Automated segmentation of the individual branches of the carotid arteries in contrast-enhanced MR angiography using DeepMedic

Abstract Background Non-invasive imaging is of interest for tracking the progression of atherosclerosis in the carotid bifurcation, and segmenting this region into its constituent branch arteries is necessary for analyses. The purpose of this study was to validate and demonstrate a method for segmenting the carotid bifurcation into the common, internal, and external carotid arteries (CCA, ICA, ECA) in contrast-enhanced MR angiography (CE-MRA) data. Methods A segmentation pipeline utilizing a convolutional neural network (DeepMedic) was tailored and trained for multi-class segmentation of the carotid arteries in CE-MRA data from the Swedish CardioPulmonsary bioImage Study (SCAPIS). Segmentation quality was quantitatively assessed using the Dice similarity coefficient (DSC), Matthews Correlation Coefficient (MCC), F2, F0.5, and True Positive Ratio (TPR). Segmentations were also assessed qualitatively, by three observers using visual inspection. Finally, geometric descriptions of the carotid bifurcations were generated for each subject to demonstrate the utility of the proposed segmentation method. Results Branch-level segmentations scored DSC = 0.80 ± 0.13, MCC = 0.80 ± 0.12, F2 = 0.82 ± 0.14, F0.5 = 0.78 ± 0.13, and TPR = 0.84 ± 0.16, on average in a testing cohort of 46 carotid bifurcations. Qualitatively, 61% of segmentations were judged to be usable for analyses without adjustments in a cohort of 336 carotid bifurcations without ground-truth. Carotid artery geometry showed wide variation within the whole cohort, with CCA diameter 8.6 ± 1.1 mm, ICA 7.5 ± 1.4 mm, ECA 5.7 ± 1.0 mm and bifurcation angle 41 ± 21°. Conclusion The proposed segmentation method automatically generates branch-level segmentations of the carotid arteries that are suitable for use in further analyses and help enable large-cohort investigations.

Download Full-text

Carotid Arteries: Maximizing Arterial to Venous Contrast in Fluoroscopically Triggered Contrast-enhanced MR Angiography with Elliptic Centric View Ordering

Radiology ◽

10.1148/radiology.211.1.r99ap08265 ◽

1999 ◽

Vol 211 (1) ◽

pp. 265-273 ◽

Cited By ~ 92

Author(s):

John Huston ◽

Sean B. Fain ◽

Stephen J. Riederer ◽

Alan H. Wilman ◽

Matt A. Bernstein ◽

...

Keyword(s):

Mr Angiography ◽

Carotid Arteries ◽

Contrast Enhanced

Download Full-text

Variations in the Branching Pattern of External Carotid Artery in South Kerala Population – A Cadaveric Study

Journal of Evidence Based Medicine and Healthcare ◽

10.18410/jebmh/2021/336 ◽

2021 ◽

Vol 8 (22) ◽

pp. 1780-1785

Author(s):

Manju Sudhakaran ◽

Mini Alikunju ◽

Vandana Latha Raveendran ◽

Umesan Kannanvilakom Govindapillai

Keyword(s):

Carotid Artery ◽

Head And Neck ◽

Carotid Arteries ◽

Carotid Bifurcation ◽

External Carotid Artery ◽

External Carotid ◽

Superior Thyroid Artery ◽

South Indian Population ◽

Branching Pattern ◽

South Indian

BACKGROUND External carotid arteries account for a major share of arterial supply of head and neck regions. As variations are frequently observed in the branching pattern of external carotid artery, surgeons, radiologists and anaesthetists often encounter difficulties in various procedures of head and neck. The purpose of this study is to describe the variations in the branching pattern of external carotid artery as observed in South Indian population which definitely reduces its iatrogenic injuries associated with surgical and radiological procedures of head and neck. METHODS This is cross-sectional descriptive study. Bilateral neck dissection was done on twenty-two formalin fixed cadavers to study the branching pattern of external carotid artery during a period of two years in the Department of Anatomy in Government Medical College, Alappuzha. Common carotid, external carotid and internal carotid arteries were dissected. All the branches of external carotid artery were traced and the variations were noted. The distance between carotid bifurcation and point of origin of individual branches of external carotid were measured and statistically analyzed. RESULTS In the present study along with normal branching pattern of external carotid artery, variations like origin of superior thyroid artery from common carotid artery and also from carotid bifurcation were seen. A common linguofacial trunk and direct origin of superior laryngeal artery from external carotid artery were also observed. CONCLUSIONS Prior knowledge of the variations will be helpful to surgeons and anaesthetists while dealing with these vessels during procedures of head and neck regions. KEYWORDS External Carotid Artery, Carotid Bifurcation, Superior Thyroid Artery, Linguofacial Trunk

Download Full-text

Abstract WP120: Measuring Carotid Stenosis With a Novel Non-contrast Enhanced MR Angiography Technique (SNAP): Comparison With Contrast-enhanced MR Angiography

Stroke ◽

10.1161/str.47.suppl_1.wp120 ◽

2016 ◽

Vol 47 (suppl_1) ◽

Author(s):

Hongge Shu ◽

Jie Sun ◽

Niranjan Balu ◽

Haining Liu ◽

Daniel S Hippe ◽

...

