Fetal Re-Identification in Multiple Pregnancy Ultrasound Images Using Deep Learning

Gabler E, Nissen M, Altstidl TR, Titzmann A, Packhäuser K, Maier A, Fasching P, Eskofier B, Leutheuser H (2023)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2023

Journal

Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society IEEE Engineering in Medicine and Biology Society

Publisher: Institute of Electrical and Electronics Engineers Inc.

Series: Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

Pages Range: 1-4

Conference Proceedings Title: 2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)

Event location: Sydney, NSW AU

ISBN: 979-8-3503-2447-1

DOI: 10.1109/EMBC40787.2023.10340336

Abstract

Ultrasound examinations during pregnancy can detect abnormal fetal development, which is a leading cause of perinatal mortality. In multiple pregnancies, the position of the fetuses may change between examinations. The individual fetus cannot be clearly identified. Fetal re-identification may improve diagnostic capabilities by tracing individual fetal changes. This work evaluates the feasibility of fetal re-identification on FETAL-PLANES-DB, a publicly available dataset of singleton pregnancy ultrasound images. Five dataset subsets with 6,491 images from 1,088 pregnant women and two re-identification frameworks (Torchreid, FastReID) are evaluated. FastReID achieves a mean average precision of 68.77% (68.42%) and mean precision at rank 10 score of 89.60% (95.55%) when trained on images showing the fetal brain (abdomen). Visualization with gradient-weighted class activation mapping shows that the classifiers appear to rely on anatomical features. We conclude that fetal re-identification in ultrasound images may be feasible. However, more work on additional datasets, including images from multiple pregnancies and several subsequent examinations, is required to ensure and investigate performance stability and explainability.Clinical relevance - To date, fetuses in multiple pregnancies cannot be distinguished between ultrasound examinations. This work provides the first evidence for feasibility of fetal re-identification in pregnancy ultrasound images. This may improve diagnostic capabilities in clinical practice in the future, such as longitudinal analysis of fetal changes or abnormalities.

Authors with CRIS profile

Michael Nissen Machine Learning and Data Analytics Lab Thomas Robert Altstidl Machine Learning and Data Analytics Lab Adriana Titzmann Department of Obstetrics and Gynaecology Kai Packhäuser Lehrstuhl für Informatik 5 (Mustererkennung) Andreas Maier Lehrstuhl für Informatik 5 (Mustererkennung) Peter Fasching Professur für Translationale Frauenheilkunde und Geburtshilfe Björn Eskofier Machine Learning and Data Analytics Lab Heike Leutheuser Machine Learning and Data Analytics Lab

How to cite

APA:

Gabler, E., Nissen, M., Altstidl, T.R., Titzmann, A., Packhäuser, K., Maier, A.,... Leutheuser, H. (2023). Fetal Re-Identification in Multiple Pregnancy Ultrasound Images Using Deep Learning. In 2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (pp. 1-4). Sydney, NSW, AU: Institute of Electrical and Electronics Engineers Inc..

MLA:

Gabler, Elisabeth, et al. "Fetal Re-Identification in Multiple Pregnancy Ultrasound Images Using Deep Learning." Proceedings of the 45th Annual International Conference of the IEEE Engineering in Medicine and Biology Conference, EMBC 2023, Sydney, NSW Institute of Electrical and Electronics Engineers Inc., 2023. 1-4.

BibTeX: Download