Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Deep Learning on Ultrasound Images Visualizes the Femoral Nerve with Good Precision

Berggreen, Johan LU ; Johansson, Anders LU ; Jahr, John LU ; Möller, Sebastian LU and Jansson, Tomas LU (2023) In Healthcare (Switzerland) 11(2).
Abstract

The number of hip fractures per year worldwide is estimated to reach 6 million by the year 2050. Despite the many advantages of regional blockades when managing pain from such a fracture, these are used to a lesser extent than general analgesia. One reason is that the opportunities for training and obtaining clinical experience in applying nerve blocks can be a challenge in many clinical settings. Ultrasound image guidance based on artificial intelligence may be one way to increase nerve block success rate. We propose an approach using a deep learning semantic segmentation model with U-net architecture to identify the femoral nerve in ultrasound images. The dataset consisted of 1410 ultrasound images that were collected from 48... (More)

The number of hip fractures per year worldwide is estimated to reach 6 million by the year 2050. Despite the many advantages of regional blockades when managing pain from such a fracture, these are used to a lesser extent than general analgesia. One reason is that the opportunities for training and obtaining clinical experience in applying nerve blocks can be a challenge in many clinical settings. Ultrasound image guidance based on artificial intelligence may be one way to increase nerve block success rate. We propose an approach using a deep learning semantic segmentation model with U-net architecture to identify the femoral nerve in ultrasound images. The dataset consisted of 1410 ultrasound images that were collected from 48 patients. The images were manually annotated by a clinical professional and a segmentation model was trained. After training the model for 350 epochs, the results were validated with a 10-fold cross-validation. This showed a mean Intersection over Union of 74%, with an interquartile range of 0.66–0.81.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
artificial intelligence, deep learning, hip fracture, nerve blocks, ultrasound
in
Healthcare (Switzerland)
volume
11
issue
2
article number
184
publisher
MDPI AG
external identifiers
  • pmid:36673552
  • scopus:85146776556
ISSN
2227-9032
DOI
10.3390/healthcare11020184
language
English
LU publication?
yes
id
182e3260-0e78-442d-b4cf-391332ec4163
date added to LUP
2023-02-13 13:50:08
date last changed
2024-06-13 23:38:19
@article{182e3260-0e78-442d-b4cf-391332ec4163,
  abstract     = {{<p>The number of hip fractures per year worldwide is estimated to reach 6 million by the year 2050. Despite the many advantages of regional blockades when managing pain from such a fracture, these are used to a lesser extent than general analgesia. One reason is that the opportunities for training and obtaining clinical experience in applying nerve blocks can be a challenge in many clinical settings. Ultrasound image guidance based on artificial intelligence may be one way to increase nerve block success rate. We propose an approach using a deep learning semantic segmentation model with U-net architecture to identify the femoral nerve in ultrasound images. The dataset consisted of 1410 ultrasound images that were collected from 48 patients. The images were manually annotated by a clinical professional and a segmentation model was trained. After training the model for 350 epochs, the results were validated with a 10-fold cross-validation. This showed a mean Intersection over Union of 74%, with an interquartile range of 0.66–0.81.</p>}},
  author       = {{Berggreen, Johan and Johansson, Anders and Jahr, John and Möller, Sebastian and Jansson, Tomas}},
  issn         = {{2227-9032}},
  keywords     = {{artificial intelligence; deep learning; hip fracture; nerve blocks; ultrasound}},
  language     = {{eng}},
  number       = {{2}},
  publisher    = {{MDPI AG}},
  series       = {{Healthcare (Switzerland)}},
  title        = {{Deep Learning on Ultrasound Images Visualizes the Femoral Nerve with Good Precision}},
  url          = {{http://dx.doi.org/10.3390/healthcare11020184}},
  doi          = {{10.3390/healthcare11020184}},
  volume       = {{11}},
  year         = {{2023}},
}