Keyword(s):

Carotid Stenosis ◽

Mr Angiography ◽

Carotid Arteries ◽

Weighted Kappa ◽

Intraplaque Hemorrhage ◽

Gadolinium Contrast ◽

Isotropic Resolution ◽

Contrast Enhanced ◽

Hemorrhage Risk ◽

Maximum Intensity Projections

Introduction: Contrast-enhanced MR angiography (CE-MRA) provides highly accurate measurement of carotid stenosis. But non-contrast techniques are desired as contrast agents may lead to anaphylaxis or nephrogenic system fibrosis. Recently, an inversion-recovery gradient echo sequence with phase-sensitive reconstruction was developed for assessment of lumen and intraplaque hemorrhage in one sequence - Simultaneous Noncontrast Angiography and intraPlaque hemorrhage (SNAP). Hypothesis: We tested the hypothesis that SNAP provides an accurate and reproducible assessment of carotid stenosis compared to CE-MRA. Methods: Fifty-eight subjects with 16-79% stenosis on ultrasound were scanned using a large-coverage (16 cm), isotropic-resolution (0.8 mm) SNAP sequence. Minimum intensity projections were generated at ten degrees increments to get 3D views of carotid arteries. Carotid stenosis was measured bilaterally according to the NASCET criteria by independent readers to estimate inter-reader reproducibility. To assess agreement between SNAP and CE-MRA, 24 subjects also underwent CE-MRA with same resolution (0.8 mm isotropic) after injection of gadolinium contrast (Magnevist). Maximum intensity projections were generated for CE-MRA and analyzed while blinded to SNAP data. Results: Of 116 carotid arteries imaged by SNAP, 10 (8.6%) were excluded by at least one reader due to poor image quality or insufficient coverage. Inter-reader reproducibility was high, yielding an intra-class correlation coefficient (ICC) of 0.95 (95% CI: 0.93, 0.96). When stenosis measurements were categorized as no/mild (0-29%), moderate (30-69%) and severe (70-99%), weighted kappa was 0.77 (95% CI: 0.66, 0.88). In the 48 arteries with CE-MRA images, agreement between SNAP and CE-MRA was excellent (ICC: 0.96, 95% CI: 0.92, 0.98; weighted kappa: 0.90, 95% CI: 0.79, 1.00). Conclusions: SNAP can be used to obtain accurate and reproducible measurement of extracranial carotid artery stenosis without gadolinium contrast. The ability of SNAP to assess both traditional (stenosis) and emerging (intraplaque hemorrhage) risk factors may promote its use in clinical workup of carotid stenosis.

Download Full-text

Fully Automated Segmentation of Lower Extremity Deep Vein Thrombosis Using Convolutional Neural Network

BioMed Research International ◽

10.1155/2019/3401683 ◽

2019 ◽

Vol 2019 ◽

pp. 1-7 ◽

Cited By ~ 1

Author(s):

Chen Huang ◽

Junru Tian ◽

Chenglang Yuan ◽

Ping Zeng ◽

Xueping He ◽

...

Keyword(s):

Deep Vein Thrombosis ◽

Lower Extremity ◽

Automatic Segmentation ◽

Ground Truth ◽

Dice Similarity Coefficient ◽

Vein Thrombosis ◽

Contrast Enhanced ◽

Fully Automatic ◽

Segmentation Task ◽

Deep Vein

Objective. Deep vein thrombosis (DVT) is a disease caused by abnormal blood clots in deep veins. Accurate segmentation of DVT is important to facilitate the diagnosis and treatment. In the current study, we proposed a fully automatic method of DVT delineation based on deep learning (DL) and contrast enhanced magnetic resonance imaging (CE-MRI) images. Methods. 58 patients (25 males; 28~96 years old) with newly diagnosed lower extremity DVT were recruited. CE-MRI was acquired on a 1.5 T system. The ground truth (GT) of DVT lesions was manually contoured. A DL network with an encoder-decoder architecture was designed for DVT segmentation. 8-Fold cross-validation strategy was applied for training and testing. Dice similarity coefficient (DSC) was adopted to evaluate the network’s performance. Results. It took about 1.5s for our CNN model to perform the segmentation task in a slice of MRI image. The mean DSC of 58 patients was 0.74± 0.17 and the median DSC was 0.79. Compared with other DL models, our CNN model achieved better performance in DVT segmentation (0.74± 0.17 versus 0.66±0.15, 0.55±0.20, and 0.57±0.22). Conclusion. Our proposed DL method was effective and fast for fully automatic segmentation of lower extremity DVT.

