Potential for computer-aided diagnosis using a convolutional neural network algorithm to diagnose fat-poor angiomyolipoma in enhanced computed tomography and T2-weighted magnetic resonance imaging.

Soma, Takahiko; Ishioka, Junichiro; Tanaka, Hajime; Matsuoka, Yoh; Saito, Kazutaka; Fujii, Yasuhisa

Soma, Takahiko; Ishioka, Junichiro; Tanaka, Hajime; Matsuoka, Yoh; Saito, Kazutaka; Fujii, Yasuhisa.

Afiliación

Soma T; Department of Urology, Tokyo Medical and Dental University Graduate School, Tokyo, Japan.
Ishioka J; Department of Urology, Tokyo Medical and Dental University Graduate School, Tokyo, Japan.
Tanaka H; Department of Urology, Tokyo Medical and Dental University Graduate School, Tokyo, Japan.
Matsuoka Y; Department of Urology, Tokyo Medical and Dental University Graduate School, Tokyo, Japan.
Saito K; Department of Urology, Tokyo Medical and Dental University Graduate School, Tokyo, Japan.
Fujii Y; Department of Urology, Tokyo Medical and Dental University Graduate School, Tokyo, Japan.

Int J Urol ; 25(11): 978-979, 2018 11.

Article en En | MEDLINE | ID: mdl-30136400

Asunto(s)

Angiomiolipoma/diagnóstico por imagen; Diagnóstico por Computador; Neoplasias Renales/diagnóstico por imagen; Algoritmos; Diagnóstico Diferencial; Reacciones Falso Positivas; Humanos; Imagen por Resonancia Magnética; Redes Neurales de la Computación; Curva ROC; Tomografía Computarizada por Rayos X

Texto completo

Imprimir

XML

PubMed Links

Buscar en Google

Texto completo: 1 Base de datos: MEDLINE Asunto principal: Diagnóstico por Computador / Angiomiolipoma / Neoplasias Renales Tipo de estudio: Diagnostic_studies / Prognostic_studies Idioma: En Revista: Int J Urol Asunto de la revista: UROLOGIA Año: 2018 Tipo del documento: Article

Texto completo

Imprimir

XML

PubMed Links

Buscar en Google