Your browser doesn't support javascript.
loading
Random Fourier Features-Based Deep Learning Improvement with Class Activation Interpretability for Nerve Structure Segmentation.
Jimenez-Castaño, Cristian Alfonso; Álvarez-Meza, Andrés Marino; Aguirre-Ospina, Oscar David; Cárdenas-Peña, David Augusto; Orozco-Gutiérrez, Álvaro Angel.
Afiliación
  • Jimenez-Castaño CA; Automatic Research Group, Universidad Tecnológica de Pereira, Pereira 660003, Colombia.
  • Álvarez-Meza AM; Signal Processing and Recognition Group, Universidad Nacional de Colombia, Manizales 170003, Colombia.
  • Aguirre-Ospina OD; Medicina Hospitalaria, Servicios Especiales de Salud (SES) Hospital de Caldas, Manizales 170003, Colombia.
  • Cárdenas-Peña DA; Automatic Research Group, Universidad Tecnológica de Pereira, Pereira 660003, Colombia.
  • Orozco-Gutiérrez ÁA; Automatic Research Group, Universidad Tecnológica de Pereira, Pereira 660003, Colombia.
Sensors (Basel) ; 21(22)2021 Nov 20.
Article en En | MEDLINE | ID: mdl-34833817
Peripheral nerve blocking (PNB) is a standard procedure to support regional anesthesia. Still, correct localization of the nerve's structure is needed to avoid adverse effects; thereby, ultrasound images are used as an aid approach. In addition, image-based automatic nerve segmentation from deep learning methods has been proposed to mitigate attenuation and speckle noise ultrasonography issues. Notwithstanding, complex architectures highlight the region of interest lacking suitable data interpretability concerning the learned features from raw instances. Here, a kernel-based deep learning enhancement is introduced for nerve structure segmentation. In a nutshell, a random Fourier features-based approach was utilized to complement three well-known semantic segmentation architectures, e.g., fully convolutional network, U-net, and ResUnet. Moreover, two ultrasound image datasets for PNB were tested. Obtained results show that our kernel-based approach provides a better generalization capability from image segmentation-based assessments on different nerve structures. Further, for data interpretability, a semantic segmentation extension of the GradCam++ for class-activation mapping was used to reveal relevant learned features separating between nerve and background. Thus, our proposal favors both straightforward (shallow) and complex architectures (deeper neural networks).
Asunto(s)
Palabras clave

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Procesamiento de Imagen Asistido por Computador / Aprendizaje Profundo Tipo de estudio: Clinical_trials / Diagnostic_studies Idioma: En Revista: Sensors (Basel) Año: 2021 Tipo del documento: Article País de afiliación: Colombia Pais de publicación: Suiza

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Procesamiento de Imagen Asistido por Computador / Aprendizaje Profundo Tipo de estudio: Clinical_trials / Diagnostic_studies Idioma: En Revista: Sensors (Basel) Año: 2021 Tipo del documento: Article País de afiliación: Colombia Pais de publicación: Suiza