Convolutional neural network for brachial plexus segmentation at the interscalene level

Abstract

Background: Regional anesthesia with ultrasound-guided brachial plexus block is widely used for patients undergoing shoulder and upper limb surgery, but needle misplacement can result in complications. The purpose of this study was to develop and validate a convolutional neural network (CNN) model for segmentation of the brachial plexus at the interscalene level.

Methods: This prospective study included patients who underwent ultrasound-guided brachial plexus block in the Anesthesiology Department of Beijing Jishuitan Hospital between October 2019 and June 2022. A Unet semantic segmentation model was developed to train the CNN to identify the brachial plexus features in the ultrasound images. The degree of overlap between the predicted segmentation and ground truth segmentation (manually drawn by experienced clinicians) was evaluated by calculation of the Dice index and Jaccard index.

Results: The final analysis included 502 images from 127 patients aged 41 ± 14 years-old (72 men, 56.7%). The mean Dice index was 0.748 ± 0.190, which was extremely close to the threshold level of 0.75 for good overlap between the predicted and ground truth segregations. The Jaccard index was 0.630 ± 0.213, which exceeded the threshold value of 0.5 for a good overlap.

Conclusion: The CNN performed well at segregating the brachial plexus at the interscalene level. Further development could allow the CNN to be used to facilitate real-time identification of the brachial plexus during interscalene block administration.

Clinical trial registration: The trial was registered prior to patient enrollment at the Chinese Clinical Trial Registry (ChiCTR2200055591), the site url is https://www.chictr.org.cn/ . The date of trial registration and patient enrollment is 14/01/2022.

Keywords: Anesthesia regional; Brachial plexus block; Neural network models; Ultrasound imaging; Validation study.

Fig. 1

Ultrasound images acquired at various levels. (A) Images acquired at the supraclavicular region. The area containing nerves (and including as many nerves as possible) but excluding the middle scalene muscle was marked (N, right-hand images). The subclavian artery was also marked (SA). (B) Images acquired at a region between the supraclavicular area and the level of the transverse process of C7. The area containing all the nerves (C5–C7 as well as C8 if it was clearly visible on the surface of the first rib) was marked (N). (C) Images acquired at the level of the transverse process of C7. The area containing the nerves (C5 and C6 plus C7 if the surface of the transverse process of C7 was clearly displayed) was marked (N)

Fig. 2

Metrics used to validate the convolutional neural network. (A) Calculation of the Dice index. (B) Calculation of the Jaccard index

Fig. 3

Distribution of the Dice index and Jaccard index. Each circle is color-coded according to the number of number of segmentations with a particular Dice Index and Jaccard index. The color represents the frequency of occurrence and the darker the color, the more IOU and DICE appear. IOU: Jaccard index (also known as the Intersection-Over-Union).