Automated segmentation and quantification of the healthy and diseased aorta in CT angiographies using a dedicated deep learning approach

Sieren, M; Widmann, Cornelia; Weiss, Nick; Moltz, Jan Hendrik; Link, Florian; Wegner, Franz; Stahlberg, Erik; Horn, Marco; Oecherting, Thekla Helene; Goltz, Jan Peter; Barkhausen, Joerg; Frydrychowicz, Alex

doi:10.1007/s00330-021-08130-2

Cited by 21 publications

(24 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The age of the lesion was classified as acute (< 2 weeks), subacute (> 2 weeks to < 4 weeks), or chronic (> 4 weeks) according to the onset of symptoms, as reported by the patient. For each patient, comorbidities and the degree of vessel calcification were noted [ 14 ]. Both the length of the vessel occlusion and the degree of vessel calcification were included due to their possible association with an increased risk of failure of primary thrombectomy and complications.…”

Section: Methodsmentioning

confidence: 99%

Percutaneous Thrombectomy in Patients with Occlusions of the Aortoiliac Segment: A Case Series

Sieren

Pfarr

Aludin

et al. 2022

Cardiovasc Intervent Radiol

Self Cite

View full text Add to dashboard Cite

Objective Thrombectomy of the aortoiliac segment remains a challenge for surgical and endovascular revision. This study aimed to evaluate the concept of percutaneous thrombectomy in patients with aortoiliac segment occlusions. Materials & Methods Eighteen patients with aortoiliac occlusion who underwent percutaneous thrombectomy were retrospectively identified using the local picture archive and divided into the stent-graft (N = 10) and native vessels (N = 8) groups. The procedure was performed by placing a 12–24 French sheath adjacent to the distal end of the occluded vessel segment. The occlusion was passed with a balloon catheter which was retracted after inflation, to deliver the thrombus into the sheath. Technical success (reperfusion of the vessel and no residual thrombus/stenosis < 30%), complications and primary arterial patency were assessed. Follow-up included computed tomography angiography and evaluation of the clinical situation via telephone. Results Technical success was achieved in 38% (7/18) of patients after percutaneous thrombectomy alone and in 100% after additional procedures. The most common complication was peripheral embolism (44%, 8/18), which was treated successfully in all cases and was linked to a mismatch between the sheath and target vessel of ≥ 1 mm (P < .01). There were no significant differences in the incidence of complications between the two groups. Primary patency was 72% (13/18) with no significant difference between groups (P = .94). Follow-up CT scans were available for 13/18 patients (72%), with a mean follow-up time of 270 ± 146 days. All patients were contacted via phone (follow-up time, 653 ± 264 days). Conclusion Percutaneous thrombectomy appears to be effective for revascularization of the aortoiliac segment, both in stent-grafts and in native vessels. The most common complication is peripheral embolism; however, the risk may be reduced by choosing an adequate sheath size.

show abstract

Section: Methodsmentioning

confidence: 99%

Percutaneous Thrombectomy in Patients with Occlusions of the Aortoiliac Segment: A Case Series

Sieren

Pfarr

Aludin

et al. 2022

Cardiovasc Intervent Radiol

Self Cite

View full text Add to dashboard Cite

show abstract

“…The same reason holds for the pulmonary FoV; (iii) All UNet classes had four to five layers, expect sUNet that had up to a maximum of 13 layers [42][43][44][45][46][47][48][49][50][51][52][53][54]. Note that as the number of layers increase, the DL system becomes more complex; (iv) Cross-Entropy (CE) loss function was most common or popular in all the five types of UNet , while, Dice loss function was also part of cUNet and sUNet classes ; (v) sUNet and acUNet were the two sets of classes which embraced multicenter studies [49,.…”

