Deep Learning‐Based Segmentation and Risk Stratification for Gastrointestinal Stromal Tumors in Transabdominal Ultrasound Imaging
Journal of Ultrasound in Medicine · 2024
DOI: 10.1002/jum.16489 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Ultrasound in Medicine, 2024. Verfasst von Minling Zhuo und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Ultrasound, Fujian Medical University Union Hospital, Fuzhou, China. Hauptthemen laut MEDLINE: Gastrointestinal Stromal Tumors, Deep Learning, Ultrasonography. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 33 Literaturangaben. Gefördert von: Startup Fund for scientific research, Fujian Medical University.
Abstract (Originalsprache)
Purpose
To develop a deep neural network system for the automatic segmentation and risk stratification prediction of gastrointestinal stromal tumors (GISTs).
Methods
A total of 980 ultrasound (US) images from 245 GIST patients were retrospectively collected. These images were randomly divided (6:2:2) into a training set, a validation set, and an internal test set. Additionally, 188 US images from 47 prospective GIST patients were collected to evaluate the segmentation and diagnostic performance of the model. Five deep learning‐based segmentation networks, namely, UNet, FCN, DeepLabV3+, Swin Transformer, and SegNeXt, were employed, along with the ResNet 18 classification network, to select the most suitable network combination. The performance of the segmentation models was evaluated using metrics such as the intersection over union (IoU), Dice similarity coefficient (DSC), recall, and precision. The classification performance was assessed based on accuracy and the area under the receiver operating characteristic curve (AUROC).
Results
Among the compared models, SegNeXt‐ResNet18 exhibited the best segmentation and classification performance. On the internal test set, the proposed model achieved IoU, DSC, precision, and recall values of 82.1, 90.2, 91.7, and 88.8%, respectively. The accuracy and AUC for GIST risk prediction were 87.4 and 92.0%, respectively. On the external test set, the segmentation models exhibited IoU, DSC, precision, and recall values of 81.0, 89.5, 92.8, and 86.4%, respectively. The accuracy and AUC for GIST risk prediction were 86.7 and 92.5%, respectively.
Conclusion
This two‐stage SegNeXt‐ResNet18 model achieves automatic segmentation and risk stratification prediction for GISTs and demonstrates excellent segmentation and classification performance.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Ultrasound, Fujian Medical University Union Hospital, Fuzhou, China.
- Department of General Surgery, Fujian Medical University Provincial Clinical Medical College, Fujian Provincial Hospital, Fuzhou, China.
ORCID-Profile: Ensheng Xue, Zhikui Chen
Förderung
- Startup Fund for scientific research, Fujian Medical University
Zitieren
APA
Zhuo, M., Chen, X., Guo, J., Qian, Q., Xue, E., & Chen, Z. (2024). Deep Learning‐Based Segmentation and Risk Stratification for Gastrointestinal Stromal Tumors in Transabdominal Ultrasound Imaging. Journal of Ultrasound in Medicine. https://doi.org/10.1002/jum.16489
Vancouver
Zhuo M, Chen X, Guo J, Qian Q, Xue E, Chen Z. Deep Learning‐Based Segmentation and Risk Stratification for Gastrointestinal Stromal Tumors in Transabdominal Ultrasound Imaging. Journal of Ultrasound in Medicine. 2024. doi:10.1002/jum.16489
BibTeX
@article{Zhuo2024,
author = {Zhuo, Minling and Chen, Xing and Guo, Jingjing and Qian, Qingfu and Xue, Ensheng and Chen, Zhikui},
title = {Deep Learning‐Based Segmentation and Risk Stratification for Gastrointestinal Stromal Tumors in Transabdominal Ultrasound Imaging},
journal = {Journal of Ultrasound in Medicine},
year = {2024},
doi = {10.1002/jum.16489}
}
EUVIMED