Toward improved endoscopic examination of urinary stones: a concordance study between endoscopic digital pictures vs microscopy

Estrade, V.; Alméras, Christophe; Bladou, Franck; Bernhard, Jean‐Christophe; Robert, G.; Traxer, Olivier; Daudon, Michel

doi:10.1111/bju.15312

Cited by 26 publications

(71 citation statements)

References 24 publications

(34 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The images used in this contribution (see Table 5) were acquired by an urologist (Dr. Vincent Estrade) who is among the few experts in France able to visually recognize kidney stone types using only in vivo images displayed on a screen during an ureteroscopy. Additionally to this expertise, the annotation of the images used in this work was statistically confirmed in Estrade et al (2020) by a concordance study exploiting the morpho-constitutional analysis of extracted kidney stone fragments (the morpho-constitutional analysis confirmed the visual classification made by the urologist), using microscopy and a Fourier transform infrared spectroscopy (FTIR) analysis, which were exploited as follows.…”

Section: Database Constructionmentioning

confidence: 63%

“…Indeed, despite the variety of compositions and morphologies observed in urinary calculi, about 90% are composed of a limited number of crystalline species and morphological characteristics that are easily recognised through an endoscopic examination Estrade et al (2013Estrade et al ( , 2017. The study in Estrade et al (2020) showed a high concordance between endoscopic and microscopic typing of the kidney stones. More precisely, the concordance of the results was observed in 86.1% of the type I kidney stones, in 85% of the type II kidney stones, in 91% of the type III kidney stones and in 79% of type IV kidney stones made of calcium phosphate.…”

Section: Database Constructionmentioning

confidence: 89%

“…However, such an analysis requires a great deal of experience due to the high inter-class similarities and intraclass variations of the stones. This visual analysis, which is designated by the term "endoscopic stone recognition" (ESR, Estrade et al (2020)), can currently only be achieved by a limited number of specialists, whereas the management of urolithiasis diseases is part of the daily life of every urologist in the world. Moreover, even for experienced specialists, the classification remains often operator-dependent Siener et al (2016); Sampogna et al (2020).…”

Section: Context and Recent Trends In Ureteroscopymentioning

confidence: 99%

“…In a standard morpho-constitutional analysis, the surface, the section and the nucleus of each kidney stone are inspected. In the concordance study in Estrade et al (2020), the visual recognition of kidney stone types was considered as "confirmed" when a non-significant difference between the endoscopic and microscopic images (p-value > 0.05) was obtained. The area under the ROC curve (AUROC), the sensitivity, the specificity, the positive predictive value (PPV) and the negative predictive value (NPV) were calculated for a dataset with a confirmed concordance.…”

Section: Database Constructionmentioning

confidence: 99%

“…The area under the ROC curve (AUROC), the sensitivity, the specificity, the positive predictive value (PPV) and the negative predictive value (NPV) were calculated for a dataset with a confirmed concordance. The authors of Estrade et al (2020) regrouped the following pairs of kidney stone morphologies that have similar aetiologies: Ia and Ib, IIa and IIb, IIIa and IIIb, Va and Vb, and VIa and VIb. These six morphological types cover 95% of the most common pure stones that urologists encounter in their daily practice.…”

Section: Database Constructionmentioning

confidence: 99%

See 4 more Smart Citations

On the in vivo recognition of kidney stones using machine learning

Ochoa-Ruiz¹,

Estrade²,

López³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Determining the type of kidney stones allows urologists to prescribe a treatment to avoid recurrence of renal lithiasis. An automated in-vivo image-based classification method would be an important step towards an immediate identification of the kidney stone type required as a first phase of the diagnosis. In the literature it was shown on ex-vivo data (i.e., in very controlled scene and image acquisition conditions) that an automated kidney stone classification is indeed feasible. This pilot study compares the kidney stone recognition performances of six shallow machine learning methods and three deep-learning architectures which were tested with in-vivo images of the four most frequent urinary calculi types acquired with an endoscope during standard ureteroscopies. This contribution details the database construction and the design of the tested kidney stones classifiers. Even if the best results were obtained by the Inception v3 architecture (weighted precision, recall and F1-score of 0.97, 0.98 and 0.97, respectively), it is also shown that choosing an appropriate colour space and texture features allows a shallow machine learning method to approach closely the performances of the most promising deep-learning methods (the XGBoost classifier led to weighted precision, recall and F1-score values of 0.96). This paper is the first one that explores the most discriminant features to be extracted from images acquired during ureteroscopies.

show abstract

Section: Database Constructionmentioning

confidence: 63%

Section: Database Constructionmentioning

confidence: 89%

Section: Context and Recent Trends In Ureteroscopymentioning

confidence: 99%

Section: Database Constructionmentioning

confidence: 99%

Section: Database Constructionmentioning

confidence: 99%

See 3 more Smart Citations

On the in vivo recognition of kidney stones using machine learning

Ochoa-Ruiz¹,

Estrade²,

López³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Self‐attention based progressive generative adversarial network optimized with arithmetic optimization algorithm for kidney stone detection

V.¹,

K.²,

Rooban

et al. 2023

Concurrency and Computation

View full text Add to dashboard Cite

Summary Self‐attention based progressive generative adversarial network optimized with arithmetic optimization algorithm (AOA) is proposed in this manuscript for kidney stone detection. Initially, the input kidney stone images are gathered via CT kidney dataset. Then, the input image is preprocessed by utilizing APPDRC filtering approach. Also, the preprocessed images are given to the multi‐level thresholding segmentation technique for segmented the image. Then the segmented images are given to the TF‐IDF feature extraction method for extracting the features. Then the extracted features are fed to feature selection using Weibull distributive generalized multidimensional scaling methods for selecting the features. Then the selected features are SPGGAN classification method for kidney stone detection. Generally, SPGGAN not reveal any adoption of optimization methods compute optimum parameters for assuring correct kidney stone detection. Thus, AOA is used for optimizing the weight parameters of SPGGAN and it is implemented in python, its performance is examined under certain performances metrics, such as accuracy, precision, sensitivity, specificity, F‐measure, computational time, and ROC. The proposed SPGGAN‐AOA‐KSD method attains 54.78%, 34.89%, and 20.96% higher accuracy and 3.45%, 4.08%, and 5.06% greater AUC compared with existing methods, such as a ANN‐OGGA‐KSD, HMANN‐BPA‐KSD, and ANN‐CSOA‐KSD respectively.

show abstract