Four-dimensional ultrasonography for dynamic bladder shape visualization and analysis during voiding

Detection of Vesicoureteral Reflux Using Electrical Impedance Tomography

OBJECTIVE

The purpose of this study is to detect vesicoureteral reflux (VUR) noninvasively using an electrical impedance tomography (EIT). VUR is characterized by the backflow of urine from the bladder to the kidneys.

METHODS

Using porcine models, small quantities of a solution mimicking the electrical properties of urine were infused into each ureter. EIT measurements were taken before, during and after the infusion using electrodes positioned around the abdomen. The collected data from 116 experiments were then processed and time-difference images reconstructed. Objective VUR detection was determined through statistical analysis of the mean change in the voltage signals and EIT image pixel intensities.

RESULTS

Unilateral VUR was successfully detected in 94.83% of all mean voltage signals and in over 98.28% of the reconstructed images. The images showed strong visual contrast between the region of interest and the background.

CONCLUSION

In animal models, EIT has the capability to detect reflux in the kidneys with high accuracy. The results show promise for EIT to be used for screening of VUR in children.

SIGNIFICANCE

VUR is the most common congenital urinary tract abnormality in children. The condition predisposes children to urinary tract infections and kidney damage. The current gold standard diagnostic test, a voiding cystourethrogram, is invasive and uses ionizing radiation; therefore, there is a need for new tools for identifying VUR in children. This study presents a noninvasive method to detect VUR in animal models, illustrating the potential for EIT as a screening tool in clinical scenarios.

Image-based classification of bladder state using electrical impedance tomography

OBJECTIVE

In this study, we examine the potential of using machine learning classification to determine the bladder state ('not full', 'full') with electrical impedance tomography (EIT) images of the pelvic region. Accurate classification of these states would enable urinary incontinence (UI) monitoring to alert the patient, before involuntary voiding occurs, in a low-cost and discrete manner.

APPROACH

Using both numerical and experimental data, we form datasets that contain diverse observations with varying clinical parameters such as bladder volume, urine conductivity, and the reference used for time-difference imaging. We then classify the bladder state using both pixel-wise and feature extraction-based classification techniques. We employ principal component analysis, wavelets, and image segmentation to help create features.

MAIN RESULTS

The performance was compared across several classifier algorithms. The minimum accuracy was 77.50%. The highest accuracy observed was 100%, and was found by combining principal component analysis and the Gaussian radial based function kernel support vector machine. This combination also offered the best trade-off between classification performance and the costs of training time and memory space. The biggest challenge in bladder state classification is classifying volumes near the separation volume of not full and full, in which choosing the most suitable classifier combination can minimize this error.

SIGNIFICANCE

We performed the first machine learning classification of bladder EIT images, achieving high classification accuracies with both numerical and experimental data. This work highlights the potential of using image-based machine learning with an EIT device to support bladder monitoring for those suffering from UI.

Supervised Learning Classifiers for Electrical Impedance-based Bladder State Detection

Urinary Incontinence affects over 200 million people worldwide, severely impacting the quality of life of individuals. Bladder state detection technology has the potential to improve the lives of people with urinary incontinence by alerting the user before voiding occurs. To this end, the objective of this study is to investigate the feasibility of using supervised machine learning classifiers to determine the bladder state of ‘full’ or ‘not full’ from electrical impedance measurements. Electrical impedance data was obtained from computational models and a realistic experimental pelvic phantom. Multiple datasets with increasing complexity were formed for varying noise levels in simulation. 10-Fold testing was performed on each dataset to classify ‘full’ and ‘not full’ bladder states, including phantom measurement data. Support vector machines and k-Nearest-Neighbours classifiers were compared in terms of accuracy, sensitivity, and specificity. The minimum and maximum accuracies across all datasets were 73.16% and 100%, respectively. Factors that contributed most to misclassification were the noise level and bladder volumes near the threshold of ‘full’ or ‘not full’. This paper represents the first study to use machine learning for bladder state detection with electrical impedance measurements. The results show promise for impedance-based bladder state detection to support those living with urinary incontinence.

