Segmentation of the heart and major vascular structures in cardiovascular CT images

Author(s):  
J. Peters ◽  
O. Ecabert ◽  
C. Lorenz ◽  
J. von Berg ◽  
M. J. Walker ◽  
...  
2016 ◽  
Vol 30 (1) ◽  
pp. 122-126
Author(s):  
Amit Agrawal ◽  
Reddy V. Umamaheshwara ◽  
Kishor V. Hegde ◽  
P. Suneetha ◽  
Divya Siddharth Kolikipudi

Abstract Encephaloceles are rare embryological mesenchymal developmental anomalies resulting from inappropriate ossification in skull through with herniation of intracranial contents of the sac. Encephaloceles are classified based on location of the osseous defect and contents of sac. Convexity encephalocele with osseous defect in occipital bone is called occipital encephalocele. Giant occipital encephaloceles can be sometimes larger than the size of baby skull itself and they pose a great surgical challenge. Occipital encephaloceles (OE) are further classified as high OE when defect is only in occipital bone above the foramen magnum, low OE when involving occipital bone and foramen magnum and occipito-cervical when there involvement of occipital bone, foramen magnum and posterior upper neural arches. Chiari III malformation can be associated with high or low occipital encephaloceles. Pre-operatively, it is essential to know the size of the sac, contents of the sac, relation to the adjacent structures, presence or absence of venous sinuses/vascular structures and osseous defect size. Sometimes it becomes imperative to perform both CT and MRI for the necessary information. Volume rendered CT images can depict the relation of osseous defect to foramen magnum and provide information about upper neural arches which is necessary in classifying these lesions.


2020 ◽  
pp. 1-11
Author(s):  
Bin Wang ◽  
Han Shi ◽  
Enuo Cui ◽  
Hai Zhao ◽  
Dongxiang Yang ◽  
...  

BACKGROUND: Tubular structure segmentation in chest CT images can reduce false positives (FPs) dramatically and improve the performance of nodules malignancy levels classification. OBJECTIVE: In this study, we present a framework that can segment the pulmonary tubular structure regions robustly and efficiently. METHODS: Firstly, we formulate a global tubular structure identification model based on Frangi filter. The model can recognize irregular vascular structures including bifurcation, small vessel, and junction, robustly and sensitively in 2D images. In addition, to segment the vessels from JVN, we design a local tubular structure identification model with a sliding window. Finally, we propose a multi-view voxel discriminating scheme on the basis of the previous two models. This scheme reduces the computational complexity of obtaining high entropy spatial tubular structure information. RESULTS: Experimental results have shown that the proposed framework achieves TPR of 85.79%, FPR of 24.83%, and ACC of 84.47% with the average elapsed time of 162.9 seconds. CONCLUSIONS: The framework provides an automated approach for effectively segmenting tubular structure from the chest CT images.


2016 ◽  
Vol 30 (1) ◽  
pp. 10-14 ◽  
Author(s):  
Ha Son Nguyen ◽  
Mohit Patel ◽  
Luyuan Li ◽  
Shekar Kurpad ◽  
Wade Mueller

