datasets, including CT pancreas, MR endocardium, and MR multi-structures segmentation on the ACDC dataset. Compared with the current state of the art, our CoraNet has demonstrated superior performance. In addition, we have also analyzed its connection with and difference from conventional methods of uncertainty estimation in semi-supervised medical image segmentation.

show abstract

OFF-eNET: An Optimally Fused Fully End-to-End Network for Automatic Dense Volumetric 3D Intracranial Blood Vessels Segmentation

Abstract: This is a repository copy of OFF-eNET: An optimally fused fully end-to-end network for automatic dense volumetric 3D intracranial blood vessels segmentation.

Cited by 90 publications

References 50 publications

An Algorithm for the Labeling and Interactive Visualization of the Cerebrovascular System of Ischemic Strokes

An Algorithm for the Labeling and Interactive Visualization of the Cerebrovascular System of Ischemic Strokes

A nested parallel multiscale convolution for cerebrovascular segmentation

Inconsistency-aware Uncertainty Estimation for Semi-supervised Medical Image Segmentation

Contact Info

Product

Resources

About