Utility of Artificial Intelligence for Real-Time Anatomical Landmark Identification in Ultrasound-Guided Thoracic Paravertebral Block

Abstract

Thoracic paravertebral block (TPVB) is a common method of inducing perioperative analgesia in thoracic and abdominal surgery. Identifying anatomical structures in ultrasound images is very important especially for inexperienced anesthesiologists who are unfamiliar with the anatomy. Therefore, our aim was to develop an artificial neural network (ANN) to automatically identify (in real-time) anatomical structures in ultrasound images of TPVB. This study is a retrospective study using ultrasound scans (both video and standard still images) that we acquired. We marked the contours of the paravertebral space (PVS), lung, and bone in the TPVB ultrasound image. Based on the labeled ultrasound images, we used the U-net framework to train and create an ANN that enabled real-time identification of important anatomical structures in ultrasound images. A total of 742 ultrasound images were acquired and labeled in this study. In this ANN, the Intersection over Union (IoU) and Dice similarity coefficient (DSC or Dice coefficient) of the paravertebral space (PVS) were 0.75 and 0.86, respectively, the IoU and DSC of the lung were 0.85 and 0.92, respectively, and the IoU and DSC of the bone were 0.69 and 0.83, respectively. The accuracies of the PVS, lung, and bone were 91.7%, 95.4%, and 74.3%, respectively. For tenfold cross validation, the median interquartile range for PVS IoU and DSC was 0.773 and 0.87, respectively. There was no significant difference in the scores for the PVS, lung, and bone between the two anesthesiologists. We developed an ANN for the real-time automatic identification of thoracic paravertebral anatomy. The performance of the ANN was highly satisfactory. We conclude that AI has good prospects for use in TPVB. Clinical registration number: ChiCTR2200058470 (URL: http://www.chictr.org.cn/showproj.aspx?proj=152839 ; registration date: 2022-04-09).

Keywords: Artificial intelligence; Automated; Paravertebral block; U-net; Ultrasound.

Fig. 1

Typical ultrasound images of thoracic paravertebral nerve block and anesthesiologist’s labeling of anatomical structures in ultrasound images. The ultrasound diagram is shown on the left (A, C, E). The labled diagram is shown on the right (B, D, F). A Ultrasound image of bone structural section. B Ultrasound image of bone structural section. C Ultrasound image of standard TPVB section. D Ultrasound image of standard TPVB section. E Modified TPVB section. F Modified TPVB section. Green—bone, yellow—paravertebral space, and red—lungs

Fig. 2

Illustration of the structure of the U-net neural network used in this study

Fig. 3

Prediction of anatomical structure boundaries in TPVB ultrasound images by artificial intelligence. Solid line indicates the area marked by the anesthesiologist. Color overlay indicates AI recognition of the area

Fig. 4

Total IoU and Dice (group-wise) for different groups in cross validation