Development and evaluation of automated ultrasonographic detection of bladder diameter for estimation of bladder urine volume

Portable Ultrasound Bladder Volume Measurement Over Entire Volume Range Using a Deep Learning Artificial Intelligence Model in a Selected Cohort: A Proof of Principle Study

OBJECTIVE

We aimed to prospectively investigate whether bladder volume measured using deep learning artificial intelligence (AI) algorithms (AI-BV) is more accurate than that measured using conventional methods (C-BV) if using a portable ultrasound bladder scanner (PUBS).

PATIENTS AND METHODS

Patients who underwent filling cystometry because of lower urinary tract symptoms between January 2021 and July 2022 were enrolled. Every time the bladder was filled serially with normal saline from 0 mL to maximum cystometric capacity in 50 mL increments, C-BV was measured using PUBS. Ultrasound images obtained during this process were manually annotated to define the bladder contour, which was used to build a deep learning AI model. The true bladder volume (T-BV) for each bladder volume range was compared with C-BV and AI-BV for analysis.

RESULTS

We enrolled 250 patients (213 men and 37 women), and a deep learning AI model was established using 1912 bladder images. There was a significant difference between C-BV (205.5 ± 170.8 mL) and T-BV (190.5 ± 165.7 mL) (p = 0.001), but no significant difference between AI-BV (197.0 ± 161.1 mL) and T-BV (190.5 ± 165.7 mL) (p = 0.081). In bladder volume ranges of 101-150, 151-200, and 201-300 mL, there were significant differences in the percentage of volume differences between [C-BV and T-BV] and [AI-BV and T-BV] (p < 0.05), but no significant difference if converted to absolute values (p > 0.05). C-BV (R2 = 0.91, p < 0.001) and AI-BV (R2 = 0.90, p < 0.001) were highly correlated with T-BV. The mean difference between AI-BV and T-BV (6.5 ± 50.4) was significantly smaller than that between C-BV and T-BV (15.0 ± 50.9) (p = 0.001).

CONCLUSION

Following image pre-processing, deep learning AI-BV more accurately estimated true BV than conventional methods in this selected cohort on internal validation. Determination of the clinical relevance of these findings and performance in external cohorts requires further study.

TRIAL REGISTRATION

The clinical trial was conducted using an approved product for its approved indication, so approval from the Ministry of Food and Drug Safety (MFDS) was not required. Therefore, there is no clinical trial registration number.

Anticipating impending peripheral intravenous catheter failure: A diagnostic accuracy observational study combining ultrasound and artificial intelligence to improve clinical care

OBJECTIVE

Peripheral intravenous catheter (PIVC) failure occurs in approximately 50% of insertions. Unexpected PIVC failure leads to treatment delays, longer hospitalizations, and increased risk of patient harm. In current practice there is no method to predict if PIVC failure will occur until it is too late and a grossly obvious complication has occurred. The aim of this study is to demonstrate the diagnostic accuracy of a predictive model for PIVC failure based on artificial intelligence (AI).

METHODS

This study evaluated the capabilities of a novel machine learning algorithm. The algorithm was trained using real-world ultrasound videos of PIVC sites with a goal of predicting which PIVCs would fail within the following day. After training, AI models were validated using another, unseen, collection of real-world ultrasound videos of PIVC sites.

RESULTS

2133 ultrasound videos (361 failure and 1772 non-failure) were used for algorithm development. When the algorithm was tasked with predicting failure in the unseen collection of videos, the best achieved results were an accuracy of 0.93, sensitivity of 0.77, specificity of 0.98, positive predictive value of 0.91, negative predictive value of 0.93, and area under the curve of 0.87.

CONCLUSIONS

This proprietary and novel machine learning algorithm can accurately and reliably predict PIVC failure 1 day prior to clinically evident failure. Implementation of this technology in the patient care setting would provide timely information for clinicians to plan and manage impending device failure. Future research on the use of AI technology and PIVCs should focus on improving catheter function and longevity, while limiting complication rates.