Section: B Five Types Of Unet and Their Attributesmentioning

confidence: 99%

“…To begin with, the encoder is the most adapted and most changeable component of the UNet architecture. Since it is practically not possible to study each of the architectural variations in the encoder, we have therefore listed here the 23 variations (E1 to E23, representing encoder changes) along with their references in a tabular format and it is as follows: (E1) conventional system (Ronneberger) [43][44][45][46][47][48][49][50][51][52]90]; (E2) cascade of convolutions [77,91,99,116,117]; (E3) parallel convolutions (multiple convolution network) [57]; (E4) convolution with dropout [70,76,86,95,101,102,134,138]; (E5) Residual network [76,78,105,129,135,138,[149][150][151]; (E6) Xception encoder [56,88,112]; (E7) encoder layers with independent inputs [104,140]; (E8) squeeze excitation (SE) network [92,103,138]; (E9) pooling types (max pooling, global average pooling) [95]; (E10) input image dimension change with changing filter (channe...…”

Section: A Encoder Variationsmentioning

confidence: 99%

“…The skip connection has taken many kinds of advances during the evolution of UNet architecture. We have categorized the variation in the skip connection of the UNet architecture by considering nine new variations shown in Table 3, namely (S1) direct skip without any addition [44,46,51,76]; (S2) UNet++ with middle neurons are supported by the encoder layers [130,144,154]; (S3) UNet+++ (UNet 3+) skip connection with full scale [157]; (S4) addition of long short-term memory network (LSTM) [159], recurrent neural network (RNN) [109], generative adversial network (GAN), bidirectional long short-term memory network (BiLSTM), bidirectional recurrent neural network (BiRNN), bidirectional generative adversial network (BiGAN) [74,160]; (S5) skip connection between two cascaded UNet where skip of one is connected with skip of second and output of UNet first decoder goes in the skip of second UNet [81]; (S6) skip of first UNet into the skip of second UNet [89]; (S7) addition of the channel attention to improve the feature extraction along with atrous dense convolution block [65, 66, 71, 75, 82, 113, 119, 125, 126, 128, 129, 131-135, 139, 161]; (S8) squeeze-excitation (SE) network [125,133]; and (S9) Res skip [150]. The skip connection offers the ability to interface the powerful classification paradigms such as LSTM, RNN, and GAN.…”

Section: Skip Connection and Its Variationsmentioning

confidence: 99%

“…Initiation networks have improved gradually with more up-to-date and fresher variants and have outperformed different structure (Figure 7 (a)). The other modification is the transpose convolution [46,64,71,113,115], which is opposite of the convolution.…”

Section: G Understanding Major Blocks Affecting For Unet Modificationmentioning

confidence: 99%

See 2 more Smart Citations

UNet Deep Learning Architecture for Segmentation of Vascular and Non-Vascular Images: A Microscopic Look at UNet Components Buffered With Pruning, Explainable Artificial Intelligence, and Bias

Suri¹,

Bhagawati

Agarwal³

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Background & Motivation: Biomedical image segmentation (BIS) task is challenging due to the variations in organ types, position, shape, size, scale, orientation, and image contrast. Conventional methods lack accurate and automated designs. Artificial intelligence (AI)-based UNet has recently dominated BIS. This is the first review of its kind that microscopically addressed UNet types by complexity, stratification of UNet by its components, addressing UNet in vascular vs. non-vascular framework, the key to segmentation challenge vs. UNet-based architecture, and finally interfacing the three facets of AI, the pruning, the explainable AI (XAI), and the AI-bias. Methods: PRISMA was used to select 267 UNet-based studies. Five classes were identified and labeled as conventional UNet, superior UNet, attention-channel UNet, hybrid UNet, and ensemble UNet. We discovered 81 variations of UNet by considering six kinds of components, namely encoder, decoder, skip connection, bridge network, loss function, and their combination. Vascular vs. non-vascular UNet architecture was compared. AP(ai)Bias 2.0-UNet was identified in these UNet classes based on (i) attributes of UNet architecture and its performance, (ii) explainable AI (XAI), and, (iii) pruning (compression). Five bias methods such as (i) ranking, (ii) radial, (iii) regional area, (iv) PROBAST, and (v) ROBINS-I were applied and compared using a Venn diagram. Findings and Conclusions: Vascular and non-vascular UNet systems dominated with sUNet classes with attention. The majority of the studies suffered from low interest in XAI and pruning strategies. None of the UNet models qualified to be bias-free. There is a need to move from paper-to-practice paradigms for clinical evaluation and settings. INDEX TERMS Image segmentation; vascular; non-vascular; UNet classes; UNet variations; UNetcomponents; explainable AI; pruning; bias.

