Automated Machine Learning Segmentation and Measurement of Urinary Stones on CT Scan

Can Artificial Intelligence Accurately Detect Urinary Stones? A Systematic Review

Objectives: To perform a systematic review on artificial intelligence (AI) performances to detect urinary stones. Methods: A PROSPERO-registered (CRD473152) systematic search of Scopus, Web of Science, Embase, and PubMed databases was performed to identify original research articles pertaining to AI stone detection or measurement, using search terms ("automatic" OR "machine learning" OR "convolutional neural network" OR "artificial intelligence" OR "detection" AND "stone volume"). Risk-of-bias (RoB) assessment was performed according to the Cochrane RoB tool, the Joanna Briggs Institute Checklist for nonrandomized studies, and the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). Results: Twelve studies were selected for the final review, including three multicenter and nine single-center retrospective studies. Eleven studies completed at least 50% of the CLAIM checkpoints and only one presented a high RoB. All included studies aimed to detect kidney (5/12, 42%), ureter (2/12, 16%), or urinary (5/12, 42%) stones on noncontrast computed tomography (NCCT), but 42% intended to automate measurement. Stone distinction from vascular calcification interested two studies. All studies used AI machine learning network training and internal validation, but a single one provided an external validation. Trained networks achieved stone detection, with sensitivity, specificity, and accuracy rates ranging from 58.7% to 100%, 68.5% to 100%, and 63% to 99.95%, respectively. Detection Dice score ranged from 83% to 97%. A high correlation between manual and automated stone volume (r = 0.95) was noted. Differentiate distal ureteral stones and phleboliths seemed feasible. Conclusions: AI processes can achieve automated urinary stone detection from NCCT. Further studies should provide urinary stone detection coupled with phlebolith distinction and an external validation, and include anatomical abnormalities and urologic foreign bodies (ureteral stent and nephrostomy tubes) cases.

Comparison of automated kidney stone size measurement and volumetry in photon counting CT compared to 3rd generation dual energy CT and physically measurements - an ex vivo study

PURPOSE

This ex vivo study aimed to compare a newly developed dual-source photon-counting CT (PCCT) with a 3rd generation dual-source dual-energy CT (DECT) for the detection and measurement (stone lengths and volumetrics) of urinary stones.

METHODS

143 urinary stones with a known geometry were physically measured and defined as reference values. Next, urinary stones were placed in an anthropomorphic abdomen-model and were scanned with DECT and PCCT. Images were read by two experienced examiners and automatically evaluated using a specific software.

RESULTS

DECT and PCCT showed a high sensitivity for manual stone detection of 97.9% and 94.4%, and for automatic detection of 93.0% and 87.4%, respectively. Compared to that uric acid and xanthine stones were recognized slightly worse by DECT and PCCT with manual stone detection (93.3% and 82.2%), and with automatic detection (77.8% and 60.0%). All other stone entities were completely recognized. By comparing the maximum diameter of the reference value and DECT, Pearson-correlation was 0.96 (p < 0.001) for manual and 0.97 (p < 0.001) for automatic measurement, and for PCCT it was 0.94 (p < 0.001) for manual and 0.97 (p < 0.001) for automatic measurements. DECT and PCCT can also reliably determine volume manually and automatically with a Pearson-correlation of 0.99 (p < 0.001), respectively.

CONCLUSION

Both CTs showed comparable results in stone detection, length measurement and volumetry compared to the reference values. Automatic measurement tends to underestimate the maximum diameter. DECT proved to be slightly superior in the recognition of xanthine and uric acid stones.

A machine learning approach using stone volume to predict stone-free status at ureteroscopy

INTRODUCTION

To develop a predictive model incorporating stone volume along with other clinical and radiological factors to predict stone-free (SF) status at ureteroscopy (URS).

MATERIAL AND METHODS

Retrospective analysis of patients undergoing URS for kidney stone disease at our institution from 2012 to 2021. SF status was defined as stone fragments < 2 mm at the end of the procedure confirmed endoscopically and no evidence of stone fragments > 2 mm at XR KUB or US KUB at 3 months follow up. We specifically included all non-SF patients to optimise our algorithm for identifying instances with residual stone burden. SF patients were also randomly sampled over the same time period to ensure a more balanced dataset for ML prediction. Stone volumes were measured using preprocedural CT and combined with 19 other clinical and radiological factors. A bagged trees machine learning model with cross-validation was used for this analysis.