Bladder ultrasound: evidence of content validity of a checklist for training nurses

OBJECTIVES

to develop and analyze evidence of content validity of a checklist for training nurses in measuring bladder volume through ultrasound.

METHODS

a methodological study, consisting of three stages: literature review; instrument item preparation; and analysis of evidence of content validity. The Content Validity Index (CVI) and Gwet's AC2 were used for content validity analyses.

RESULTS

the checklist consisted of 23 items. The CVIs for clarity, relevance and dimensionality were 0.99, 0.99 and 0.98 respectively, and the CVIs for Gwet's AC2 with coefficients for clarity, relevance and dimensionality were 0.89, 0.97 and 0.95, respectively, with p<0.001.

CONCLUSIONS

the checklist developed for training nurses in measuring bladder volume through ultrasound achieved adequate evidence of content validity, and can be used to train nurses in clinical practice and future research.

Development of an e-learning program for biofeedback in pelvic floor muscle training for adult women using self-performed ultrasound: An observational study

INTRODUCTION

Pelvic floor muscle training (PFMT) for urinary incontinence (UI) is recommended in combination with biofeedback to visualize pelvic floor muscles. The focus is on non-invasive hand-held ultrasound (US) measurement methods for PFMT, which can be performed at home. Recently, self-performed US measurements in which the patient applies the US to themself have gradually spreading. This study aimed to develop an educational program for the biofeedback method using self-performed US and to evaluate its feasibility.

METHODS

This study was an observational study. The ADDIE model (Analysis, Design, Development, Implementation, and Evaluation) was utilized to create an e-learning program for women aged ≥40 years with UI. Participants self-performed bladder US via e-learning, using a hand-held US device with a convex probe. The primary outcome was the number of times the bladder area was successfully extracted using an existing automatic bladder area extraction system. The secondary outcome was the total score of the technical evaluation of the self-performed US, which was evaluated across three proficiency levels. Descriptive statistics were conducted for participant characteristics, presenting categorical variables as percentages and continuous variables as means ± SD.

RESULTS

We included 11 participants with a mean age of 56.2 years. Nine participants were able to record US videos, and two were unable to record bladder videos. Regarding the technical evaluation scores, all participants scored ≥80%; four had perfect scores.

CONCLUSIONS

This study showed that transabdominal self-performed bladder US can be performed in 81.8% of women with UI in their 40-60s by using an e-learning program.

Intelligent Bladder Volume Monitoring for Wearable Ultrasound Devices: Enhancing Accuracy Through Deep Learning-Based Coarse-to-Fine Shape Estimation

Accurate and continuous bladder volume monitoring is crucial for managing urinary dysfunctions. Wearable ultrasound (US) devices offer a solution by enabling noninvasive and real-time monitoring. Previous studies have limitations in power consumption and computation cost or quantitative volume estimation capability. To alleviate this, we present a novel pipeline that effectively integrates conventional feature extraction and deep learning (DL) to achieve continuous quantitative bladder volume monitoring efficiently. Particularly, in the proposed pipeline, bladder shape is coarsely estimated by a simple bladder wall detection algorithm in wearable devices, and the bladder wall coordinates are wirelessly transferred to an external server. Subsequently, a roughly estimated bladder shape from the wall coordinates is refined in an external server with a diffusion-based model. With this approach, power consumption and computation costs on wearable devices remained low, while fully harnessing the potential of DL for accurate shape estimation. To evaluate the proposed pipeline, we collected a dataset of bladder US images and RF signals from 250 patients. By simulating data acquisition from wearable devices using the dataset, we replicated real-world scenarios and validated the proposed method within these scenarios. Experimental results exhibit superior improvements, including +9.32% of IoU value in 2-D segmentation and -22.06 of RMSE in bladder volume regression compared to state-of-the-art (SOTA) performance from alternative methods, emphasizing the potential of this approach in continuous bladder volume monitoring in clinical settings. Therefore, this study effectively bridges the gap between accurate bladder volume estimation and the practical deployment of wearable US devices, promising improved patient care and quality of life.