show abstract

Deep Learning‐Based Analysis of Aortic Morphology From Three‐Dimensional MRI

Guo,

Bouaou,

Houriez‐‐Gombaud‐Saintonge

et al. 2024

Magnetic Resonance Imaging

View full text Add to dashboard Cite

BackgroundQuantification of aortic morphology plays an important role in the evaluation and follow‐up assessment of patients with aortic diseases, but often requires labor‐intensive and operator‐dependent measurements. Automatic solutions would help enhance their quality and reproducibility.PurposeTo design a deep learning (DL)‐based automated approach for aortic landmarks and lumen detection derived from three‐dimensional (3D) MRI.Study TypeRetrospective.PopulationThree hundred ninety‐one individuals (female: 47%, age = 51.9 ± 18.4) from three sites, including healthy subjects and patients (hypertension, aortic dilation, Turner syndrome), randomly divided into training/validation/test datasets (N = 236/77/78). Twenty‐five subjects were randomly selected and analyzed by three operators with different levels of expertise.Field Strength/Sequence1.5‐T and 3‐T, 3D spoiled gradient‐recalled or steady‐state free precession sequences.AssessmentReinforcement learning and a two‐stage network trained using reference landmarks and segmentation from an existing semi‐automatic software were used for aortic landmark detection and segmentation from sinotubular junction to coeliac trunk. Aortic segments were defined using the detected landmarks while the aortic centerline was extracted from the segmentation and morphological indices (length, aortic diameter, and volume) were computed for both the reference and the proposed segmentations.Statistical TestsSegmentation: Dice similarity coefficient (DSC), Hausdorff distance (HD), average symmetrical surface distance (ASSD); landmark detection: Euclidian distance (ED); model robustness: Spearman correlation, Bland–Altman analysis, Kruskal–Wallis test for comparisons between reference and DL‐derived aortic indices; inter‐observer study: Williams index (WI). A WI 95% confidence interval (CI) lower bound >1 indicates that the method is within the inter‐observer variability. A P‐value <0.05 was considered statistically significant.ResultsDSC was 0.90 ± 0.05, HD was 12.11 ± 7.79 mm, and ASSD was 1.07 ± 0.63 mm. ED was 5.0 ± 6.1 mm. A good agreement was found between all DL‐derived and reference aortic indices (r >0.95, mean bias <7%). Our segmentation and landmark detection performances were within the inter‐observer variability except the sinotubular junction landmark (CI = 0.96;1.04).Data ConclusionA DL‐based aortic segmentation and anatomical landmark detection approach was developed and applied to 3D MRI data for achieve aortic morphology evaluation.Evidence Level3Technical EfficacyStage 2

show abstract

Automated segmentation and quantification of the healthy and diseased aorta in CT angiographies using a dedicated deep learning approach

Cited by 21 publications

References 29 publications

Percutaneous Thrombectomy in Patients with Occlusions of the Aortoiliac Segment: A Case Series

Percutaneous Thrombectomy in Patients with Occlusions of the Aortoiliac Segment: A Case Series

UNet Deep Learning Architecture for Segmentation of Vascular and Non-Vascular Images: A Microscopic Look at UNet Components Buffered With Pruning, Explainable Artificial Intelligence, and Bias

Deep Learning‐Based Analysis of Aortic Morphology From Three‐Dimensional MRI

Contact Info

Product

Resources

About