metricas
covid
Buscar en
Actas Urológicas Españolas (English Edition)
Toda la web
Inicio Actas Urológicas Españolas (English Edition) Computer-aided analysis of transrectal ultrasound images of the prostate
Journal Information
Vol. 35. Issue 7.
Pages 404-413 (July - August 2011)
Share
Share
Download PDF
More article options
Visits
1415
Vol. 35. Issue 7.
Pages 404-413 (July - August 2011)
Original article
Computer-aided analysis of transrectal ultrasound images of the prostate
Análisis de imagen asistido por ordenador en ecografía transrectal de próstata
Visits
1415
Á. Gómez-Ferrer
Corresponding author
dr.alvaro@gomez-ferrer.net

Corresponding author.
, S. Arlandis
Servicio de Urología, Hospital Universitario La Fe, Valencia, Spain
This item has received
Article information
Abstract
Full Text
Bibliography
Download PDF
Statistics
Figures (5)
Show moreShow less
Tables (4)
Table 1. Results of urologist 1.
Table 2. Results of urologist 2.
Table 3. Results of urologist 3.
Table 4. Results of urologist 4.
Show moreShow less
Abstract
Introduction

Prostate cancer is usually diagnosed by transrectal ultrasound (TRUS) biopsy. Nevertheless, suspicious images are frequently not found. Imaging analysis studies aim to identify ultrasound patterns characteristic of apparently hidden conditions.

Material and methods

We digitally recorded 288 TRUS ultrasound guided transrectal biopsies and extracted 3 static images from the puncture-biopsy area. The extraction of the texture characteristics were obtained by “simple mapping” on a gray scale and spatial gray level dependence matrices (SGLDM), also known as Haralick's co-occurrence matrices, which study the relationship of each pixel and its neighbors. A pattern recognition software system was developed with two different classification methods: nearest neighbor (k-NN) and Markov's hidden models. Finally, a virtual experiment was carried out in which four urologists compared their diagnostic accuracy for prostate cancer with our system in 408 TRUS images, not in real time.

Results

The diagnostic capacity (ROC curve) with the simple gray map study was 59.7% with nearest-neighbor classification and 61.6% with Markov's hidden models classification. The co-occurrence matrices showed an area under ROC curve of 60.1% and 60.0% with k-NN and Markov's hidden models classification, respectively. The virtual experiment was conducted with a simple gray map study and k-NN classification. The images processed by our system showed the following diagnostic accuracy: 63.3, 67, 64.3 and 63.7% compared to 61.7, 60.5, 66.2 and 60.7% with the original image.

Conclusions

Our pattern recognition system for prostate cancer TRUS images has a limited, yet stable, accuracy.

Keywords:
Prostate cancer
Computer-Aided Diagnosis
Transrectal ultrasound
Resumen
Introducción

El método de diagnóstico de elección del cáncer de próstata (CP) es la biopsia transrectal guiada ecográficamente. Sin embargo, es frecuente no objetivar imágenes sospechosas. Los estudios de análisis de imagen pretenden identificar patrones ecográficos propios de una patología aparentemente ocultos.

Materiales y método

Registramos digitalmente 288 biopsias transrectales ecoguiadas, de las que se aislaron imágenes estáticas de cada punción-biopsia para su análisis computarizado. Para ello se procedió a la extracción de características de textura mediante «mapeo simple» en escala de gris y «matrices espaciales dependientes del nivel de gris» o «matrices de coaparición», que estudian la relación de cada píxel con sus vecinos. Se desarrolló un sistema de «reconocimiento de formas» con dos métodos de clasificación: «técnica de k-vecinos» y «modelos ocultos de Markov». Finalmente realizamos una simulación del sistema con 4 ecografistas, comparando su capacidad diagnóstica en escala de gris con imágenes procesadas con nuestro sistema en 408 punciones grabadas, no en tiempo real.

Resultados

La capacidad diagnóstica (curva ROC) con mapeo simple fue de 59,7 y 61,6% con clasificación mediante k-vecinos y modelos ocultos de Markov, respectivamente. Las matrices de coaparición ofrecieron un área bajo la curva ROC de 60,1 y 60,0%. El experimento virtual se llevó a cabo mediante «mapeo simple» y clasificación con «k-vecinos», otorgando una capacidad diagnóstica en cada urólogo de 63,3, 67,0, 64,3 y 63,7% frente a 61,7, 60,5, 66,2 y 60,7% conseguidas con la imagen original.

Conclusiones

La utilización de nuestro método de análisis de imagen tiene una capacidad limitada, aunque estable, en la detección de áreas prostáticas cancerígenas.

Palabras clave:
Cáncer de próstata
Diagnóstico
Ecografía transrectal

Article

These are the options to access the full texts of the publication Actas Urológicas Españolas (English Edition)
Subscriber
Subscriber

If you already have your login data, please click here .

If you have forgotten your password you can you can recover it by clicking here and selecting the option “I have forgotten my password”
Subscribe
Subscribe to

Actas Urológicas Españolas (English Edition)

Purchase
Purchase article

Purchasing article the PDF version will be downloaded

Price 19.34 €

Purchase now
Contact
Phone for subscriptions and reporting of errors
From Monday to Friday from 9 a.m. to 6 p.m. (GMT + 1) except for the months of July and August which will be from 9 a.m. to 3 p.m.
Calls from Spain
932 415 960
Calls from outside Spain
+34 932 415 960
E-mail
Article options
es en pt

¿Es usted profesional sanitario apto para prescribir o dispensar medicamentos?

Are you a health professional able to prescribe or dispense drugs?

Você é um profissional de saúde habilitado a prescrever ou dispensar medicamentos

Quizás le interese:
10.1016/j.acuroe.2021.05.005
No mostrar más