Effects of ultrasound with an automatic vessel detection system using artificial intelligence on the selection of puncture points among ultrasound beginner clinical nurses

BACKGROUND

Ultrasound guidance increases the success rate of peripheral intravenous catheter placement. However, the longer time required to obtain ultrasound-guided access poses difficulties for ultrasound beginners. Notably, interpretation of ultrasonographic images is considered as one of the main reasons of difficulty in using ultrasound for catheter placement. Therefore, an automatic vessel detection system (AVDS) using artificial intelligence was developed. This study aimed to investigate the effectiveness of AVDS for ultrasound beginners in selecting puncture points and determine suitable users for this system.

METHODS

In this crossover experiment involving the use of ultrasound with and without AVDS, we enrolled 10 clinical nurses, including 5 with some experience in peripheral intravenous catheterization using ultrasound-aided methods (categorized as ultrasound beginners) and 5 with no experience in ultrasound and less experience in peripheral intravenous catheterization using conventional methods (categorized as inexperienced). These participants chose two puncture points (those with the largest and second largest diameter) as ideal in each forearm of a healthy volunteer. The results of this study were the time required for the selection of puncture points and the vein diameter of the selected points.

RESULTS

Among ultrasound beginners, the time required for puncture point selection in the right forearm second candidate vein with a small diameter (<3 mm) was significantly shorter when using ultrasound with AVDS than when using it without AVDS (mean, 87 vs 247 s). Among inexperienced nurses, no significant difference in the time required for all puncture point selections was found between the use of ultrasound with and without AVDS. In the vein diameter, significant difference was shown only in the absolute difference at left second candidate among inexperienced participants.

CONCLUSION

Ultrasonography beginners needed less time to select the puncture points in a small diameter vein using ultrasound with AVDS than without AVDS.

Evaluating Accuracy of Rectal Fecal Stool Assessment Using Transgluteal Cleft Approach Ultrasonography

BACKGROUND

Transabdominal ultrasound is used to detect fecal impaction, but the rectum is difficult to visualize without bladder urine or with gastrointestinal gas.

OBJECTIVE

We developed a transgluteal cleft approach that is unaffected by these factors and sought to determine if our ultrasound method could detect and classify fecal matter in the lower rectum using this approach.

METHODS

We classified ultrasound images from hospitalized patients into four groups: Group 1 (bowed and rock-like echogenic areas), Group 2 (irregular and cotton candy-like hyperechoic areas), Group 3 (flat and mousse-like hyperechoic areas), and Group 4 (linear echogenic areas in the lumen). Stool characteristics were classified as hard, normal, and muddy/watery. Sensitivity and specificity were determined based on fecal impaction and stool classification accuracy.

RESULTS

We obtained 129 ultrasound images of 23 patients. The sensitivity and specificity for fecal retention in the rectum were both 100.0%. The recall rates were 71.8% for Group 1, 93.1% for Group 2, 100.0% for Group 3, and 100.0% for Group 4. The precision rates were 96.6% for Group 1, 71.1% for Group 2, 88.9% for Group 3, and 100.0% for Group 4. Our method was 89.9% accurate overall.

CONCLUSION

Transgluteal cleft approach ultrasound scanning can detect and classify fecal properties with high accuracy.

Pelvic floor muscle contraction automatic evaluation algorithm for pelvic floor muscle training biofeedback using self-performed ultrasound

INTRODUCTION

Non-invasive biofeedback of pelvic floor muscle training (PFMT) is required for continuous training in home care. Therefore, we considered self-performed ultrasound (US) in adult women with a handheld US device applied to the bladder. However, US images are difficult to read and require assistance when using US at home. In this study, we aimed to develop an algorithm for the automatic evaluation of pelvic floor muscle (PFM) contraction using self-performed bladder US videos to verify whether it is possible to automatically determine PFM contraction from US videos.

