Direct estimation of fetal head circumference from ultrasound images based on regression CNN

Jing Zhang, Caroline Petitjean, Pierre Lopez, Samia Ainouz
; Proceedings of the Third Conference on Medical Imaging with Deep Learning, PMLR 121:914-922, 2020.

Abstract

The measurement of fetal head circumference (HC) is performed throughout the pregnancy as a key biometric to monitor fetus growth. This measurement is performed on ultrasound images, via the manual fitting of an ellipse. The operation is operator-dependent and as such prone to intra and inter-variability error. There have been attempts to design automated segmentation algorithms to segment fetal head, especially based on deep encoding-decoding architectures. In this paper, we depart from this idea and propose to leverage the ability of convolutional neural networks (CNN) to directly measure the head circumference, without having to resort to handcrafted features or manually labeled segmented images. The intuition behind this idea is that the CNN will learn itself to localize and identify the head contour. Our approach is experimented on the public HC18 dataset, that contains images of all trimesters of the pregnancy. We investigate various architectures and three losses suitable for regression. While room for improvement is left, encouraging results show that it might be possible in the future to directly estimate the HC - without the need for a large dataset of manually segmented ultrasound images. This approach might be extended to other applications where segmentation is just an intermediate step to the computation of biomarkers.

Cite this Paper


BibTeX
@InProceedings{pmlr-v121-zhang20a, title = {Direct estimation of fetal head circumference from ultrasound images based on regression CNN}, author = {Zhang, Jing and Petitjean, Caroline and Lopez, Pierre and Ainouz, Samia}, pages = {914--922}, year = {2020}, editor = {Tal Arbel and Ismail Ben Ayed and Marleen de Bruijne and Maxime Descoteaux and Herve Lombaert and Christopher Pal}, volume = {121}, series = {Proceedings of Machine Learning Research}, address = {Montreal, QC, Canada}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v121/zhang20a/zhang20a.pdf}, url = {http://proceedings.mlr.press/v121/zhang20a.html}, abstract = {The measurement of fetal head circumference (HC) is performed throughout the pregnancy as a key biometric to monitor fetus growth. This measurement is performed on ultrasound images, via the manual fitting of an ellipse. The operation is operator-dependent and as such prone to intra and inter-variability error. There have been attempts to design automated segmentation algorithms to segment fetal head, especially based on deep encoding-decoding architectures. In this paper, we depart from this idea and propose to leverage the ability of convolutional neural networks (CNN) to directly measure the head circumference, without having to resort to handcrafted features or manually labeled segmented images. The intuition behind this idea is that the CNN will learn itself to localize and identify the head contour. Our approach is experimented on the public HC18 dataset, that contains images of all trimesters of the pregnancy. We investigate various architectures and three losses suitable for regression. While room for improvement is left, encouraging results show that it might be possible in the future to directly estimate the HC - without the need for a large dataset of manually segmented ultrasound images. This approach might be extended to other applications where segmentation is just an intermediate step to the computation of biomarkers.} }
Endnote
%0 Conference Paper %T Direct estimation of fetal head circumference from ultrasound images based on regression CNN %A Jing Zhang %A Caroline Petitjean %A Pierre Lopez %A Samia Ainouz %B Proceedings of the Third Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2020 %E Tal Arbel %E Ismail Ben Ayed %E Marleen de Bruijne %E Maxime Descoteaux %E Herve Lombaert %E Christopher Pal %F pmlr-v121-zhang20a %I PMLR %J Proceedings of Machine Learning Research %P 914--922 %U http://proceedings.mlr.press %V 121 %W PMLR %X The measurement of fetal head circumference (HC) is performed throughout the pregnancy as a key biometric to monitor fetus growth. This measurement is performed on ultrasound images, via the manual fitting of an ellipse. The operation is operator-dependent and as such prone to intra and inter-variability error. There have been attempts to design automated segmentation algorithms to segment fetal head, especially based on deep encoding-decoding architectures. In this paper, we depart from this idea and propose to leverage the ability of convolutional neural networks (CNN) to directly measure the head circumference, without having to resort to handcrafted features or manually labeled segmented images. The intuition behind this idea is that the CNN will learn itself to localize and identify the head contour. Our approach is experimented on the public HC18 dataset, that contains images of all trimesters of the pregnancy. We investigate various architectures and three losses suitable for regression. While room for improvement is left, encouraging results show that it might be possible in the future to directly estimate the HC - without the need for a large dataset of manually segmented ultrasound images. This approach might be extended to other applications where segmentation is just an intermediate step to the computation of biomarkers.
APA
Zhang, J., Petitjean, C., Lopez, P. & Ainouz, S.. (2020). Direct estimation of fetal head circumference from ultrasound images based on regression CNN. Proceedings of the Third Conference on Medical Imaging with Deep Learning, in PMLR 121:914-922

Related Material