Muller S. et al., 2021: Can a Dinosaur Think? Implementation of Artificial Intelligence in Extracorporeal Shock Wave Lithotripsy.
Muller S, Abildsnes H, Østvik A, Kragset O, Gangås I, Birke H, Langø T, Arum C.
Department of Health Research, SINTEF Digital, Trondheim, Norway.
Department of Circulation and Medical Imaging, Norwegian University of Science and Technology, Trondheim, Norway.
Medical School, Norwegian University of Science and Technology, Trondheim, Norway.
Department of Radiology, St. Olavs Hospital, Trondheim University Hospital, Trondheim, Norway.
Department of Surgery, St. Olavs Hospital, Trondheim University Hospital, Trondheim, Norway.
Department of Clinical and Molecular Medicine, Norwegian University of Science and Technology, Trondheim, Norway.
Department of Urology, Skane University Hospital, Malmö, Sweden.
Department of Translational Medicine, Lund University, Malmö, Sweden.
Background: Extracorporeal shock wave lithotripsy (ESWL) of kidney stones is losing ground to more expensive and invasive endoscopic treatments.
Objective: This proof-of-concept project was initiated to develop artificial intelligence (AI)-augmented ESWL and to investigate the potential for machine learning to improve the efficacy of ESWL.
Design setting and participants: Two-dimensional ultrasound videos were captured during ESWL treatments from an inline ultrasound device with a video grabber. An observer annotated 23 212 images from 11 patients as either in or out of focus. The median hit rate was calculated on a patient level via bootstrapping. A convolutional neural network with U-Net architecture was trained on 57 ultrasound images with delineated kidney stones from the same patients annotated by a second observer. We tested U-Net on the ultrasound images annotated by the first observer. Cross-validation with a training set of nine patients, a validation set of one patient, and a test set of one patient was performed.
Outcome measurements and statistical analysis: Classical metrics describing classifier performance were calculated, together with an estimation of how the algorithm would affect shock wave hit rate.
Results and limitations: The median hit rate for standard ESWL was 55.2% (95% confidence interval [CI] 43.2-67.3%). The performance metrics for U-Net were accuracy 63.9%, sensitivity 56.0%, specificity 74.7%, positive predictive value 75.3%, negative predictive value 55.2%, Youden's J statistic 30.7%, no-information rate 58.0%, and Cohen's κ 0.2931. The algorithm reduced total mishits by 67.1%. The main limitation is that this is a proof-of-concept study involving only 11 patients.
Conclusions: Our calculated ESWL hit rate of 55.2% (95% CI 43.2-67.3%) supports findings from earlier research. We have demonstrated that a machine learning algorithm trained on just 11 patients increases the hit rate to 75.3% and reduces mishits by 67.1%. When U-Net is trained on more and higher-quality annotations, even better results can be expected.
Patient summary: Kidney stones can be treated by applying shockwaves to the outside of the body. Ultrasound scans of the kidney are used to guide the machine delivering the shockwaves, but the shockwaves can still miss the stone. We used artificial intelligence to improve the accuracy in hitting the stone being treated.
J.Eur Urol Open Sci. 2021 Mar 21;27:33-42. doi: 10.1016/j.euros.2021.02.007. eCollection 2021 May. PMID: 34337515
The statement “Ultrasound scans of the kidney are used to guide the machine delivering the shockwaves” in the patients summary, is fuzzy. The images guide not the machine but the operator to adjust the shockwave focus to the stone. The present paper offers a short course on how to create a machine learning system and what difficulties can be met.
The idea to improve the hit rate is not new and the interested reader will know the publications from Taiwan (1-4) reviewed earlier. The last 2013 publication of this group closed with a look on the future: “To provide more evidence proving the effectiveness … further results of simulated animal experiments will be presented in the future.” Unfortunately, I could not detect further publications from that group. It seems that the ESWL machines producing companies are not interested in that business.
The present paper is published in a new open access journal: European Urology Open Science. It is the open access journal of the European Urology, including Urology Focus and European Urology Oncology. Authors have to pay USD 1800 US$ for research Articles, Reviews and 600 US$ for Video Articles, Case Reports. There is a 20% discount for EAU members and charge waiver for authors based in countries eligible for the Research4Life program. In addition, several institutions have special contracts with medical journals allowing open access publication without that the authors have to pay.
1. Chang CC, Liang SM, Pu YR et al: In vitro study of ultrasound based real-time tracking of renal stones for shock wave lithotripsy: part 1. J Urol 2001; 166: 28.
2. Chang CC, Manousakas I, Pu YR et al: In vitro study of ultrasound based real-time tracking for renal stones in shock wave lithotripsy: Part II - A simulated animal experiment. J Urol 2002; 167: 2594.
3. Chen CJ, Hsu HC, Chung WS et al: Clinical experience with ultrasound-based real-time tracking lithotripsy in the single renal stone treatment. J Endourol 2009; 23: 1811). and others have done similar studies (Orkisz, M., Farchtchian, T., Saighi, D. et al: Image based renal stone tracking to improve efficacy in extracorporeal lithotripsy. J Urol, 160: 1237, 1998)
4 Chang CC, Pu YR, Manousakas I, Liang SM, Yu FM, Tong YC, Lin SH. In vitro study of the revised ultrasound based real-time tracking of renal stones for shock wave lithotripsy: Part 1. J Urol. 2013 Jun;189(6):2357-63. doi: 10.1016/j.juro.2012.11.111. Epub 2012 Nov 27. PMID: 23201381