Brain tumors reduce life expectancy due to the lack of a cure. Moreover, their diagnosis involves complex and costly procedures such as magnetic resonance imaging (MRI) and lengthy, careful examination to determine their severity. However, the timely diagnosis of brain tumors in their early stages may save a patient’s life. Therefore, this work utilizes MRI with a machine learning approach to diagnose brain tumor severity (glioma, meningioma, no tumor, and pituitary) in a timely manner. MRI Gaussian and nonlinear scale features are extracted due to their robustness over rotation, scaling, and noise issues, which are common in image processing features such as texture, local binary patterns, histograms of oriented gradient, etc. For the features, each MRI is broken down into multiple small 8 × 8-pixel MR images to capture small details. To counter memory issues, the strongest features based on variance are selected and segmented into 400 Gaussian and 400 nonlinear scale features, and these features are hybridized against each MRI. Finally, classical machine learning classifiers are utilized to check the performance of the proposed hybrid feature vector. An available online brain MRI image dataset is utilized to validate the proposed approach. The results show that the support vector machine-trained model has the highest classification accuracy of 95.33%, with a low computational time. The results are also compared with the recent literature, which shows that the proposed model can be helpful for clinicians/doctors for the early diagnosis of brain tumors.

PURPOSE:

Veno-venous ECMO is indicated in reversible life-threatening respiratory failure without life-threatening circulatory failure. Recirculation of oxygenated blood in the ECMO circuit decreases efficiency of patient oxygen delivery but is difficult to measure. We seek to identify and quantify some of the factors responsible for recirculation in a simulation model and compare with clinical data.

METHODS:

A closed-loop real-time simulation model of the cardiovascular system has been developed. ECMO is simulated with a fixed flow pump 0 to 5 l/min with various cannulation sites - 1) right atrium to inferior vena cava, 2) inferior vena cava to right atrium, and 3) superior+inferior vena cava to right atrium. Simulations are compared to data from a retrospective cohort of 11 consecutive adult veno-venous ECMO patients in our department.

RESULTS:

Recirculation increases with increasing ECMO-flow, decreases with increasing cardiac output, and is highly dependent on choice of cannulation sites. A more peripheral drainage site decreases recirculation substantially.

CONCLUSIONS:

Simulations suggest that recirculation is a significant clinical problem in veno-venous ECMO in agreement with clinical data. Due to the difficulties in measuring recirculation and interpretation of the venous oxygen saturation in the ECMO drainage blood, flow settings and cannula positioning should rather be optimized with help of arterial oxygenation parameters. Simulation may be useful in quantification and understanding of recirculation in VV-ECMO.

Background: Computer technology enables realistic simulation of cardiovascular physiology. The increasing number of clinical surgical and medical treatment options imposes a need for better understanding of patient-specific pathology and outcome prediction. Methods: A distributed lumped parameter real-time closed-loop model with 26 vascular segments, cardiac modelling with time-varying elastance functions and gradually opening and closing valves, the pericardium, intrathoracic pressure, the atrial and ventricular septum, various pathological states and including oxygen transport has been developed. Results: Model output is pressure, volume, flow and oxygen saturation from every cardiac and vascular compartment. The model produces relevant clinical output and validation of quantitative data in normal physiology and qualitative directions in simulation of pathological states show good agreement with published data. Conclusion: The results show that it is possible to build a clinically relevant real-time computer simulation model of the normal adult cardiovascular system. It is suggested that understanding qualitative interaction between physiological parameters in health and disease may be improved by using the model, although further model development and validation is needed for quantitative patient-specific outcome prediction.

Accurate prostate cancer localization with noninvasive imaging can be used to guide biopsy, radiotherapy and surgery as well as to monitor disease progression [1]. Published studies have shown multispectral magnetic resonance imaging (MRI), i.e., a combination of multiple types of MR images, as a promising noninvasive imaging technique for the localization of prostate cancer.

This paper presents a tumor detecting system that allows interactive 3D tumor visualization and tumor volume measurements. An improved level set method is proposed to automatically segment the tumor images slice by slice. PET images are used to detect the tumor while CT images make a 3D representation of the patient's body possible. An initial slice with a seed within the tumor is firstly chosen by the operator. The system then performs automatically the tumor volume segmentation that allows the clinician to visualize the tumor, to measure it and to evaluate the best medical treatment adapted to the patient.

