Nerve Structure Segmentation from Ultrasound Images Using Random Under-Sampling and an SVM Classifier

Jimenez, C.; Diaz, Damaris; Salazar, David R. Castillo; Alvarez, Azucena L.; Orozco, Álvaro A.; Henao, Oscar

doi:10.1007/978-3-319-93000-8_65

Cited by 1 publication

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thereby, let Ĩ(λ) = S(λ) I be the explanation map of image I with respect to the normalized class activation mapping S(λ) = S(λ)/ max(S(λ)) at a given layer of interest. Moreover, let ỹ(λ) = E{ Gij : ∀i, j|M ij = λ} be the expected class-conditional score concerning S(λ), where G = W L ⊗ FL−1 + B L , Gij ∈ G, fixing F0 = Ĩ(λ), that is, the explanation map Ĩ(λ) feeds the deep learning predictor in Equation (1) till the penultimate layer that holds a linear activation to preserve a class-conditional score activation as in Equation (7). Then, the following relevance analysis measures arises:…”

Section: Methods Comparison Performance Measures and Implementation Detailsmentioning

confidence: 99%

“…Among the works proposed, feature engineering-based techniques employ wavelet transform, standard deviation, and entropy-based super-pixel representations. Further, the predefined features are used to feed a classifier for nerve segmentation [7,8]. Nevertheless, hand-computed features can yield poor segmentation results, not to mention their high computational burden [9,10].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Random Fourier Features-Based Deep Learning Improvement with Class Activation Interpretability for Nerve Structure Segmentation

Jimenez-Castaño

Álvarez-Meza

Aguirre-Ospina

et al. 2021

Sensors

View full text Add to dashboard Cite

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).

show abstract

Section: Methods Comparison Performance Measures and Implementation Detailsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Random Fourier Features-Based Deep Learning Improvement with Class Activation Interpretability for Nerve Structure Segmentation

Jimenez-Castaño

Álvarez-Meza

Aguirre-Ospina

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

Nerve Structure Segmentation from Ultrasound Images Using Random Under-Sampling and an SVM Classifier

Cited by 1 publication

References 6 publications

Random Fourier Features-Based Deep Learning Improvement with Class Activation Interpretability for Nerve Structure Segmentation

Random Fourier Features-Based Deep Learning Improvement with Class Activation Interpretability for Nerve Structure Segmentation

Contact Info

Product

Resources

About