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

Abstract

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).

Brachial Plexus Nerve Trunk Recognition From Ultrasound Images: A Comparative Study of Deep Learning Models

“…It is widely used in image enhancement processing. In our experiments, the ultrasound images are CLAHE processed using the builtin toolkit of the image processing tool OpenCV-Python, with clipLimit set to 1 and tileGridSize set to (8,8). By analyzing Table 3, we observe that all models' segmentation accuracy improved after processing the images with CLAHE.…”

“…Vashishtha et al [7] combine the canny edge detection algorithm with the support vector machine (SVM) to achieve neural segmentation in the ultrasonic image. Jimenez et al [8] use random undersampling (RUS) and SVM for neural segmentation of ultrasound images. Although traditional segmentation methods can accomplish segmentation of neural block regions on smaller datasets, they all need to design feature extraction methods manually.…”

Opportunities of AI-powered applications in anesthesiology to enhance patient safety

“…62 AI methods enhanced image processing to improve the identification of the anatomy and the relationship between anatomic structures. 12 By highlighting the relevant structures, AI-enhanced ultrasound imaging can reduce the risk of unwanted needle trauma to the surrounding structures in 62.9% to 86.4% of cases and reduce the risk of block failure in 81.3% of scans. 63 Recent work has also focused on using machine learning to precisely localize and track the needle tip during 2D ultrasound imaging.…”

“…These models excel with complex, multimodal data, such as text, images, and waveforms. Examples of deep learning models include convolutional neural networks that can identify anatomic structures from ultrasound images 12 . While these types of models require high computational resources and may be difficult to interpret, they are highly performant and used in many health care applications today.…”

Ultrasonic Imaging and Sensors

“…In particular, the presence of clutter and texture can make the manual identification and delimitation of structures in ultrasound images difficult, a task that can could be assisted by automatic algorithms. In [ 13 ], Jimenez-Castano et. al.…”