Download Full-text

Carotid Artery Stenosis: Comparison of 3D Time-of-Flight MR Angiography and Contrast-Enhanced MR Angiography at 3T

Radiology Research and Practice ◽

10.1155/2014/508715 ◽

2014 ◽

Vol 2014 ◽

pp. 1-5 ◽

Cited By ~ 1

Author(s):

Ivan Platzek ◽

Dominik Sieron ◽

Philipp Wiggermann ◽

Michael Laniado

Keyword(s):

Carotid Artery ◽

Carotid Artery Stenosis ◽

Mr Angiography ◽

Carotid Arteries ◽

Time Of Flight ◽

Internal Carotid Artery Stenosis ◽

Artery Stenosis ◽

Wilcoxon Test ◽

Tof Mra ◽

Contrast Enhanced

Purpose. The aim of this study was to assess the correlation of 3D time-of-flight MR angiography (TOF MRA) and contrast-enhanced MR angiography (CEMRA) for carotid artery stenosis evaluation at 3T.Material and Methods. Twenty-three patients (5 f, 18 m; mean age 61 y, age range 45–78 y) with internal carotid artery stenosis detected with ultrasonography were examined on a 3.0T MR system. The MR examination included both 3D TOF MRA and CEMRA of the carotid arteries. MR images were evaluated independently by two board-certified radiologists. Stenosis evaluation was based on a five-point scale. Stenosis grades determined by TOF and CEMRA were compared using Spearman’s rank correlation coefficient and the Wilcoxon test. Cohen’s Kappa was used to evaluate interrater reliability.Results. CEMRA detected stenosis in 24 (52%) of 46 carotids evaluated, while TOF detected stenosis in 27 (59%) of 46 carotids. TOF MRA yielded significantly higher results for stenosis grade in comparison to CEMRA (P=0.014). Interrater agreement was very good for both TOF MRA (κ=0.93) and CEMRA (κ=0.93).Conclusion. At 3T, 3D TOF MRA should not be used as replacement for contrast-enhanced MRA of the carotid arteries, as it results in significantly higher stenosis grades.

Download Full-text

Recessed elliptical-centric view-ordering for contrast-enhanced 3D MR angiography of the carotid arteries

Magnetic Resonance in Medicine ◽

10.1002/mrm.10235 ◽

2002 ◽

Vol 48 (3) ◽

pp. 419-424 ◽

Cited By ~ 22

Author(s):

R. Watts ◽

Y. Wang ◽

B. Redd ◽

P.A. Winchester ◽

K.C. Kent ◽

...

Keyword(s):

Mr Angiography ◽

Carotid Arteries ◽

Contrast Enhanced

Download Full-text

Variations, relations and clinical significance of carotid arterial system in anterior neck: a cadaveric study

International Journal of Research in Medical Sciences ◽

10.18203/2320-6012.ijrms20191311 ◽

2019 ◽

Vol 7 (4) ◽

pp. 1127

Author(s):

Anasuya Ghosh ◽

Subhramoy Chaudhury ◽

Atin Datta

Keyword(s):

Carotid Artery ◽

Carotid Arteries ◽

Internal Carotid ◽

Hypoglossal Nerve ◽

Carotid Bifurcation ◽

External Carotid Artery ◽

Arterial System ◽

External Carotid ◽

The Common ◽

Carotid Arterial

Background: The common carotid, internal and external carotid arteries and their branches serve as major source of blood supply in head-neck region of human and are often encountered during numerous surgical and clinical interventions of neck.Methods: We dissected and examined both sides of neck in 49 well embalmed cadavers (98 sides). We recorded the following anatomical parameters of carotid arterial system-level of bifurcation, the relation between internal and external carotid arteries, branching pattern of anterior branches of external carotid artery, tortuosity in carotid arterial system, and relation of hypoglossal nerve with the carotid arteries.Results: In 56.16 % cases, the common carotid arterial bifurcation took place at the upper border of thyroid cartilage though high bifurcation was quite common (43.88%). The external carotid artery was located antero-medial to internal carotid artery in most cases (93.87%). Abnormal tortuosity of carotid arterial system was detected in 2.04% cases only. In 86.73% cases, the hypoglossal nerve crossed the internal and external carotid artery superior to carotid bifurcation above the level of hyoid bone while in 1 case it crossed immediately inferior to carotid bifurcation. In branching pattern, following variations were observed- linguo-facial trunk in 15.3% cases, thyro-lingual trunk in 5.1% cases, origin of superior thyroid artery from common carotid in 10.02% cases and origin of superior thyroid from internal carotid in one case (1.02%).Conclusions: The carotid arterial system has complex and variable anatomy in neck and this information should be kept in mind to avoid unwanted damage during surgical procedures of neck.

Download Full-text