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

Zhao, Wei1; Su, Xiuyun2; Guo, Yao1; Li, Haojin3; Basnet, Shiva1; Chen, Jianyu3; Yang, Zide3; Zhong, Rihang3; Liu, Jiang3; Chui, Elvis Chun-Sing4; Pei, Guoxian1,2,5,6; Li, Heng3,7

2023-06-01

10.21037/qims-23-9

QUANTITATIVE IMAGING IN MEDICINE AND SURGERY   影响因子和分区

2223-4292

2223-4306

Background: 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: 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: 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 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: 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.

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

SCI

英语

第一 ; 通讯

Shenzhen Science and Technology Program (CN)[SGDX20211123114204007] ; Basic and Applied Fundamental Research Foundation of Guangdong Province[2020A1515110286] ; China Postdoctoral Science Foundation, No. 72 General Fund[2022M721474] ; Research Startup Fund of the Southern University of Science and Technology[Y01416214]

Radiology, Nuclear Medicine & Medical Imaging

Radiology, Nuclear Medicine & Medical Imaging

WOS:001021639500001

AME PUBLISHING COMPANY

Web of Science

1.Southern Univ Sci & Technol, Sch Med, Shenzhen, Peoples R China
2.Southern Univ Sci, Technol Hosp, Med Intelligence & Innovat Acad, Shenzhen, Peoples R China
3.Southern Univ Sci & Technol, Dept Comp Sci & Engn, Shenzhen, Peoples R China
4.Chinese Univ Hong Kong, Dept Orthopaed & Traumatol, Hong Kong, Peoples R China
5.Southern Univ Sci, Technol Hosp, Med Intelligence & Innovat Acad, 6019 Liuxian Rd, Shenzhen 518055, Guangdong, Peoples R China
6.Southern Univ Sci & Technol, Sch Med, 1088 Xueyuan Rd, Shenzhen 518055, Guangdong, Peoples R China
7.Southern Univ Sci & Technol, Dept Comp Sci & Engn, 1088 Xueyuan Rd, Shenzhen 518055, Guangdong, Peoples R China

Zhao, Wei,Su, Xiuyun,Guo, Yao,et al. Deep learning based ultrasonic visualization of distal humeral cartilage for image-guided therapy: a pilot validation study[J]. QUANTITATIVE IMAGING IN MEDICINE AND SURGERY,2023.

Zhao, Wei.,Su, Xiuyun.,Guo, Yao.,Li, Haojin.,Basnet, Shiva.,...&Li, Heng.(2023).Deep learning based ultrasonic visualization of distal humeral cartilage for image-guided therapy: a pilot validation study.QUANTITATIVE IMAGING IN MEDICINE AND SURGERY.

Zhao, Wei,et al."Deep learning based ultrasonic visualization of distal humeral cartilage for image-guided therapy: a pilot validation study".QUANTITATIVE IMAGING IN MEDICINE AND SURGERY (2023).