RESULTS

330 patients were included (SF: n = 276, not SF: n = 54, mean age 59.5 ± 16.1 years). A fivefold cross validated RUSboosted trees model has an accuracy of 74.5% and AUC of 0.82. The model sensitivity and specificity were 75% and 72.2% respectively. Variable importance analysis identified total stone volume (17.7% of total importance), operation time (14.3%), age (12.9%) and stone composition (10.9%) as important factors in predicting non-SF patients. Single and cumulative stone size which are commonly used in current practice to guide management, only represented 9.4% and 4.7% of total importance, respectively.

CONCLUSION

Machine learning can be used to predict patients that will be SF at the time of URS. Total stone volume appears to be more important than stone size in predicting SF status. Our findings could be used to optimise patient counselling and highlight an increasing role of stone volume to guide endourological practice and future guidelines.

Comparison of ureteral stone measurements for predicting the efficacy of a single session of extracorporeal shockwave lithotripsy: one-, two-, and three-dimensional computed tomography measurements

The objective of this study was to compare the value of one-, two- and three-dimensional computed tomography (CT) measurements for predicting the efficacy of a single session of extracorporeal shock wave lithotripsy (ESWL) in patients with a single ureteral stone. A total of 165 patients were included based on the inclusion and exclusion criteria. Different models were constructed using a combination of patients' clinical data and measurements obtained by manual sketching and automated extraction software. Multivariate logistic regression was used to develop the models. Receiver operating characteristic curves were used to assess the performance of the models. There was good interobserver agreement for all measurements in different dimensions (P < 0.001). We also found that hydronephrosis, the largest diameter, the largest area, volume, and mean CT value were significantly greater in the failure group than in the success group (P < 0.01). Furthermore, all sizes and CT measurement values were found to be independent predictors for predicting efficacy after one session of ESWL (P < 0.05). In addition, the multivariate logistic analysis showed that the area under the curve (AUC) for two-dimensional and three-dimensional measurements was superior to that of one-dimensional measurement (P < 0.01). However, when size alone was included as a measurable predictor, there was no significant difference in the AUC among the one-, two-, and three-dimensional measurements (P > 0.05). In summary, after adjusting for clinical data, two- and three-dimensional measurements combining ureteral stone size and CT values were found to be the best predictors of ESWL efficacy, and software-based three-dimensional measurements should be considered to avoid interobserver variability in clinical practice.

Surgical Artificial Intelligence: Endourology

Endourology is ripe with information that includes patient factors, laboratory tests, outcomes, and visual data, which is becoming increasingly complex to assess. Artificial intelligence (AI) has the potential to explore and define these relationships; however, humans might not be involved in the input, analysis, or even determining the methods of analysis. Herein, the authors present the current state of AI in endourology and highlight the need for urologists to share their proposed AI solutions for reproducibility outside of their institutions and prepare themselves to properly critique this new technology.

Artificial Intelligence in Pediatric Urology

Application of artificial intelligence (AI) is one of the hottest topics in medicine. Unlike traditional methods that rely heavily on statistical assumptions, machine learning algorithms can identify highly complex patterns from data, allowing robust predictions. There is an abundance of evidence of exponentially increasing pediatric urologic publications using AI methodology in recent years. While these studies show great promise for better understanding of disease and patient care, we should be realistic about the challenges arising from the nature of pediatric urologic conditions and practice, in order to continue to produce high-impact research.

How to estimate stone volume and its use in stone surgery: a comprehensive review

OBJECTIVE

Current interventional guidelines refer to the cumulative stone diameter to choose the appropriate surgical modality (ureteroscopy [URS], extracorporeal shockwave lithotripsy [ESWL] and percutaneous nephrolithotomy [PCNL]). The stone volume (SV) has been introduced recently, to better estimate the stone burden. This review aimed to summarize the available methods to evaluate the SV and its use in urolithiasis treatment.

MATERIAL AND METHODS

A comprehensive review of the literature was performed in December 2022 by searching Embase, Cochrane and Pubmed databases. Articles were considered eligible if they described SV measurement or the stone free rate after different treatment modalities (SWL, URS, PCNL) or spontaneous passage, based on SV measurement. Two reviewers independently assessed the eligibility and the quality of the articles and performed the data extraction.

