Deep learning based ultrasonic visualization of distal humeral cartilage for image-guided therapy: a pilot validation study.

Deep learning distal humeral cartilage image-guided therapy (IGT) minimally invasive surgery ultrasound visualization

Journal

Quantitative imaging in medicine and surgery
ISSN: 2223-4292
Titre abrégé: Quant Imaging Med Surg
Pays: China
ID NLM: 101577942

Informations de publication

Date de publication:
01 Aug 2023
Historique:
received: 03 01 2023
accepted: 26 05 2023
medline: 15 8 2023
pubmed: 15 8 2023
entrez: 15 8 2023
Statut: ppublish

Résumé

Ultrasound is widely used for image-guided therapy (IGT) in many surgical fields, thanks to its various advantages, such as portability, lack of radiation and real-time imaging. This article presents the first attempt to utilize multiple deep learning algorithms in distal humeral cartilage segmentation for dynamic, volumetric ultrasound images employed in minimally invasive surgery. The dataset, consisting 5,321 ultrasound images were collected from 12 healthy volunteers. These images were randomly split into training and validation sets in an 8:2 ratio. Based on deep learning algorithms, 9 semantic segmentation networks were developed and trained using our dataset at Southern University of Science and Technology Hospital in September 2022. The performance of the networks was evaluated based on their segmenting accuracy and processing efficiency. Furthermore, these networks were implemented in an IGT system to assess their feasibility in 3-dimentional imaging precision. In 2D segmentation, Medical Transformer (MedT) showed the highest accuracy result with a Dice score of 89.4%, however, the efficiency in processing images was relatively lower at 2.6 frames per second (FPS). In 3D imaging, the average root mean square (RMS) between ultrasound (US)-generated models based on the networks and magnetic resonance imaging (MRI)-generated models was no more than 1.12 mm. The findings of this study indicate the technological feasibility of a novel method for real-time visualization of distal humeral cartilage. The increased precision of ultrasound calibration and segmentation are both important approaches to improve the accuracy of 3D imaging.

Sections du résumé

Background UNASSIGNED
Ultrasound is widely used for image-guided therapy (IGT) in many surgical fields, thanks to its various advantages, such as portability, lack of radiation and real-time imaging. This article presents the first attempt to utilize multiple deep learning algorithms in distal humeral cartilage segmentation for dynamic, volumetric ultrasound images employed in minimally invasive surgery.
Methods UNASSIGNED
The dataset, consisting 5,321 ultrasound images were collected from 12 healthy volunteers. These images were randomly split into training and validation sets in an 8:2 ratio. Based on deep learning algorithms, 9 semantic segmentation networks were developed and trained using our dataset at Southern University of Science and Technology Hospital in September 2022. The performance of the networks was evaluated based on their segmenting accuracy and processing efficiency. Furthermore, these networks were implemented in an IGT system to assess their feasibility in 3-dimentional imaging precision.
Results UNASSIGNED
In 2D segmentation, Medical Transformer (MedT) showed the highest accuracy result with a Dice score of 89.4%, however, the efficiency in processing images was relatively lower at 2.6 frames per second (FPS). In 3D imaging, the average root mean square (RMS) between ultrasound (US)-generated models based on the networks and magnetic resonance imaging (MRI)-generated models was no more than 1.12 mm.
Conclusions UNASSIGNED
The findings of this study indicate the technological feasibility of a novel method for real-time visualization of distal humeral cartilage. The increased precision of ultrasound calibration and segmentation are both important approaches to improve the accuracy of 3D imaging.

Identifiants

pubmed: 37581069
doi: 10.21037/qims-23-9
pii: qims-13-08-5306
pmc: PMC10423345
doi:

Types de publication

Journal Article

Langues

eng

Pagination

5306-5320

Informations de copyright

2023 Quantitative Imaging in Medicine and Surgery. All rights reserved.

Déclaration de conflit d'intérêts

Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://qims.amegroups.com/article/view/10.21037/qims-23-9/coif). The authors have no conflicts of interest to declare.

Références

Magn Reson Imaging. 2012 Nov;30(9):1323-41
pubmed: 22770690
Quant Imaging Med Surg. 2022 Apr;12(4):2397-2415
pubmed: 35371952
Int J Comput Assist Radiol Surg. 2015 Jun;10(6):959-69
pubmed: 25847667
Ann Intern Med. 2015 Jan 6;162(1):W1-73
pubmed: 25560730
Clin Orthop Relat Res. 2006 Dec;453:160-7
pubmed: 17312591
Comput Methods Programs Biomed. 2021 Mar;200:105897
pubmed: 33317873
Comput Methods Programs Biomed. 2021 Aug;207:106211
pubmed: 34134076
Int J Comput Assist Radiol Surg. 2022 Sep;17(9):1663-1672
pubmed: 35588339
Med Image Anal. 2016 Oct;33:181-186
pubmed: 27344106
Ultrasound Med Biol. 2020 Feb;46(2):422-435
pubmed: 31767454
Annu Int Conf IEEE Eng Med Biol Soc. 2019 Jul;2019:966-969
pubmed: 31946054
BMC Bioinformatics. 2017 Jan 25;18(1):68
pubmed: 28122501
Ann Intern Med. 2015 Jan 6;162(1):55-63
pubmed: 25560714
Comput Methods Programs Biomed. 2021 Aug;207:106210
pubmed: 34130088
IEEE Trans Biomed Eng. 2014 Oct;61(10):2527-37
pubmed: 24833412
Med Image Anal. 2020 Feb;60:101631
pubmed: 31927473
Med Image Anal. 2017 Dec;42:60-88
pubmed: 28778026
Quant Imaging Med Surg. 2021 Jan;11(1):300-316
pubmed: 33392030
IEEE Trans Biomed Eng. 2020 Nov;67(11):3234-3241
pubmed: 32167884

Auteurs

Wei Zhao (W)

School of Medicine, Southern University of Science and Technology, Shenzhen, China.

Xiuyun Su (X)

Medical Intelligence and Innovation Academy, Southern University of Science and Technology Hospital, Shenzhen, China.

Yao Guo (Y)

School of Medicine, Southern University of Science and Technology, Shenzhen, China.

Haojin Li (H)

Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China.

Shiva Basnet (S)

School of Medicine, Southern University of Science and Technology, Shenzhen, China.

Jianyu Chen (J)

Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China.

Zide Yang (Z)

Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China.

Rihang Zhong (R)

Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China.

Jiang Liu (J)

Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China.

Elvis Chun-Sing Chui (EC)

Department of Orthopaedics and Traumatology, The Chinese University of Hong Kong, Hong Kong, China.

Guoxian Pei (G)

School of Medicine, Southern University of Science and Technology, Shenzhen, China.
Medical Intelligence and Innovation Academy, Southern University of Science and Technology Hospital, Shenzhen, China.

Heng Li (H)

Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China.

Classifications MeSH