EUVIMEDDescoperă EUVIMED
Crossref

Topology‐preserving segmentation of abdominal muscle layers from ultrasound images

Feiyang Liao, Dongli Li, Xiaoyu Yang, Weiwei Cao, Dehui Xiang, Gang Yuan, Yingwei Wang, Jian Zheng

Medical Physics · 2024

DOI: 10.1002/mp.17377 ↗

At a glance

Journal article in Medical Physics, 2024. Written by Feiyang Liao and 7 co-authors. Institution: Division of Life Sciences and Medicine, School of Biomedical Engineering (Suzhou), University of Science and Technology of China, Suzhou, China. Major MEDLINE topics: Ultrasonography, Image Processing, Computer-Assisted, Abdominal Muscles, Deep Learning. 30 references. Funded by: National Natural Science Foundation of China, Natural Science Foundation of Shandong Province, Foundation of Shanghai Municipal Key Clinical Specialty.

RezumatSubjectsDate bibliograficeCiteRelated studies

Abstract (original language)

Background

In clinical anesthesia, precise segmentation of muscle layers from abdominal ultrasound images is crucial for identifying nerve block locations accurately. Despite deep learning advancements, challenges persist in segmenting muscle layers with accurate topology due to pseudo and weak edges caused by acoustic artifacts in ultrasound imagery.

Purpose

To assist anesthesiologists in locating nerve block areas, we have developed a novel deep learning algorithm that can accurately segment muscle layers in abdominal ultrasound images with interference.

Methods

We propose a comprehensive approach emphasizing the preservation of the segmentation's low‐rank property to ensure correct topology. Our methodology integrates a Semantic Feature Extraction (SFE) module for redundant encoding, a Low‐rank Reconstruction (LR) module to compress this encoding, and an Edge Reconstruction (ER) module to refine segmentation boundaries. Our evaluation involved rigorous testing on clinical datasets, comparing our algorithm against seven established deep learning‐based segmentation methods using metrics such as Mean Intersection‐over‐Union (MIoU) and Hausdorff distance (HD). Statistical rigor was ensured through effect size quantification with Cliff's Delta, Multivariate Analysis of Variance (MANOVA) for multivariate analysis, and application of the Holm‐Bonferroni method for multiple comparisons correction.

Results

We demonstrate that our method outperforms other industry‐recognized deep learning approaches on both MIoU and HD metrics, achieving the best outcomes with 88.21%/4.98 () on the standard test set and 85.48%/6.98 () on the challenging test set. The best&worst results for the other models on the standard test set were (87.20%/5.72)&(83.69%/8.12), and on the challenging test set were (81.25%/10.00)&(71.74%/16.82). Ablation studies further validate the distinct contributions of the proposed modules, which synergistically achieve a balance between maintaining topological integrity and edge precision.

Conclusions

Our findings validate the effective segmentation of muscle layers with accurate topology in complex ultrasound images, leveraging low‐rank constraints. The proposed method not only advances the field of medical imaging segmentation but also offers practical benefits for clinical anesthesia by improving the reliability of nerve block localization.

Subjects

MeSH terms (MEDLINE)

UltrasonographyImage Processing, Computer-AssistedAbdominal MusclesDeep LearningHumansAlgorithms

Author keywords

low‐rank constraintmuscle layer segmentationultrasound image

Authors and institutions

  • Division of Life Sciences and Medicine, School of Biomedical Engineering (Suzhou), University of Science and Technology of China, Suzhou, China.
  • Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Science, Suzhou, China.
  • Department of Anesthesiology, Huashan Hospital, Fudan University, Shanghai, China.
  • School of Electronic and Information Engineering, Soochow University, Jiangsu, China.
  • Jinan Guoke Medical Technology Development Co., Ltd, Jinan, China.

Funding

  • National Natural Science Foundation of China
  • Natural Science Foundation of Shandong Province
  • Foundation of Shanghai Municipal Key Clinical Specialty

Cite

APA

Liao, F., Li, D., Yang, X., Cao, W., Xiang, D., Yuan, G., Wang, Y., & Zheng, J. (2024). Topology‐preserving segmentation of abdominal muscle layers from ultrasound images. Medical Physics. https://doi.org/10.1002/mp.17377

Vancouver

Liao F, Li D, Yang X, Cao W, Xiang D, Yuan G, et al. Topology‐preserving segmentation of abdominal muscle layers from ultrasound images. Medical Physics. 2024. doi:10.1002/mp.17377

BibTeX
@article{Liao2024,
  author = {Liao, Feiyang and Li, Dongli and Yang, Xiaoyu and Cao, Weiwei and Xiang, Dehui and Yuan, Gang and Wang, Yingwei and Zheng, Jian},
  title = {Topology‐preserving segmentation of abdominal muscle layers from ultrasound images},
  journal = {Medical Physics},
  year = {2024},
  doi = {10.1002/mp.17377}
}
Start for free →