RESULTS

In total, 28 studies were included. All studies used different measurement techniques for stone volume. The automated volume measurement appeared to be more precise than the calculated volume. In vitro studies showed that the automated volume measurement was closer to actual stone volume, with a lower inter-observer variability. Regarding URS, stone volume was found to be more predictive of stone free rates as compared to maximum stone diameter or cumulative diameter for stones >20 mm. This was not the case for PCNL and SWL.

CONCLUSIONS

Stone volume estimation is feasible, manually or automatically and is likely a better representation of the actual stone burden. While for larger stones treated by retrograde intrarenal surgery, stone volume appears to be a better predictor of SFR, the superiority of stone volume throughout all stone burdens and for all stone treatments, remains to be proven. Automated volume acquisition is more precise and reproducible than calculated volume.

Clinical Reproducibility of the Stone Volume Measurement: A "Kidney Stone Calculator" Study

BACKGROUND

An accurate estimation of the stone burden is the key factor for predicting retrograde intra-renal surgical outcomes. Volumetric calculations better stratify stone burden than linear measurements. We developed a free software to assess the stone volume and estimate the lithotrity duration according to 3D-segmented stone volumes, namely the Kidney Stone Calculator (KSC). The present study aimed to validate the KSC's reproducibility in clinical cases evaluating its inter-observer and intra-observer correlations.

METHODS

Fifty patients that harbored renal stones were retrospectively selected from a prospective cohort. For each patient, three urologists with different experience levels in stone management made five measurements of the stone volume on non-contrast-enhanced computed tomography (NCCT) images using the KSC.

RESULTS

the overall inter-observer correlation (Kendall's concordance coefficient) was 0.99 (p < 0.0001). All three paired analyses of the inter-observer reproducibility were superior to 0.8. The intra-observer variation coefficients varied from 4% to 6%, and Kendall's intra-observer concordance coefficient was found to be superior to 0.98 (p < 0.0001) for each participant. Subgroup analyses showed that the segmentation of complex stones seems to be less reproductible.

CONCLUSIONS

The Kidney Stone Calculator is a reliable tool for the stone burden estimation. Its extension for calculating the lithotrity duration is of major interest and could help the practitioner in surgical planning.

Fully Automated Longitudinal Assessment of Renal Stone Burden on Serial CT Imaging Using Deep Learning

Purpose: Use deep learning (DL) to automate the measurement and tracking of kidney stone burden over serial CT scans. Materials and Methods: This retrospective study included 259 scans from 113 symptomatic patients being treated for urolithiasis at a single medical center between 2006 and 2019. These patients underwent a standard low-dose noncontrast CT scan followed by ultra-low-dose CT scans limited to the level of the kidneys. A DL model was used to detect, segment, and measure the volume of all stones in both initial and follow-up scans. The stone burden was characterized by the total volume of all stones in a scan (SV). The absolute and relative change of SV, (SVA and SVR, respectively) over serial scans were computed. The automated assessments were compared with manual assessments using concordance correlation coefficient (CCC), and their agreement was visualized using Bland-Altman and scatter plots. Results: Two hundred twenty-eight out of 233 scans with stones were identified by the automated pipeline; per-scan sensitivity was 97.8% (95% confidence interval [CI]: 96.0-99.7). The per-scan positive predictive value was 96.6% (95% CI: 94.4-98.8). The median SV, SVA, and SVR were 476.5 mm3, -10 mm3, and 0.89, respectively. After removing outliers outside the 5th and 95th percentiles, the CCC measuring agreement on SV, SVA, and SVR were 0.995 (0.992-0.996), 0.980 (0.972-0.986), and 0.915 (0.881-0.939), respectively Conclusions: The automated DL-based measurements showed good agreement with the manual assessments of the stone burden and its interval change on serial CT scans.

Theranostic roles of machine learning in clinical management of kidney stone disease

Kidney stone disease (KSD) is a common illness caused by deposition of solid minerals formed inside the kidney. The disease prevalence varies, based on sociodemographic, lifestyle, dietary, genetic, gender, age, environmental and climatic factors, but has been continuously increasing worldwide. KSD is a highly recurrent disease, and the recurrence rate is about 11% within two years after the stone removal. Recently, machine learning has been widely used for KSD detection, stone type prediction, determination of appropriate treatment modality and prediction of therapeutic outcome. This review provides a brief overview of KSD and discusses how machine learning can be applied to diagnostics, therapeutics and prognostics in clinical management of KSD for better therapeutic outcome.