Automated Analysis of Urinary Stone Composition Using Raman Spectroscopy: Pilot Study for the Development of a Compact Portable System for Immediate Postoperative Ex Vivo Application

Miernik, Arkadiusz; Eilers, Y.; Bolwien, Carsten; Lambrecht, A.; Hauschke, Dieter; Rebentisch, G; Lossin, Phillipp S.; Hesse, Albrecht; Rassweiler, Jens; Wetterauer, Ulrich; Schoenthaler, Martin

doi:10.1016/j.juro.2013.06.024

Cited by 24 publications

(27 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Brushite specifically has been noted as a difficult stone composition to classify with computer vision methods due to its high level of intraclass variability . To our knowledge, this is the first report of using CNNs to predict kidney stone composition, although other methods such as Raman spectroscopy and autofluorescence have been studied .…”

Section: Discussionmentioning

confidence: 99%

Deep learning computer vision algorithm for detecting kidney stone composition

et al. 2020

View full text Add to dashboard Cite

ObjectivesTo assess the recall of a deep learning (DL) method to automatically detect kidney stones composition from digital photographs of stones. Materials and MethodsA total of 63 human kidney stones of varied compositions were obtained from a stone laboratory including calcium oxalate monohydrate (COM), uric acid (UA), magnesium ammonium phosphate hexahydrate (MAPH/struvite), calcium hydrogen phosphate dihydrate (CHPD/brushite), and cystine stones. At least two images of the stones, both surface and inner core, were captured on a digital camera for all stones. A deep convolutional neural network (CNN), ResNet-101 (ResNet, Microsoft), was applied as a multi-class classification model, to each image. This model was assessed using leaveone-out cross-validation with the primary outcome being network prediction recall. ResultsThe composition prediction recall for each composition was as follows: UA 94% (n = 17), COM 90% (n = 21), MAPH/ struvite 86% (n = 7), cystine 75% (n = 4), CHPD/brushite 71% (n = 14). The overall weighted recall of the CNNs composition analysis was 85% for the entire cohort. Specificity and precision for each stone type were as follows: UA (97.83%, 94.12%), COM (97.62%, 95%), struvite (91.84%, 71.43%), cystine (98.31%, 75%), and brushite (96.43%, 75%). ConclusionDeep CNNs can be used to identify kidney stone composition from digital photographs with good recall. Future work is needed to see if DL can be used for detecting stone composition during digital endoscopy. This technology may enable integrated endoscopic and laser systems that automatically provide laser settings based on stone composition recognition with the goal to improve surgical efficiency.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep learning computer vision algorithm for detecting kidney stone composition

et al. 2020

View full text Add to dashboard Cite

show abstract

“…As mentioned in the introduction, Miernik et al performed experiments on fiber‐coupled fluorescence spectroscopy for a lithotripsy laser system . Since signal excitation and detection takes place via the treatment fiber, the method is not influenced by the type of ureteroscope used.…”

Section: Discussionmentioning

confidence: 99%

Stone/tissue differentiation for Holmium laser lithotripsy using autofluorescence: Clinical proof of concept study

et al. 2016

View full text Add to dashboard Cite

show abstract

“…One of these advantages is that prior sample preparation is not necessary, [17] while it is required for XRD and IRS. [18] Analysis using LIBS is easy and rapid. Small stones can be analyzed using LIBS, whereas only large stones can be analyzed using XRD.…”

Section: Discussionmentioning

confidence: 99%

Laser-induced breakdown spectroscopy is a reliable method for urinary stone analysis

Mutlu

Çiftçi

Gülecen

et al. 2016

Turkish Journal of Urology

View full text Add to dashboard Cite

Objective: We compared laser-induced breakdown spectroscopy (LIBS) with the traditionally used and recommended X-ray diffraction technique (XRD) for urinary stone analysis. Material and methods:In total, 65 patients with urinary calculi were enrolled in this prospective study. Stones were obtained after surgical or extracorporeal shockwave lithotripsy procedures. All stones were divided into two equal pieces. One sample was analyzed by XRD and the other by LIBS. The results were compared by the kappa (κ) and Spearman's correlation coefficient (rho) tests.Results: Using LIBS, 95 components were identified from 65 stones, while XRD identified 88 components. LIBS identified 40 stones with a single pure component, 20 stones with two different components, and 5 stones with three components. XRD demonstrated 42 stones with a single component, 22 stones with two different components, and only 1 stone with three different components. There was a strong relationship in the detection of stone types between LIBS and XRD for stones components (Spearman rho, 0.866; p<0.001). There was excellent agreement between the two techniques among 38 patients with pure stones (κ index, 0.910; Spearman rho, 0.916; p<0.001). Conclusion:Our study indicates that LIBS is a valid and reliable technique for determining urinary stone composition. Moreover, it is a simple, low-cost, and nondestructive technique. LIBS can be safely used in routine daily practice if our results are supported by studies with larger numbers of patients.

show abstract

Automated Analysis of Urinary Stone Composition Using Raman Spectroscopy: Pilot Study for the Development of a Compact Portable System for Immediate Postoperative Ex Vivo Application

Cited by 24 publications

References 22 publications

Deep learning computer vision algorithm for detecting kidney stone composition

Deep learning computer vision algorithm for detecting kidney stone composition

Stone/tissue differentiation for Holmium laser lithotripsy using autofluorescence: Clinical proof of concept study

Laser-induced breakdown spectroscopy is a reliable method for urinary stone analysis

Contact Info

Product

Resources

About