METHODS

Women aged ≥ 20 years were recruited from the outpatient Urology and Gynecology departments of a general hospital or through snowball sampling. The researcher supported the participants in their self-performed bladder US and videos were obtained several times during PFMT. The US videos obtained were used to develop an automatic evaluation algorithm. Supervised machine learning was then performed using expert PFM contraction classifications as ground truth data. Time-series features were generated from the x- and y-coordinate values of the bladder area including the bladder base. The final model was evaluated for accuracy, area under the curve (AUC), recall, precision, and F1. The contribution of each feature variable to the classification ability of the model was estimated.

RESULTS

The 1144 videos obtained from 56 participants were analyzed. We split the data into training and test sets with 7894 time series features. A light gradient boosting machine model (Light GBM) was selected, and the final model resulted in an accuracy of 0.73, AUC = 0.91, recall = 0.66, precision = 0.73, and F1 = 0.73. Movement of the y-coordinate of the bladder base was shown as the most important.

CONCLUSION

This study showed that automated classification of PFM contraction from self-performed US videos is possible with high accuracy.

Proof-of-Concept of Microwave-Based Bladder State Detection Using Realistic Pelvic Models

Goal: Urinary incontinence (UI) affects a significant proportion of the population and is associated with negative physical and psychological side-effects. Microwave-based technologies may have the potential to monitor bladder volume, providing a proactive, low-cost and non-invasive tool to support individuals with UI. Methods: Studies to date on microwave bladder monitoring have been limited to highly simplified computational and experimental scenarios. In this work, we study the most realistic models to date (both male and female), which incorporate dielectrically and anatomically representative tissues of the pelvic region. Results: We examine the ability of detecting bladder fullness through both reflection and transmission-based parameters and, for the first time, study the effect of urine permittivity. As a proof-of-concept of bladder state detection, we further investigate reconstructing differential radar images of the bladder with two different volumes of urine. Conclusions: The results indicate that there is strong potential for monitoring and detecting the bladder state using microwave measurements.

Concurrent multi-session anodal trans-cranial direct current stimulation enhances pelvic floor muscle training effectiveness for female patients with multiple sclerosis suffering from urinary incontinence and pelvic floor dysfunction: a randomized clinical trial study

INTRODUCTION AND HYPOTHESIS

Urinary incontinence following a pelvic floor muscle (PFM) dysfunction is a common disorder in women with multiple sclerosis (MS). Concurrent anodal transcranial direct current stimulation (a-tDCS) of the primary motor cortex (M1) may prime the effects of PFM training (PFMT) in MS patients. This study was aimed at investigating the effects of M1 a-tDCS on the effectiveness of PFMT in the treatment of female MS patients with urinary incontinence and PFM dysfunctions.

METHODS

In a randomized double-blinded, control trial study, 30 women with MS were divided into two groups (experimental group: concurrent active M1 a-tDCS and PFMT; control group: concurrent sham M1 a-tDCS and PFMT). Over the course of 8 weeks, these patients received 20-min interventions three times a week. As an indication of PFM function, the bladder base displacement was measured by ultrasonography before, during the 4th week, immediately, and 1 month after the intervention ended. Urinary incontinence was also measured by Incontinence Questionnaire-Urinary Incontinence Short Form (ICIQ-UISF) before, immediately, and 1 month after the intervention ended.

RESULTS

A significant improvement in PFM function occurred in the 4th week of intervention and remained 1 month after the intervention in the experimental group when compared with the control group (p<0.05). Compared with baseline, both groups reported significant improvements in PFM function at 8 weeks (p<0.05). Also, both groups were found to have decreased ICIQ-UIS scores after the intervention and at 1-month follow-up (p<0.05).

CONCLUSIONS

In MS patients, M1 a-tDCS can significantly enhance the effects of PFMT on the PFM function and urinary incontinence.

