An end-to-end multi-task system of automatic lesion detection and anatomical localization in whole-body bone scintigraphy by deep learning
Bioinformatics · 2023
DOI: 10.1093/bioinformatics/btac753 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2023. Verfasst von Kaibin Huang und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen 518037, China. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key-Area Research and Development Program of Guangdong Province, Key Technology Development Program of Shenzhen, Department of Education of Guangdong Province.
Abstract (Originalsprache)
Summary Limited by spatial resolution and visual contrast, bone scintigraphy interpretation is susceptible to subjective factors, which considerably affects the accuracy and repeatability of lesion detection and anatomical localization. In this work, we design and implement an end-to-end multi-task deep learning model to perform automatic lesion detection and anatomical localization in whole-body bone scintigraphy. A total of 617 whole-body bone scintigraphy cases including anterior and posterior views were retrospectively analyzed. The proposed semi-supervised model consists of two task flows. The first one, the lesion segmentation flow, received image patches and was trained in a supervised way. The other one, skeleton segmentation flow, was trained on as few as five labeled images in conjunction with the multi-atlas approach, in a semi-supervised way. The two flows joint in their encoder layers so each flow can capture more generalized distribution of the sample space and extract more abstract deep features. The experimental results show that the architecture achieved the highest precision in the finest bone segmentation task in both anterior and posterior images of whole-body scintigraphy. Such an end-to-end approach with very few manual annotation requirement would be suitable for algorithm deployment. Moreover, the proposed approach reliably balances unsupervised labels construction and supervised learning, providing useful insight for weakly labeled image analysis. Supplementary information Supplementary data are available at Bioinformatics online.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen 518037, China.
- National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital & Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Shenzhen 518116, China.
- National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China.
- Shenzhen Key Laboratory of Precision Medicine for Hematological Malignancies, Shenzhen 518037, China.
- Marshall Laboratory of Biomedical Engineering, Shenzhen 518037, China.
ORCID-Profile: Yi Gao
Förderung
- Key-Area Research and Development Program of Guangdong Province
- Key Technology Development Program of Shenzhen
- Department of Education of Guangdong Province
- National Natural Science Foundation of China
- Shenzhen Key Laboratory Foundation
- Shenzhen Peacock Plan
- SZU Top Ranking Project
Zitieren
APA
Huang, K., Huang, S., Chen, G., Li, X., Li, S., Liang, Y., & Gao, Y. (2023). An end-to-end multi-task system of automatic lesion detection and anatomical localization in whole-body bone scintigraphy by deep learning. Bioinformatics. https://doi.org/10.1093/bioinformatics/btac753
Vancouver
Huang K, Huang S, Chen G, Li X, Li S, Liang Y, et al. An end-to-end multi-task system of automatic lesion detection and anatomical localization in whole-body bone scintigraphy by deep learning. Bioinformatics. 2023. doi:10.1093/bioinformatics/btac753
BibTeX
@article{Huang2023,
author = {Huang, Kaibin and Huang, Shengyun and Chen, Guojing and Li, Xue and Li, Shawn and Liang, Ying and Gao, Yi},
title = {An end-to-end multi-task system of automatic lesion detection and anatomical localization in whole-body bone scintigraphy by deep learning},
journal = {Bioinformatics},
year = {2023},
doi = {10.1093/bioinformatics/btac753}
}
EUVIMED