Deep morphological recognition of kidney stones using intra-operative endoscopic digital videos

Estrade, V.; Daudon, Michel; Richard, Emmanuel; Bernhard, Jean Christophe; Bladou, Franck; Robert, G.; Facq, Laurent

doi:10.1088/1361-6560/ac8592

Cited by 7 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using a dataset of smartphone-based microscopic images, Onal et al [68] have evaluated an image recognition system for categorizing four types of kidney stones in the rapid and precise manner. Likewise, Estrade et al [69] have applied deep learning method on digital endoscopic video sequences to automatically detect stone morphology during the stone fragmentation process. All the aforementioned studies, including their goals, AI methods used and results, are summarized in Table 2 .…”

Section: Roles Of Machine Learning For Stone Type Predictionmentioning

confidence: 99%

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

Sassanarakkit

Hadpech

Thongboonkerd

2023

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

Section: Roles Of Machine Learning For Stone Type Predictionmentioning

confidence: 99%

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

Sassanarakkit

Hadpech

Thongboonkerd

2023

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

“…These models learn from data and experience, enabling them to make predictions, recognize patterns, and solve problems without being explicitly programmed for each specific task. They are now widely used in urology to detect kidney stones in videos [ 18 ] and images [ 19 – 24 ], predict sepsis risk [ 25 , 26 ] and lithotripsy treatment outcomes [ 27 – 29 ], and set SWL machine parameters [ 30 ].…”

Section: Introductionmentioning

confidence: 99%

Stone decision engine accurately predicts stone removal and treatment complications for shock wave lithotripsy and laser ureterorenoscopy patients

Noble,

Hamilton,

Gerber

2024

PLoS ONE

View full text Add to dashboard Cite

Kidney stones form when mineral salts crystallize in the urinary tract. While most stones exit the body in the urine stream, some can block the ureteropelvic junction or ureters, leading to severe lower back pain, blood in the urine, vomiting, and painful urination. Imaging technologies, such as X-rays or ureterorenoscopy (URS), are typically used to detect kidney stones. Subsequently, these stones are fragmented into smaller pieces using shock wave lithotripsy (SWL) or laser URS. Both treatments yield subtly different patient outcomes. To predict successful stone removal and complication outcomes, Artificial Neural Network models were trained on 15,126 SWL and 2,116 URS patient records. These records include patient metrics like Body Mass Index and age, as well as treatment outcomes obtained using various medical instruments and healthcare professionals. Due to the low number of outcome failures in the data (e.g., treatment complications), Nearest Neighbor and Synthetic Minority Oversampling Technique (SMOTE) models were implemented to improve prediction accuracies. To reduce noise in the predictions, ensemble modeling was employed. The average prediction accuracies based on Confusion Matrices for SWL stone removal and treatment complications were 84.8% and 95.0%, respectively, while those for URS were 89.0% and 92.2%, respectively. The average prediction accuracies for SWL based on Area-Under-the-Curve were 74.7% and 62.9%, respectively, while those for URS were 77.2% and 78.9%, respectively. Taken together, the approach yielded moderate to high accurate predictions, regardless of treatment or outcome. These models were incorporated into a Stone Decision Engine web application (http://peteranoble.com/webapps.html) that suggests the best interventions to healthcare providers based on individual patient metrics.

show abstract

Acoustic emission of kidney stones: a medical adaptation of statistical breakdown mechanisms

Eckstein,

Wiseman,

Carpenter

et al. 2024

Urolithiasis

View full text Add to dashboard Cite

Kidney stones have a prevalence rate of > 10% in some countries. There has been a significant increase in surgery to treat kidney stones over the last 10 years, and it is crucial that such techniques are as effective as possible, while limiting complications. A selection of kidney stones with different chemical and structural properties were subjected to compression. Under compression, they emit acoustic signals called crackling noise. The variability of the crackling noise was surprisingly great comparing weddellite, cystine and uric acid stones. Two types of signals were found in all stones. At high energies of the emitted sound waves, we found avalanche behaviour, while all stones also showed signals of local, uncorrelated collapse. These two types of events are called ‘wild’ for avalanches and ‘mild’ for uncorrelated events. The key observation is that the crossover from mild to wild collapse events differs greatly between different stones. Weddellite showed brittle collapse, extremely low crossover energies (< 5 aJ) and wild avalanches over 6 orders of magnitude. In cystine and uric acid stones, the collapse was more complicated with a dominance of local “mild” breakings, although they all contained some stress-induced collective avalanches. Cystine stones had high crossover energies, typically $$\sim$$ ∼ 750 aJ, and a narrow window over which they showed wild avalanches. Uric acid stones gave moderate values of crossover energies, $$\sim$$ ∼ 200 aJ, and wild avalanche behaviour for $$\sim$$ ∼ 3 orders of magnitude. Further research extended to all stone types, and measurement of stone responses to different lithotripsy strategies, will assist in optimisation of settings of the laser and other lithotripsy devices to insight fragmentation by targeting the ‘wild’ avalanche regime.

show abstract

Deep morphological recognition of kidney stones using intra-operative endoscopic digital videos

Cited by 7 publications

References 25 publications

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

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

Stone decision engine accurately predicts stone removal and treatment complications for shock wave lithotripsy and laser ureterorenoscopy patients

Acoustic emission of kidney stones: a medical adaptation of statistical breakdown mechanisms

Contact Info

Product

Resources

About