A Lightweight Deep Learning Network on a System-on-Chip for Wearable Ultrasound Bladder Volume Measurement Systems: Preliminary Study

Bladder volume assessments are crucial for managing urinary disorders. Ultrasound imaging (US) is a preferred noninvasive, cost-effective imaging modality for bladder observation and volume measurements. However, the high operator dependency of US is a major challenge due to the difficulty in evaluating ultrasound images without professional expertise. To address this issue, image-based automatic bladder volume estimation methods have been introduced, but most conventional methods require high-complexity computing resources that are not available in point-of-care (POC) settings. Therefore, in this study, a deep learning-based bladder volume measurement system was developed for POC settings using a lightweight convolutional neural network (CNN)-based segmentation model, which was optimized on a low-resource system-on-chip (SoC) to detect and segment the bladder region in ultrasound images in real time. The proposed model achieved high accuracy and robustness and can be executed on the low-resource SoC at 7.93 frames per second, which is 13.44 times faster than the frame rate of a conventional network with negligible accuracy drawbacks (0.004 of the Dice coefficient). The feasibility of the developed lightweight deep learning network was demonstrated using tissue-mimicking phantoms.

Automatic vein measurement by ultrasonography to prevent peripheral intravenous catheter failure for clinical practice using artificial intelligence: development and evaluation study of an automatic detection method based on deep learning

OBJECTIVES

Complications due to peripheral intravenous catheters (PIVC) can be assessed using ultrasound imaging; however, it is not routinely conducted due to the need for training in image reading techniques. This study aimed to develop and validate a system that automatically measures blood vessel diameters on ultrasound images using artificial intelligence (AI) and provide recommendations for selecting an implantation site.

DESIGN

Pilot study.

SETTING

The University of Tokyo Hospital, Japan.

PRIMARY AND SECONDARY OUTCOME MEASURES

First, based on previous studies, the vessel diameter was calculated as the mean value of the maximum long diameter plus the maximum short diameter orthogonal to it. Second, the size of the PIVC to be recommended was evaluated based on previous studies. For the development and validation of an automatic detection tool, we used a fully convoluted network for automatic estimation of vein location and diameter. The agreement between manually generated correct data and automatically estimated data was assessed using Pearson's product correlation coefficient, systematic error was identified using the Bland-Altman plot, and agreement between catheter sizes recommended by the research nurse and those recommended by the system was evaluated.

RESULTS

Through supervised machine learning, automated determination was performed using 998 ultrasound images, of which 739 and 259 were used as the training and test data set, respectively. There were 24 false-negatives indicating no arteries detected and 178 true-positives indicating correct detection. Correlation of the results between the system and the nurse was calculated from the 178 images detected (r=0.843); no systematic error was identified. The agreement between the sizes of the PIVC recommended by the research nurse and the system was 70.2%; 7% were underestimated and 21.9% were overestimated.

CONCLUSIONS

Our automated AI-based image processing system may aid nurses in assessing peripheral veins using ultrasound images for catheterisation; however, further studies are still warranted.t.

Portable Ultrasound Research System for Use in Automated Bladder Monitoring with Machine-Learning-Based Segmentation

We developed a new mobile ultrasound device for long-term and automated bladder monitoring without user interaction consisting of 32 transmit and receive electronics as well as a 32-element phased array 3 MHz transducer. The device architecture is based on data digitization and rapid transfer to a consumer electronics device (e.g., a tablet) for signal reconstruction (e.g., by means of plane wave compounding algorithms) and further image processing. All reconstruction algorithms are implemented in the GPU, allowing real-time reconstruction and imaging. The system and the beamforming algorithms were evaluated with respect to the imaging performance on standard sonographical phantoms (CIRS multipurpose ultrasound phantom) by analyzing the resolution, the SNR and the CNR. Furthermore, ML-based segmentation algorithms were developed and assessed with respect to their ability to reliably segment human bladders with different filling levels. A corresponding CNN was trained with 253 B-mode data sets and 20 B-mode images were evaluated. The quantitative and qualitative results of the bladder segmentation are presented and compared to the ground truth obtained by manual segmentation.

