myStone: A system for automatic kidney stone classification

Serrat, Joan; Lumbreras, Felipe; Blanco, Francisco J.; Valiente, Manuel; López‐Mesas, Montserrat

doi:10.1016/j.eswa.2017.07.024

Cited by 35 publications

(53 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The lower prediction scores for other stone compositions may be a reflection of the visual heterogeneity of these stones. 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%

“…Only one prior study assessed image‐based methods to determine kidney stone composition . Serrat et al computed hand‐crafted features from each image (e.g.…”

Section: Discussionmentioning

confidence: 99%

“…Only one prior study assessed image‐based methods to determine kidney stone composition . Serrat et al computed hand‐crafted features from each image (e.g. local binary pattern and colour histogram) and applied a traditional machine‐learning approach (random forest) to classify the features.…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

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%

“…Only one prior study assessed image‐based methods to determine kidney stone composition . Serrat et al computed hand‐crafted features from each image (e.g.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning computer vision algorithm for detecting kidney stone composition

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Moreover, even for experienced specialists, the classification remains often operator-dependent Siener et al (2016); Sampogna et al (2020). Therefore, the implementation of automated and reproducible classification methods in this context would make it possible to take full Reference/Feature Kidney Stone Composition Image Type Acquisition AU WW WD STR CYS BRU Surface Section Serrat et al (2017) Ex vivo Torrell-Amado and Serrat-Gual (2018) Ex vivo Black et al (2020) Ex vivo Martínez et al (2020) In vivo Estrade et al (2021) In vivo This contribution…”

Section: Context and Recent Trends In Ureteroscopymentioning

confidence: 99%

On the in vivo recognition of kidney stones using machine learning

Ochoa-Ruiz¹,

Estrade²,

López³

et al. 2022

Preprint

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

“…For capturing images of expelled kidney stones, they design a new device and give a new method of an expert system for classification. Eight classes of Kidney stones taxonomy are used in this system that give 63% accuracy [19]. Put forward a system to predict the early stages Chronic Kidney Disease (CKD) in kidney using different machine learning techniques such as Logistic Regression, Naive Bayes, Artificial Neural Networks and Decision Trees.…”

Section: Literature Reviewmentioning

confidence: 99%

Role of Machine Vision for Identification of Kidney Stones Using Multi Features Analysis

Qadri¹

2021

Research Journal Of Computer Science And Information Technology

View full text Add to dashboard Cite

The purpose of this study is to highlight the significance of machine vision for the Classification of kidney stone identification. A novel optimized fused texture features frame work was designed to identify the stones in kidney. A fused 234 texture feature namely (GLCM, RLM and Histogram) feature set was acquired by each region of interest (ROI). It was observed that on each image 8 ROI’s of sizes (16x16, 20x20 and 22x22) were taken. It was difficult to handle a large feature space 280800 (1200x234). Now to overcome this data handling issue we have applied feature optimization technique namely POE+ACC and acquired 30 most optimized features set for each ROI. The optimized fused features data set 3600(1200x30) was used to four machine vision Classifiers that is Random Forest, MLP, j48 and Naïve Bayes. Finally, it was observed that Random Forest provides best results of 90% accuracy on ROI 22x22 among the above discussed deployed Classifiers

show abstract

myStone: A system for automatic kidney stone classification

Cited by 35 publications

References 19 publications

Deep learning computer vision algorithm for detecting kidney stone composition

Deep learning computer vision algorithm for detecting kidney stone composition

On the in vivo recognition of kidney stones using machine learning

Role of Machine Vision for Identification of Kidney Stones Using Multi Features Analysis

Contact Info

Product

Resources

About