Machine learning-assisted fluoroscopy of bladder function in awake mice
Curation statements for this article:-
Curated by eLife
Evaluation Summary:
This manuscript is of broad interest to researchers working in the area of lower urinary tract dysfunction. It describes a novel method to reliably study bladder function; the approach allows for monitoring bladder filling and emptying in freely moving, non-anaesthetized animals without the need for catheter implantation. This work has optimized a machine learning algorithm for defining the outline of the urinary bladder border from fluoroscopic images of mice that received subcutaneous injections of iodinated radiocontrast media. The advantage is that with images taken at 30 images/second and with monitoring bladder dynamics requiring hours-long observation periods, this very large number of generated images no longer requires manual analysis.
(This preprint has been reviewed by eLife. We include the public reviews from the reviewers here; the authors also receive private feedback with suggested changes to the manuscript. Reviewer #1 agreed to share their name with the authors.)
This article has been Reviewed by the following groups
Listed in
- Evaluated articles (eLife)
- Physiology (eLife)
Abstract
Understanding the lower urinary tract (LUT) and development of highly needed novel therapies to treat LUT disorders depends on accurate techniques to monitor LUT (dys)function in preclinical models. We recently developed videocystometry in rodents, which combines intravesical pressure measurements with X-ray-based fluoroscopy of the LUT, allowing the in vivo analysis of the process of urine storage and voiding with unprecedented detail. Videocystometry relies on the precise contrast-based determination of the bladder volume at high temporal resolution, which can readily be achieved in anesthetized or otherwise motion-restricted mice but not in awake and freely moving animals. To overcome this limitation, we developed a machine-learning method, in which we trained a neural network to automatically detect the bladder in fluoroscopic images, allowing the automatic analysis of bladder filling and voiding cycles based on large sets of time-lapse fluoroscopic images (>3 hr at 30 images/s) from behaving mice and in a noninvasive manner. With this approach, we found that urethane, an injectable anesthetic that is commonly used in preclinical urological research, has a profound, dose-dependent effect on urethral relaxation and voiding duration. Moreover, both in awake and in anesthetized mice, the bladder capacity was decreased ~fourfold when cystometry was performed acutely after surgical implantation of a suprapubic catheter. Our findings provide a paradigm for the noninvasive, in vivo monitoring of a hollow organ in behaving animals and pinpoint important limitations of the current gold standard techniques to study the LUT in mice.
Article activity feed
-
-
Evaluation Summary:
This manuscript is of broad interest to researchers working in the area of lower urinary tract dysfunction. It describes a novel method to reliably study bladder function; the approach allows for monitoring bladder filling and emptying in freely moving, non-anaesthetized animals without the need for catheter implantation. This work has optimized a machine learning algorithm for defining the outline of the urinary bladder border from fluoroscopic images of mice that received subcutaneous injections of iodinated radiocontrast media. The advantage is that with images taken at 30 images/second and with monitoring bladder dynamics requiring hours-long observation periods, this very large number of generated images no longer requires manual analysis.
(This preprint has been reviewed by eLife. We include the public reviews …
Evaluation Summary:
This manuscript is of broad interest to researchers working in the area of lower urinary tract dysfunction. It describes a novel method to reliably study bladder function; the approach allows for monitoring bladder filling and emptying in freely moving, non-anaesthetized animals without the need for catheter implantation. This work has optimized a machine learning algorithm for defining the outline of the urinary bladder border from fluoroscopic images of mice that received subcutaneous injections of iodinated radiocontrast media. The advantage is that with images taken at 30 images/second and with monitoring bladder dynamics requiring hours-long observation periods, this very large number of generated images no longer requires manual analysis.
(This preprint has been reviewed by eLife. We include the public reviews from the reviewers here; the authors also receive private feedback with suggested changes to the manuscript. Reviewer #1 agreed to share their name with the authors.)
-
Reviewer #1 (Public Review):
This is an interesting new bladder function monitoring approach in rodents that can accurately monitor bladder filling and emptying in freely moving non-anaesthetized animals that does not require implantation of a suprapubic catheter. This was accomplished by using machine learning to define the bladder wall from fluoroscopic images of mice injected with iodinated radiocontrast media taken at 30 images/second over 2-3 hours. While this approach cannot provide any information on intravesical pressures, it can provide much more accurate and detailed information on bladder filling, urethral flow rate, intra contraction intervals and residual bladder volume than assays of voiding spots on paper or metabolic cages monitoring of urine production with microbalances.
-
Reviewer #2 (Public Review):
Cystometry is a commonly used invasive technique to collect metrics of bladder function, where a catheter is implanted in the bladder to infuse saline and monitor the bladder pressure. The authors have shown, for the first time to non-invasively collect metrics of bladder function such as bladder capacity, residual volume and urine flow rate in an awake mouse. They have used X-ray videocystometry to show that under urethane anesthesia the voiding efficiency and urine flow rate are reduced. Further, presence of a catheter in the dome was shown to drastically reduce the bladder capacity. Furthermore, to speed up data analysis they have used deep learning tools to calculate the metrics of bladder function.
The data is excellent and it justifies the conclusions, however the reasoning behind the conclusions needs …
Reviewer #2 (Public Review):
Cystometry is a commonly used invasive technique to collect metrics of bladder function, where a catheter is implanted in the bladder to infuse saline and monitor the bladder pressure. The authors have shown, for the first time to non-invasively collect metrics of bladder function such as bladder capacity, residual volume and urine flow rate in an awake mouse. They have used X-ray videocystometry to show that under urethane anesthesia the voiding efficiency and urine flow rate are reduced. Further, presence of a catheter in the dome was shown to drastically reduce the bladder capacity. Furthermore, to speed up data analysis they have used deep learning tools to calculate the metrics of bladder function.
The data is excellent and it justifies the conclusions, however the reasoning behind the conclusions needs some fine-tuning. More details of AI measurement methods and how well it performs would help others in the field.
-