Forward-Looking Ultrasound Wearable Scanner System for Estimation of Urinary Bladder Volume

Accurate measurement of bladder volume is an important tool for evaluating bladder function. In this study, we propose a wearable bladder scanner system that can continuously measure bladder volume in daily life for urinary patients who need urodynamic studies. The system consisted of a 2-D array, which included integrated forward-looking piezoelectric transducers with thin substrates. This study aims to estimate the volume of the bladder using a small number of piezoelectric transducers. A least-squares method was implemented to optimize an ellipsoid in a quadratic surface equation for bladder volume estimation. Ex-vivo experiments of a pig bladder were conducted to validate the proposed system. This work presents the potential of the approach for wearable bladder monitoring, which has similar measurement accuracy compared to the commercial bladder imaging system. The wearable bladder scanner can be improved further as electronic voiding diaries by adding a few more features to the current function.

Evaluation of a Point-of-Care Ultrasound Educational Program for Nurse Educators

BACKGROUND

The effectiveness of point-of-care ultrasound (POCUS) for nurses has been demonstrated; however, only a limited number of nurses have been trained to perform POCUS. This article reports on a POCUS train-the-trainer program for nurse educators that targets lower urinary track dysfunction.

METHOD

Nurse educators (n = 38) were invited to participate in a POCUS train-the-trainer program, which comprised an e-learning module and a hands-on seminar. Acquisition of knowledge and skills were assessed after the module and seminar, respectively.

RESULTS

Questions from the "Basic Knowledge of Ultrasonography" test were answered correctly at a rate of 93.0% (SD, 8.5%). Measured values of bladder urinary volume using ultrasonography were in close agreement with actual values. All of the participants indicated that the program covered the content necessary to use in practice.

CONCLUSION

The POCUS train-the-trainer program equips nurse educators with the knowledge and skills needed for training nurses at their institutions. [J Contin Educ Nurs. 2021;52(8):375-381.].

Novel Three-Dimensional Bladder Reconstruction Model from B-Mode Ultrasound Image to Improve the Accuracy of Bladder Volume Measurement

Traditional bladder volume measurement from B-mode (two-dimensional) ultrasound has been found to produce inaccurate results, and thus in this work we aim to improve the accuracy of measurement from B-mode ultrasound. A total of 75 electronic medical records including ultrasonic images were reviewed retrospectively from 64 patients. We put forward a novel bladder volume measurement method, in which a three-dimensional (3D) reconstruction model was established from conventional two-dimensional (2D) ultrasonic images to estimate the bladder volume. The differences and relationships were analyzed among the actual volume, the traditional estimated volume, and the new reconstruction model estimated volume. We also compared the data in different volume groups from small volume to high volume. The mean actual volume is 531.8 mL and the standard deviation is 268.7 mL; the mean percentage error of traditional estimation is −28%. In our new bladder measurement method, the mean percentage error is −10.18% (N = 2), −4.72% (N = 3), −0.33% (N = 4), and 2.58% (N = 5). There is no significant difference between the actual volume and our new bladder measurement method (N = 4) in all data or the divided four groups. The estimated volumes from the traditional method or our new method are highly correlated with the actual volume. Our data show that the three-dimensional bladder reconstruction model provides an accurate measurement from conventional B-mode ultrasonic images compared with the traditional method. The accuracy is seen across different groups of volume, and thus we can conclude that this is a reliable and economical volume measurement model that can be applied in general software or in apps on mobile devices.

A comprehensive survey on non-invasive wearable bladder volume monitoring systems