This article describes a new method for ancient books ornamental letters segmentation and recognition. The purpose of our work is to automatically determine the letter represented in an ornamental letter image. Our process is divided in two parts: a segmentation step of the ornamental letter is followed by a recognition step. The segmentation process uses multiresolution analysis to filter background decorations followed by a binarisation step and a morphologic reconstruction of the expected letter. The recognition process use the previously obtained reconstruction and compares it with capital letters images used as a dictionary of shapes with the Local Dissimilarity Map (LDM) distance.

There are advantages of using a polymeric shelled contrast agent (CA) during ultrasound imaging instead of lipid shelled CA, e.g. particles can be attached to the surface, which enables an introduction of antibodies to the surface making the CA target specific. For this application it is essential to have a sensitive imaging technique suitable for polymeric CA. However, previously presented results have indicated difficulties in visualizing polymeric CA with commercially available contrast algorithms. Therefore a new subtraction algorithm (SA), was developed that define the difference between contrast and reference images. The aim of this study was to evaluate the response from a polymeric CA, when using the SA and compare it with existing contrast algorithms. Moreover, the possibility to detect a thin layer of CA was tested using the SA.

Ultrasound short-axis images of a tissue-mimicking vessel phantom with a pulsating flow were obtained using a GE Vivid7 system (M12L) and a Philips iE33 system (S5-1). Repeated (n=91) contrast to tissue ratios (CTR) calculated at various mechanical index (MI) using the contrast algorithms pulse inversion (PI), power modulation (PM) and SA at a concentration of 10⁵microbubbles/ml.

The developed SA showed improvements in CTR compared to existing contrast algorithms. The CTRs were -0.99 dB ± 0.67 (MI 0.2), 9.46 dB ± 0.77 (MI 0.4) and 2.98 dB ± 0.60 (MI 0.8) with PI, 8.17 dB ± 1.15 (MI 0.2), 15.60 dB ± 1.29 (MI0.4) and 11.60 dB ± 0.73 (MI 0.8) with PM and 14.97 dB ± 3.97 (MI 0.2), 20.89 dB ± 3.54 (MI 0.4) and 21.93 dB ± 4.37 (MI 0.8) with the SA. In addition to this, the layer detection, when using the SA was successful.

Background

A novel polymer-shelled contrast agent (CA) with high mechanical and chemical stability was recently developed [1]. In excess to its ultrasound properties, it also supports targeted and multimodal imaging [2-4]. Even though these new possibilities have the potential to lead to new methodologies and approaches for non-invasive diagnosis, it is important that the fundamental diagnostic features in contrast-enhanced ultrasound are preserved. The aim of this study was therefore to examine the clinical use of the polymer-shelled CA by analyzing the left ventricular endocardial border delineation capability in a porcine model. In addition, physiological effects due to CA injections were studied.

Methods

The endocardial border delineation capability was assessed in a comparative study, which included three doses (1.5 ml, 3 ml and 5 ml, [5x108 MBs/ml]) of the polymer-shelled CA and the commercially available CA SonoVue® (1.5 ml, [2-5x108 MBs/ml]). Ultrasound images of the left ventricle were evaluated manually by blinded observers (n=3) according to a 6-segment model, in which each segment was graded as 0=not visible, 1=barely visible or 2=well visible, as well as semi-automatically by a segmentation software. Furthermore, duration of clinically useful contrast enhancement and changes in physiological parameters were evaluated.

Results

For the highest dose of the polymer-shelled CA, the obtained segment scores, time for clinically sufficient contrast enhancement and semi-automatic delineation capability were comparable to SonoVue®. Moreover, neither dose of the polymer-shelled CA did affect the physiological parameters.

Conclusion

This study demonstrated that the polymer-shelled CA can be used in contrast-enhanced diagnostic imaging without influence on major physiological parameters.

