Your browser doesn't support javascript.
loading
[Study on automatic and rapid diagnosis of distal radius fracture by X-ray].
Liu, Yunpeng; Gan, Kaifeng; Li, Jin; Sun, Dechao; Qiu, Hong; Liu, Dongquan.
Afiliación
  • Liu Y; Information and Computing Science Department, International Exchange College, Ningbo University of Technology, Ningbo, Zhejiang 315000, P. R. China.
  • Gan K; Orthopedics, Lihuili Hospital Affiliated to Ningbo University, Ningbo, Zhejiang 3151000, P. R. China.
  • Li J; Zhejiang Wanli University, Ningbo, Zhejiang 315000, P. R. China.
  • Sun D; College of Digital Technology and Engineering, Ningbo University of Finance & Economics, Ningbo, Zhejiang 315000, P. R. China.
  • Qiu H; Zhejiang Wanli University, Ningbo, Zhejiang 315000, P. R. China.
  • Liu D; Radiology Department, Ninghai First Hospital, Ningbo, Zhejiang 315000, P. R. China.
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi ; 41(4): 798-806, 2024 Aug 25.
Article en Zh | MEDLINE | ID: mdl-39218607
ABSTRACT
This article aims to combine deep learning with image analysis technology and propose an effective classification method for distal radius fracture types. Firstly, an extended U-Net three-layer cascaded segmentation network was used to accurately segment the most important joint surface and non joint surface areas for identifying fractures. Then, the images of the joint surface area and non joint surface area separately were classified and trained to distinguish fractures. Finally, based on the classification results of the two images, the normal or ABC fracture classification results could be comprehensively determined. The accuracy rates of normal, A-type, B-type, and C-type fracture on the test set were 0.99, 0.92, 0.91, and 0.82, respectively. For orthopedic medical experts, the average recognition accuracy rates were 0.98, 0.90, 0.87, and 0.81, respectively. The proposed automatic recognition method is generally better than experts, and can be used for preliminary auxiliary diagnosis of distal radius fractures in scenarios without expert participation.
Asunto(s)
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Fracturas del Radio / Aprendizaje Profundo Límite: Humans Idioma: Zh Revista: Sheng Wu Yi Xue Gong Cheng Xue Za Zhi Asunto de la revista: ENGENHARIA BIOMEDICA Año: 2024 Tipo del documento: Article Pais de publicación: China
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Fracturas del Radio / Aprendizaje Profundo Límite: Humans Idioma: Zh Revista: Sheng Wu Yi Xue Gong Cheng Xue Za Zhi Asunto de la revista: ENGENHARIA BIOMEDICA Año: 2024 Tipo del documento: Article Pais de publicación: China