Vessel segmentation from volumetric images: a multi‐scale double‐pathway network with class‐balanced loss at the voxel level

Chen, Yibing; Fan, Songtao; Chen, Yongfeng; Che, Chang; Cao, Xin; He, Xiaohai; Song, Xiaolei; Zhao, Fengjun

doi:10.1002/mp.14934

Cited by 6 publications

(4 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we leveraged voxel-wise segmentation indices instead of classification indices, i.e., DSC, MSD and HD, to evaluate the performance of labeling model, given the anatomical morphology and 3D properties of vessels. The proposed model achieved the overall DSC of 0.88, MSD of 0.82 mm and HD of 6.59 mm, demonstrating superior results compared with the conventional segmentation of carotid lumens and the whole cerebral vessels ( Hemmati et al, 2017 ; Chen et al, 2021 ; Guo et al, 2021 ; Huang, Wang, and Li, 2023 ). Besides, we found that labeling performance of MCA, ACoA and PCoA seemed to decline in line with prior researches ( Dunas et al, 2017 ; Hilbert et al, 2022 ; Hong et al, 2023 ).…”

Section: Discussionmentioning

confidence: 89%

Automated anatomical labeling of the intracranial arteries via deep learning in computed tomography angiography

Chen,

You,

Zhang

et al. 2024

Front. Physiol.

View full text Add to dashboard Cite

Background and purpose: Anatomical labeling of the cerebral vasculature is a crucial topic in determining the morphological nature and characterizing the vital variations of vessels, yet precise labeling of the intracranial arteries is time-consuming and challenging, given anatomical structural variability and surging imaging data. We present a U-Net-based deep learning (DL) model to automatically label detailed anatomical segments in computed tomography angiography (CTA) for the first time. The trained DL algorithm was further tested on a clinically relevant set for the localization of intracranial aneurysms (IAs).Methods: 457 examinations with varying degrees of arterial stenosis were used to train, validate, and test the model, aiming to automatically label 42 segments of the intracranial arteries [e.g., 7 segments of the internal carotid artery (ICA)]. Evaluation metrics included Dice similarity coefficient (DSC), mean surface distance (MSD), and Hausdorff distance (HD). Additionally, 96 examinations containing at least one IA were enrolled to assess the model’s potential in enhancing clinicians’ precision in IA localization. A total of 5 clinicians with different experience levels participated as readers in the clinical experiment and identified the precise location of IA without and with algorithm assistance, where there was a washout period of 14 days between two interpretations. The diagnostic accuracy, time, and mean interrater agreement (Fleiss’ Kappa) were calculated to assess the differences in clinical performance of clinicians.Results: The proposed model exhibited notable labeling performance on 42 segments that included 7 anatomical segments of ICA, with the mean DSC of 0.88, MSD of 0.82 mm and HD of 6.59 mm. Furthermore, the model demonstrated superior labeling performance in healthy subjects compared to patients with stenosis (DSC: 0.91 vs. 0.89, p < 0.05; HD: 4.75 vs. 6.19, p < 0.05). Concurrently, clinicians with model predictions achieved significant improvements when interpreting the precise location of IA. The clinicians’ mean accuracy increased by 0.04 (p = 0.003), mean time to diagnosis reduced by 9.76 s (p < 0.001), and mean interrater agreement (Fleiss’ Kappa) increased by 0.07 (p = 0.029).Conclusion: Our model stands proficient for labeling intracranial arteries using the largest CTA dataset. Crucially, it demonstrates clinical utility, helping prioritize the patients with high risks and ease clinical workload.

show abstract

Section: Discussionmentioning

confidence: 89%

Automated anatomical labeling of the intracranial arteries via deep learning in computed tomography angiography

Chen,

You,

Zhang

et al. 2024

Front. Physiol.

View full text Add to dashboard Cite

show abstract

“…Until recently, most deep learning-based segmentation networks of intracranial vasculature were based on TOF-MRA ( 29 ), CTA ( 30 ) or CTA in combination with DSA ( 31 ). Furthermore, the recent TopCoW challenge yielded very impressive results for CoW segmentations using CTA and MRA images ( 32 ).…”

Section: Discussionmentioning

confidence: 99%

Automated intracranial vessel segmentation of 4D flow MRI data in patients with atherosclerotic stenosis using a convolutional neural network

Winter,

Berhane,

Moore

et al. 2024

Front. Radiol.