Arterial stiffness is an independent risk factor found to correlate with a wide range of cardiovascular diseases. It has been suggested that shear wave elastography (SWE) can be used to quantitatively measure local arterial shear modulus, but an accuracy assessment of the technique for arterial applications has not yet been performed. In this study, the influence of confined geometry on shear modulus estimation, by both group and phase velocity analysis, was assessed, and the accuracy of SWE in comparison with mechanical testing was measured in nine pressurized arterial phantoms. The results indicated that group velocity with an infinite medium assumption estimated shear modulus values incorrectly in comparison with mechanical testing in arterial phantoms (6.7 +/- 0.0 kPa from group velocity and 30.5 +/- 0.4 kPa from mechanical testing). To the contrary, SWE measurements based on phase velocity analysis (30.6 +/- 3.2 kPa) were in good agreement with mechanical testing, with a relative error between the two techniques of 8.8 +/- 6.0% in the shear modulus range evaluated (40-100 kPa). SWE by phase velocity analysis was validated to accurately measure stiffness in arterial phantoms.

Determining plaque vulnerability is critical when selecting the most suitable treatment for patients with atherosclerotic plaque. Currently, clinical non-invasive ultrasound-based methods for plaque characterization are limited to visual assessment of plaque morphology and new quantitative methods are needed. In this study, shear wave elastography (SWE) was used to characterize hard and soft plaque mimicking inclusions in six common carotid artery phantoms by using phase velocity analysis in static and dynamic environments. The results were validated with mechanical tensile testing. In the static environment, SWE measured a mean shear modulus of 5.8±0.3kPa and 106.2±17.2kPa versus 3.3±0.5kPa and 98.3±3.4kPa measured by mechanical testing in the soft and hard plaques respectively. Furthermore, it was possible to measure the plaques' shear moduli throughout a simulated cardiac cycle. The results show good agreement between SWE and mechanical testing and indicate the possibility for in vivo arterial plaque characterization using SWE.

1. Introduction

Shear Wave Elastography (SWE) is a recently developed noninvasive method for elastography assessment using ultrasound. The technique consists of sending an acoustic radiation force (pushing sequence) into the tissue that in turn generates an orthogonal low frequency propagating shear wave. The shear wave propagation is measured real time by high speed B-mode imaging. From the B-mode images, the shear wave is tracked via normalized cross-correlation and the speed is calculated, which is used to generate an elasticity map of the tissue’s shear modulus. To date, the technique has mostly been used in large homogeneous tissues such as breast and liver where it successfully detects lesions and tumors that are easily missed with normal B-mode ultrasound [1]. SWE could potentially be applied in vascular applications to assess elasticity of the arterial wall to characterize the stiffness as an early indicator of cardiac disease. Furthermore, SWE could aid in the characterization of plaques in the carotid artery, which is critical for the prevention of ischemic stroke

2. Methods and Results

An initial study was performed using an Aixplorer SWE system (Supersonic Imagine, France) to measure the shear modulus in a polyvinyl alcohol phantom (PVA) vessel with a plaque inclusion (Figure 1). It was possible to distinguish the softer inclusion mean shear wave speed (2.1 m/s) from the arterial wall (3.5 m/s) on the SWE colour-map, but the Young’s Modulus calculation of the arterial wall (E=19.8 kPa) did not match the measured Young’s Modulus (E=53.1 kPa) from comparative mechanical testing.</p><p>We have begun implementing various pushing sequences (single unfocused push, single focused push, line push, comb push) on a programmable ultrasound machine (Verasonics, USA) using a linear transducer (Philips L7-4) in a homogeneous PVA phantom. An algorithm for one dimensional cross-correlation tracking and shear wave speed estimation has been developed and initially tested in an experimental setup

3. Discussion

According to our initial results, it is possible that SWE could be applied in vascular applications. However, the initial mechanical testing vs. SWE comparison indicated that further development to the post processing is needed before applying it on the carotid artery, which is a heterogeneous tissue with other wave propagation properties than e.g. breast tissue. The carotid artery has a difficult geometry to study for several reasons. The intima-media complex is very thin (&lt; 1mm), and the vessel wall is not stationary. Furthermore, the cylindrical shape of the artery produces complex wave reflections within the arterial wall, which result in a polychromatic propagation of the shear wave. A few studies have applied techniques based on SWE to the arterial wall with promising results and a pilot study demonstrating the feasibility of the technique in-vivo has been published [2]. Still, a considerable effort is needed to validate and optimize the technique for the clinical vascular setting.