A realistic pelvic phantom for electrical impedance measurement

OBJECTIVE

To design and fabricate an anatomically and conductively accurate phantom for electrical impedance studies of non-invasive bladder volume monitoring.

APPROACH

A modular pelvic phantom was designed and fabricated, consisting of a mechanically and conductively stable boundary wall, a background medium, and bladder phantoms. The wall and bladders are made of conductive polyurethane. The background material is an ultrasound gel-based mixture, with conductivity matched to a weighted average of the pelvic cavity organs, bone, muscle and fat. The phantom boundary is developed using a computer tomography model of a male human pelvis. The bladder phantoms were designed to correlate with human bladder dimensions. Electrical impedance measurements of the phantom were recorded, and images produced using six different bladder phantoms and a realistic finite element model.

MAIN RESULTS

Five different bladder volumes were successfully imaged using an empty bladder as a reference. The average conductivity index from the reconstructed images showed a strong positive correlation with the bladder phantom volumes.

SIGNIFICANCE

A conductively and anatomically accurate pelvic phantom was developed for non-invasive bladder volume monitoring using electrical impedance measurements. Several bladders were designed to correlate with actual human bladder volumes, allowing for accurate volume estimation. The conductivity of the phantom is accurate over 50-250 kHz. This phantom can allow changeable electrode location, contact and size; multi-layer electrodes configurations; increased complexity by addition of other organ or bone phantoms; and electrode movement and deformation. Overall, the pelvic phantom enables greater scope for experimentation and system refinement as a precursor to in-man clinical studies.

Monte Carlo Simulations for Dosimetry in Prostate Radiotherapy with Different Intravesical Volumes and Planning Target Volume Margins

In prostate radiotherapy, the influence of bladder volume variation on the dose absorbed by the target volume and organs at risk is significant and difficult to predict. In addition, the resolution of a typical medical image is insufficient for visualizing the bladder wall, which makes it more difficult to precisely evaluate the dose to the bladder wall. This simulation study aimed to quantitatively investigate the relationship between the dose received by organs at risk and the intravesical volume in prostate radiotherapy. The high-resolution Visible Chinese Human phantom and the finite element method were used to construct 10 pelvic models with specific intravesical volumes ranging from 100 ml to 700 ml to represent bladders of patients with different bladder filling capacities during radiotherapy. This series of models was utilized in six-field coplanar 3D conformal radiotherapy simulations with different planning target volume (PTV) margins. Each organ’s absorbed dose was calculated using the Monte Carlo method. The obtained bladder wall displacements during bladder filling were consistent with reported clinical measurements. The radiotherapy simulation revealed a linear relationship between the dose to non-targeted organs and the intravesical volume and indicated that a 10-mm PTV margin for a large bladder and a 5-mm PTV margin for a small bladder reduce the effective dose to the bladder wall to similar degrees. However, larger bladders were associated with evident protection of the intestines. Detailed dosimetry results can be used by radiation oncologists to create more accurate, individual water preload protocols according to the patient’s anatomy and bladder capacity.

ASSESSMENT OF VOIDING FUNCTION BY ENDOSCOPIC IMAGING — A PRELIMINARY REPORT

We report a novel method of reconstructing the 3D structure of the prostatic urethra and measuring its elasticity using endoscopic video images, and discuss their relation to clinical relevancy. Information regarding pixel color and brightness in the endoscopic video image is converted to relative distance between the object and the light source. An opened, 3D image of the prostatic urethra is obtained from a video image captured by the endoscope as it is slowly pulled through the urethra. The elasticity of the urethra is determined by recording a video image of the endoscope fixed in the prostatic urethra, with and without irrigation under water pressure of approximately 80 cm H 2 O . Angulation of the prostatic urethra is estimated by the number of intersections between the outline of protruded prostate and the midline of the urethra in patients with severe voiding dysfunction scheduled for transurethral resection of prostate, and in those scheduled for transurethral resection of bladder tumor without apparent discomfort during urination. The number of intersections showed a relationship with voiding symptoms. In conclusion, reconstruction of the 3D structure of the prostatic urethra from endoscopic video images is a feasible method that shows promise for estimating the mechanism of voiding dysfunction.