Measuring the volume of urine in the bladder is a significant issue in patients who suffer from the lack of bladder fullness sensation or have problems with timeliness getting to the restroom, such as spinal cord injury patients and some of the elderlies. Real-time monitoring of the bladder, therefore, can be highly helpful for urinary incontinence. Bladder volume monitoring technologies can be divided into two distinct categories of invasive and non-invasive. In invasive techniques, a catheter is directly inserted into the urethra to measure the amount of urine accurately. However, it is painful, limits the user's ordinary movements, and may hurt the urinary tract. Current non-invasive techniques measure the volume of the bladder from the skin using different stationary or portable apparatus at health centers. Both techniques have difficulties and are not cost-effective to use for a long period. Recently, both invasive and non-invasive methods have been attempted to be produced in the form of wearable devices utilizing different sensing and communication technologies. Wearable bladder monitoring devices can be easily used by patients with no or few clinical steps, making them much more affordable than non-wearable devices. While wearable devices seem to be a highly convenient and effective solution, they suffer from few drawbacks, such as relatively low precision. Hence, a great number of studies have been conducted to address these issues. In this article, we review and discuss non-invasive and minimally invasive methods for monitoring the bladder volume. We focus on the most practical and state-of-the-art methods employed in wearable devices, classify them by engineering and medical characteristics, and investigate their specifications, architectures, and measurement algorithms. This study aims to introduce the latest advances in this field to practitioners while comparing the advantages and disadvantages of existing approaches. Our study concludes with open problems and future trends in the area of bladder monitoring and measurement systems. Graphical abstract Wearable bladder monitoring system.

Proposal of a Lab Bench for the Unobtrusive Monitoring of the Bladder Fullness with Bioimpedance Measurements

(1) Background: millions of people, from children to the elderly, suffer from bladder dysfunctions all over the world. Monitoring bladder fullness with appropriate miniaturized textile devices can improve, significantly, their daily life quality, or even cure them. Amongst the existing bladder sensing technologies, bioimpedance spectroscopy seems to be the most appropriate one to be integrated into textiles. (2) Methods: to assess the feasibility of monitoring the bladder fullness with textile-based bioimpedance spectroscopy; an innovative lab-bench has been designed and fabricated. As a step towards obtaining a more realistic pelvic phantom, ex vivo pig's bladder and skin were used. The electrical properties of the fabricated pelvic phantom have been compared to those of two individuals with tetrapolar impedance measurements. The measurements' reproducibility on the lab bench has been evaluated and discussed. Moreover, its suitability for the continuous monitoring of the bladder filling has been investigated. (3) Results: although the pelvic phantom failed in reproducing the frequency-dependent electrical properties of human tissues, it was found to be suitable at 5 kHz to record bladder volume change. The resistance variations recorded are proportional to the conductivity of the liquid filling the bladder. A 350 mL filling with artificial urine corresponds to a decrease in resistance of 7.2%, which was found to be in the same range as in humans. (4) Conclusions: based on that resistance variation; the instantaneous bladder fullness can be extrapolated. The presented lab-bench will be used to evaluate the ability of textiles electrodes to unobtrusively monitor the bladder volume.

Deep learning-based classification of rectal fecal retention and analysis of fecal properties using ultrasound images in older adult patients

AIM

The present study aimed to analyze the use of machine learning in ultrasound (US)-based fecal retention assessment.

METHODS

The accuracy of deep learning techniques and conventional US methods for the evaluation of fecal properties was compared. The presence or absence of rectal feces was analyzed in 42 patients. Eleven patients without rectal fecal retention on US images were excluded from the analysis; thus, fecal properties were analyzed in 31 patients. Deep learning was used to classify the transverse US images into three types: absence of feces, hyperechoic area, and strong hyperechoic area in the rectum.

RESULTS

Of the 42 patients, 31 tested positive for the presence of rectal feces, zero were false positive, zero were false negative, and 11 were negative, indicating a sensitivity of 100% and a specificity of 100% for the detection of rectal feces in the rectum. Of the 31 positive patients, 14 had hard stools and 17 had other types. Hard stool was detected by US findings in 100% of the patients (14/14), whereas deep learning-based classification detected hard stool in 85.7% of the patients (12/14). Other stool types were detected by US findings in 88.2% of the patients (15/17), while deep learning-based classification also detected other stool types in 88.2% of the patients (15/17).

CONCLUSIONS

The results showed that US findings and deep learning-based classification can detect rectal fecal retention in older adult patients and distinguish between the types of fecal retention.