View full text Add to dashboard Cite

IntroductionIntracranial 4D flow MRI enables quantitative assessment of hemodynamics in patients with intracranial atherosclerotic disease (ICAD). However, quantitative assessments are still challenging due to the time-consuming vessel segmentation, especially in the presence of stenoses, which can often result in user variability. To improve the reproducibility and robustness as well as to accelerate data analysis, we developed an accurate, fully automated segmentation for stenosed intracranial vessels using deep learning.Methods154 dual-VENC 4D flow MRI scans (68 ICAD patients with stenosis, 86 healthy controls) were retrospectively selected. Manual segmentations were used as ground truth for training. For automated segmentation, deep learning was performed using a 3D U-Net. 20 randomly selected cases (10 controls, 10 patients) were separated and solely used for testing. Cross-sectional areas and flow parameters were determined in the Circle of Willis (CoW) and the sinuses. Furthermore, the flow conservation error was calculated. For statistical comparisons, Dice scores (DS), Hausdorff distance (HD), average symmetrical surface distance (ASSD), Bland-Altman analyses, and interclass correlations were computed using the manual segmentations from two independent observers as reference. Finally, three stenosis cases were analyzed in more detail by comparing the 4D flow-based segmentations with segmentations from black blood vessel wall imaging (VWI).ResultsTraining of the network took approximately 10 h and the average automated segmentation time was 2.2 ± 1.0 s. No significant differences in segmentation performance relative to two independent observers were observed. For the controls, mean DS was 0.85 ± 0.03 for the CoW and 0.86 ± 0.06 for the sinuses. Mean HD was 7.2 ± 1.5 mm (CoW) and 6.6 ± 3.7 mm (sinuses). Mean ASSD was 0.15 ± 0.04 mm (CoW) and 0.22 ± 0.17 mm (sinuses). For the patients, the mean DS was 0.85 ± 0.04 (CoW) and 0.82 ± 0.07 (sinuses), the HD was 8.4 ± 3.1 mm (CoW) and 5.7 ± 1.9 mm (sinuses) and the mean ASSD was 0.22 ± 0.10 mm (CoW) and 0.22 ± 0.11 mm (sinuses). Small bias and limits of agreement were observed in both cohorts for the flow parameters. The assessment of the cross-sectional lumen areas in stenosed vessels revealed very good agreement (ICC: 0.93) with the VWI segmentation but a consistent overestimation (bias ± LOA: 28.1 ± 13.9%).DiscussionDeep learning was successfully applied for fully automated segmentation of stenosed intracranial vasculatures using 4D flow MRI data. The statistical analysis of segmentation and flow metrics demonstrated very good agreement between the CNN and manual segmentation and good performance in stenosed vessels. To further improve the performance and generalization, more ICAD segmentations as well as other intracranial vascular pathologies will be considered in the future.

show abstract

“…CNN algorithm [ 17 ] and V-net network (V-net) algorithm [ 18 ] were introduced to be compared with the proposed Hessian matrix enhanced filtering segmentation algorithm. In this study, Jaccard index, Dice similarity coefficient, sensitivity, and specificity were used to express the effect of coronary artery segmentation, and the range of the two values was between 0 and 1, and the higher the value, the higher the segmentation accuracy.…”

Section: Methodsmentioning

confidence: 99%

Segmentation Algorithm-Based Safety Analysis of Cardiac Computed Tomography Angiography to Evaluate Doctor-Nurse-Patient Integrated Nursing Management for Cardiac Interventional Surgery

Zhang

Chen

2022

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

To deeply analyze the influences of doctor-nurse-patient integrated nursing management on cardiac interventional surgery, 120 patients with coronary heart disease undergoing cardiac interventional therapy were selected as the subjects and randomly divided into two groups, 60 cases in each group. The experimental group used the doctor-nurse-patient integrated nursing, while the control group adopted the routine nursing. The Hessian matrix enhanced filter segmentation algorithm was used to process the cardiac computed tomography angiography (CTA) images of patients to assess the algorithm performance and the safety of nursing methods. The results showed that the Jaccard, Dice, sensitivity, and specificity of cardiac CTA images of patients with coronary heart disease processed by Hessian matrix enhanced filter segmentation algorithm were 0.86, 0.93, 0.94, and 0.95, respectively; the disease self-management ability score and quality of life score of patients in the experimental group after nursing intervention were significantly better than those before nursing intervention, with significant differences ( P < 0.05 ). The number of cases with adverse vascular events in the experimental group was 3 cases, which was obviously lower than that in the control group (15 cases). The diagnostic accuracy of the two groups of patients after segmentation algorithm processing was 0.87 and 0.88, respectively, which was apparently superior than the diagnostic accuracy of conventional CTA (0.58 and 0.61). In summary, cardiac CTA evaluation of doctor-nurse-patient integrated nursing management cardiac interventional surgery based on segmentation algorithm had good safety and was worthy of further promotion in clinical cardiac interventional surgery.

show abstract

Vessel segmentation from volumetric images: a multi‐scale double‐pathway network with class‐balanced loss at the voxel level

Cited by 6 publications

References 42 publications

Automated anatomical labeling of the intracranial arteries via deep learning in computed tomography angiography

Automated anatomical labeling of the intracranial arteries via deep learning in computed tomography angiography

Automated intracranial vessel segmentation of 4D flow MRI data in patients with atherosclerotic stenosis using a convolutional neural network

Segmentation Algorithm-Based Safety Analysis of Cardiac Computed Tomography Angiography to Evaluate Doctor-Nurse-Patient Integrated Nursing Management for Cardiac Interventional Surgery

Contact Info

Product

Resources

About