Background Diminishing volume of intracranial cerebrospinal fluid (CSF) in patients with space-occupying masses have been attributed to unfavorable outcome associated with reduction of cerebral perfusion pressure and subsequent brain ischemia. Objective The objective of this article is to employ a ratio of CSF volume to brain volume for longitudinal assessment of space-volume relationships in patients with extra-axial hematoma and to determine variability of the ratio among patients with different types and stages of hematoma. Patients and methods In our retrospective study, we reviewed 113 patients with surgical extra-axial hematomas. We included 28 patients (age 61.7 +/− 17.7 years; 19 males, nine females) with an acute epidural hematoma (EDH) ( n = 5) and subacute/chronic subdural hematoma (SDH) ( n = 23). We excluded 85 patients, in order, due to acute SDH ( n = 76), concurrent intraparenchymal pathology ( n = 6), and bilateral pathology ( n = 3). Noncontrast CT images of the head were obtained using a CT scanner (2004 GE LightSpeed VCT CT system, tube voltage 140 kVp, tube current 310 mA, 5 mm section thickness) preoperatively, postoperatively (3.8 ± 5.8 hours from surgery), and at follow-up clinic visit (48.2 ± 27.7 days after surgery). Each CT scan was loaded into an OsiriX (Pixmeo, Switzerland) workstation to segment pixels based on radiodensity properties measured in Hounsfield units (HU). Based on HU values from −30 to 100, brain, CSF spaces, vascular structures, hematoma, and/or postsurgical fluid were segregated from bony structures, and subsequently hematoma and/or postsurgical fluid were manually selected and removed from the images. The remaining images represented overall brain volume—containing only CSF spaces, vascular structures, and brain parenchyma. Thereafter, the ratio between the total number of voxels representing CSF volume (based on values between 0 and 15 HU) to the total number of voxels representing overall brain volume was calculated. Results CSF/brain volume ratio varied significantly during the course of the disease, being the lowest preoperatively, 0.051 ± 0.032; higher after surgical evacuation of hematoma, 0.067 ± 0.040; and highest at follow-up visit, 0.083 ± 0.040 ( p < 0.01). Using a repeated regression analysis, we found a significant association ( p < 0.01) of the ratio with age (odds ratio, 1.019; 95% CI, 1.009–1.029) and type of hematoma (odds ratio, 0.405; 95% CI, 0.303–0.540). Conclusion CSF/brain volume ratio calculated from CT images has potential to reflect dynamics of intracranial volume changes in patients with space-occupying mass.


2013 ◽  
Vol 61 (S 01) ◽  
Author(s):  
M Hamiko ◽  
M Endlich ◽  
C Krämer ◽  
C Probst ◽  
A Welz ◽  
...  
Keyword(s):  

2019 ◽  
Author(s):  
K Herdinai ◽  
S Urbán ◽  
Z Besenyi ◽  
L Pávics ◽  
N Zsótér ◽  
...  

2020 ◽  
Author(s):  
A Király ◽  
S Urbán ◽  
Z Besenyi ◽  
L Pávics ◽  
N Zsótér ◽  
...  

Skull Base ◽  
2007 ◽  
Vol 16 (S 2) ◽  
Author(s):  
Moon Suh Park ◽  
Jae Yong Byun ◽  
Seung Gun Yeo ◽  
Chang Il Cha
Keyword(s):  

2020 ◽  
Vol 5 (5) ◽  

Background and Objective: Rosai-Dorfman disease (RDD) are usually misdiagnosed because of rarity and nonspecific clinical and radiological features. The aim of our study is to explore the clinical and imaging characteristics of RDD to improve diagnostic accuracy. Methods: Clinical and imaging data in 10 patients with RDD were retrospectively analyzed. 7 patients were underwent CT scanning and 3 patients were underwent MR examination. Results: 8 (8/10) patients presented with painless enlarged lymph nodes (LNs) or mass. 3 cases were involved with LNs, 5 cases were involved with extra-nodal tissues, and the remaining 2 cases were involved with LNs and extra-nodal tissue simultaneously. In enhanced CT images, enlarged LNs displayed mild or moderate enhancement, and 2 cases showed heterogeneous ring-enhancement. MR features of 3 patients with extra-nodal RDD, 2 cases showed a mass located in the subcutaneous and anterior abdominal wall respectively, and 1 case showed an intracranial mass. Besides, all lesions showed high signal foci on DWI images, and were characterized by marked heterogeneous enhancement with blurred edge. The dural/fascia tail sign and dilated blood vessels could be seen around all the lesions on enhanced MRI. Radiological features of 2 cases with LN and extranodal tissue involved, one case presented with the swelling and thickening of pharyngeal lymphoid ring and nasopharynx, meanwhile with enlarged LNs in bilateral submandibular area, neck and abdominal cavity, and also companied with osteolytic lesion in right proximal humerus. All these LNs displayed mild and moderate enhancement on CT images. Another case showed enlarged LNs in bilateral neck accompanied with soft tissue mass in the sinuses. Conclusions: RDD occurred commonly in young and middle-aged men and presented with painless enlarged LNs or mass.RDD had a huge diversity of imaging findings, which varied with different location. The radiological features, such as small patches of high signal foci in the masses on DWI images, heterogeneous enhancement and blood vessels around the masses, are helpful in diagnosis of extranodal RDD.


Sign in / Sign up

Export Citation Format

Share Document