Scale-attentional U-Net for the segmentation of the median nerve in ultrasound images

Abstract

Purpose: The aim of this study was to develop a neural network that accurately and effectively segments the median nerve in ultrasound (US) images.

Methods: In total, 1,305 images of the median nerve of 123 normal subjects were used to train and evaluate the model. Four datasets from two measurement regions (wrist and forearm) of the nerve and two US machines were used. The neural network was designed for high accuracy by combining information at multiple scales, as well as for high efficiency to prevent overfitting. The model was designed in two parts (cascaded and factorized convolutions), followed by selfattention over scale and channel features. The precision, recall, dice similarity coefficient (DSC), and Hausdorff distance (HD) were used as performance metrics. The area under the receiver operating characteristic curve (AUC) was also assessed.

Results: In the wrist datasets, the proposed network achieved 92.7% and 90.3% precision, 92.4% and 89.8% recall, DSCs of 92.3% and 89.7%, HDs of 5.158 and 4.966, and AUCs of 0.9755 and 0.9399 on two machines. In the forearm datasets, 79.3% and 87.8% precision, 76.0% and 85.0% recall, DSCs of 76.1% and 85.8%, HDs of 5.206 and 4.527, and AUCs of 0.8846 and 0.9150 were achieved. In all datasets, the model developed herein achieved better performance in terms of DSC than previous U-Net-based systems.

Conclusion: The proposed neural network yields accurate segmentation results to assist clinicians in identifying the median nerve.

Keywords: Artificial intelligence; Deep learning; Median nerve; Neural networks; Ultrasound.

Fig. 1.. Overview of the proposed method.

The idea is to compute convolutional features over multiple scales, weight features by their importance, and combine and mix scale features to capture contextual information as well as the detailed echotexture, while enhancing the architectural efficiency to prevent overfitting. The proposed convolutional layer is integrated into the U-Net architecture for ultrasonography image segmentation.

Fig. 2.. Architecture of scale-attentional convolution.

A. Cascaded convolutions are performed without nonlinearity or pooling in-between, effectively using receptive fields of varying sizes. B. Intermediate convolutional outputs form a concatenated feature map to which self-attention is applied in order to select and mix important scale features.

Fig. 3.. Receiver operating characteristic curve of the proposed model in four datasets.

The curves are HM70A-Wrist (A), HM70A-Forearm (B), miniSONO-Wrist (C) and miniSONO-Forearm (D), respectively. TPR, true positive rate; FPR, false positive rate; AUC, area under the receiver operating characteristic curve.

Fig. 4.. Segmentation results on the wrist with HM70A (A-D), forearm with HM70A (E-H), wrist with miniSONO (I-L), and forearm with miniSONO (M-P).

The green line is the median nerve area annotated by the expert, and the red line is the area predicted by the proposed model.

Fig. 5.. Notable cases.

A, B. Bifid median nerves are found by the proposed model. C, D. Label ambiguity is caused by subjective annotation. E, F. Perineurium is misidentified. G. Non-elliptical shape is detection. H. Nerve is detected incorrectly. The green line is the median nerve area annotated by the expert, and the red line is the area predicted by the proposed model.