Noble PA. 2025: Real-time Monitoring of Urinary Stone Status During Shockwave Lithotripsy.
Peter A Noble
Urology. 2025 Jul 24:S0090-4295(25)00717-4. doi: 10.1016/j.urology.2025.07.044
Abstract
Objective: To develop a standardized, real-time feedback system for monitoring urinary stone fragmentation during shockwave lithotripsy (SWL), thereby optimizing treatment efficacy and minimizing patient risk.
Methods: A 2-pronged approach was implemented to quantify stone fragmentation in C-arm X-ray images. First, the initial pre-treatment stone image was compared to subsequent images to measure stone area loss. Second, a Convolutional Neural Network was trained to estimate the probability that an image contains a urinary stone. These 2 criteria were integrated to create a real-time signaling system capable of evaluating shockwave efficacy during SWL.
Results: The system was developed using data from 522 shockwave treatments encompassing 4057 C-arm X-ray images. The combined area-loss metric and Convolutional Neural Network output enabled consistent real-time assessment of stone fragmentation, providing actionable feedback to guide SWL in diverse clinical contexts.
Conclusion: The proposed system offers a novel and reliable method for monitoring urinary stone fragmentation during SWL. By helping to balance treatment efficacy with patient safety, it holds significant promise for semi-automated SWL platforms, particularly in resource-limited or remote environments such as arid regions and extended space missions.
Comment Peter Alken
The introduction is somewhat surprising:
“During treatment, patients typically undergo 5-25 shockwave applications, each generating shockwaves and a corresponding C-arm X-ray image.”
However this is followed by a standard procedure:” SWL operators generally follow a predefined protocol, delivering approximately 2000-3000 shockwaves per session”
and
“Current imaging systems cannot reliably determine when fragmentation is complete, making it difficult to stop treatment based on visual cues.” This is correct and an old problem documented by the fact that the quoted “current” references are very old, from 1990 and 2008 (1,2).
And then follows a very good definition: ”Artificial intelligence (AI) is transforming medicine by enhancing diagnostics, personalizing treatment, and improving patient outcomes through advanced data analysis and pattern recognition”
Then follows more surprise, the author used a “kidney stone register”. I was not aware of this register despite very long experience with SWL: “The research relied on the analysis of anonymized X-ray data accessed through the publicly available “Kidney Stone Registry” (https://bit.ly/4cQSIIZ). The Kidney Stone Registry is a global clinical database that provides anonymized patient information (eg, age, Body Mass Index), treatment parameters (settings used to fragment stones), and X-ray images of SWL and laser ureterorenoscopy treatments. The purpose of the database is to provide data to medical researchers so they can determine best practices and trends through analytics and statistical analysis with the long-term goal of improving patient outcomes and experiences.”
“The C-arm X-ray dataset consisted of 11,648 images,”. “An initial screening of the X-ray images yielded 4621 stone images and 4621 non- stone images. Further curation to remove ambiguous images resulted in a final dataset of 2804 stone images and 2804 non-stone images.”
My computer prevented opening https://bit.ly/4cQSIIZ. However, it seems that an old problem shows up. AI is just as good or bad as what it has been devoured so far. More than half of the stored “kidney stone” data (11,648 minus 5608= 6040) were discarded after a visual? human? control.
Reading the whole paper, at the end this is a fascinating AI application developed by a PhD working in the Department of Microbiology, University of Alabama Birmingham, Birmingham, AL. (Electronic address:
By looking at his publication list in PubMed with papers on diverse topics like death (4) and oral microbiome transplantation (5), I think he must be a crazy guy in the best sense. I rank his present paper as the top reviewer’s choice in 2025.
1 Schmitt RM, Wurster H, Kraus W, Bibinger M. The effects of errors in positioning lithotriptor and imaging kidney stones ultrasound. Proceeding of the 12th Annual International Conference of the IEEE Engineering in Medicine and Biology Society; 1990. doi:10.119/IEMBS.1990.691064.
2Leighton TG, Fedele F, Coleman AJ, et al. A passive acoustic device for real-time monitoring of the efficacy of shockwave lithotripsy treatment. Ultrasound Med Biol. 2008;34:1651–1665. https://doi.org/10.1016/j.ultrasmedbio.2008.03.011
3 Noble PA, Hamilton BD, Gerber G. Stone decision engine accurately predicts stone removal and treatment complications for shock wave lithotripsy and laser ureterorenoscopy patients. PLoS One. 2024 May 2;19(5):e0301812. doi: 10.1371/journal.pone.0301812. PMID: 38696418; PMCID: PMC11065282.
4 Noble PA, Pozhitkov A. Perspective on Death: A Gateway to a New Biology. Bioessays. 2025 Mar;47(3):e202400158. doi: 10.1002/bies.202400158. Epub 2024 Dec 17. PMID: 39686787.
5 Pozhitkov AE, Leroux BG, Randolph TW, Beikler T, Flemmig TF, Noble PA. Towards microbiome transplant as a therapy for periodontitis: an exploratory study of periodontitis microbial signature contrasted by oral health, caries and edentulism. BMC Oral Health. 2015 Oct 14;15:125. doi: 10.1186/s12903-015-0109-4. PMID: 26468081; PMCID: PMC4607249.
Peter Alken
Comments