ABSTRACT
Knowing the type (i.e., the biochemical composition) of kidney stones is crucial to prevent relapses with an appropriate treatment. During ureteroscopies, kidney stones are fragmented, extracted from the urinary tract, and their composition is determined using a morpho-constitutional analysis. This procedure is time-consuming (the morpho-constitutional analysis results are only available after several weeks) and tedious (the fragment extraction lasts up to an hour). Identifying the kidney stone type only with the in-vivo endoscopic images would allow for the dusting of the fragments and eneable early treatments, while the morpho-constitutional analysis is ready. Only few contributions dealing with the in vivo identification of kidney stones have been published. This paper discusses and compares five classification methods including deep convolutional neural networks (DCNN)-based approaches and traditional (non DCNN-based) ones. Even if the best method is a DCCN approach with a precision and recall of 98% and 97% over four classes, this contribution shows that an XGBoost classifier exploiting well-chosen feature vectors can closely approach the performances of DCNN classifiers for a medical application with a limited number of annotated data.
Subject(s)
Deep Learning , Kidney Calculi , Humans , Kidney Calculi/diagnostic imaging , Neural Networks, ComputerABSTRACT
Urolithiasis is a common disease around the world and its incidence has been growing every year. There are various diagnosis techniques based on kidney stone identification aiming to find the formation cause. However, most of them are time consuming, tedious and expensive. The accuracy of the diagnosis is crucial for the prescription of an appropriate treatment that can eliminate the stones and diminish future relapses. This paper presents two effective supervised learning methods to automate and improve the accuracy of the classification of kidney stones; as well as a dataset consisting of kidney stone images captured with ureteroscopes. In the proposed methods, the image features that are visually exploited by urologists to distinguish the type of kidney stones are analyzed and encoded as vectors. Then, the classification is performed on these feature vectors through Random Forest and ensemble K Nearest Neighbor classifiers. The overall classification accuracy obtained was 89%, outperforming previous methods by more than 10%. The details of the classifier implementation, as well as their performance and accuracy, are presented and discussed. Finally, future work and improvements are proposed.
Subject(s)
Kidney Calculi , Ureteroscopy , Algorithms , Humans , Kidney Calculi/diagnostic imaging , RecurrenceABSTRACT
Se evalúa el uso del equipo Mycrob-1000 en la determinación de las infecciones urinarias en 4 h en un centro de atención primaria de la salud. Fueron procesadas 258 muestras de orina obtenidas por micción espontánea y como método de referencia se utilizó el recuento de unidades formadoras de colonias por mililitro de orina inoculada en placa de Petri con medio CLED. Se obtuvo 92,31 por ciento de coincidencia entre los 2 métodos y una sensibilidad y especificidad de 79,00 y 96,95 por ciento, respectivamente. El nivel de sensibilidad alcanzado se afectó por aspectos no relacionados directamente al equipo. Los altos valores logrados de especificidad y de coincidencia con el método de referencia favorecen su aplicación en la realización de urocultivos, posibilitando descartar en 4 ó 5 h las muestras de orina negativas y centrar el trabajo y los recursos en las positivas
Subject(s)
Bacteriuria , Laboratory Equipment , Urinary Tract Infections , UrineABSTRACT
Se evalúa el uso del equipo Mycrob-1000 en la determinación de las infecciones urinarias en 4 h en un centro de atención primaria de la salud. Fueron procesadas 258 muestras de orina obtenidas por micción espontánea y como método de referencia se utilizó el recuento de unidades formadoras de colonias por mililitro de orina inoculada en placa de Petri con medio CLED. Se obtuvo 92,31 por ciento de coincidencia entre los 2 métodos y una sensibilidad y especificidad de 79,00 y 96,95 por ciento, respectivamente. El nivel de sensibilidad alcanzado se afectó por aspectos no relacionados directamente al equipo. Los altos valores logrados de especificidad y de coincidencia con el método de referencia favorecen su aplicación en la realización de urocultivos, posibilitando descartar en 4 ó 5 h las muestras de orina negativas y centrar el trabajo y los recursos en las positivas(AU)
Subject(s)
Urine/microbiology , Bacteriuria/urine , Urinary Tract Infections/urine , Laboratory EquipmentABSTRACT
The use of equipment Mycrob-1000 in detecting urinary infections in 4 hours in a primary health care center is evaluated. Two hundred fifty eight urine samples obtained from spontaneous miction were processed; the reference method was counting of colony-forming units per urine millimeter inoculated in Petri plaque in CLED medium. The coincidence rate between both methods was 92,31, with sensitivity and specificity rates of 79,00% and 96,95% respectively. The level of sensitivity was affected by factors not directly dependent on the equipment. High values of specificity and of coincidence achieved by this equipment in relation to the reference method facilitates its use in urine culture, making possible to differentiate negative urine samples in 4 or 5 hours and to focus work and resources on positive samples.