A shape-constraint adversarial framework with instance-normalized spatio-temporal features for inter-fetal membrane segmentation.
Deep learning
Fetoscopy
Inter-fetal membrane
Twin-to-Twin transfusion syndrome (TTTS)
Journal
Medical image analysis
ISSN: 1361-8423
Titre abrégé: Med Image Anal
Pays: Netherlands
ID NLM: 9713490
Informations de publication
Date de publication:
05 2021
05 2021
Historique:
received:
27
06
2020
revised:
17
12
2020
accepted:
16
02
2021
pubmed:
2
3
2021
medline:
24
6
2021
entrez:
1
3
2021
Statut:
ppublish
Résumé
During Twin-to-Twin Transfusion Syndrome (TTTS), abnormal vascular anastomoses in the monochorionic placenta can produce uneven blood flow between the fetuses. In the current practice, this syndrome is surgically treated by closing the abnormal connections using laser ablation. Surgeons commonly use the inter-fetal membrane as a reference. Limited field of view, low fetoscopic image quality and high inter-subject variability make the membrane identification a challenging task. However, currently available tools are not optimal for automatic membrane segmentation in fetoscopic videos, due to membrane texture homogeneity and high illumination variability. To tackle these challenges, we present a new deep-learning framework for inter-fetal membrane segmentation on in-vivo fetoscopic videos. The framework enhances existing architectures by (i) encoding a novel (instance-normalized) dense block, invariant to illumination changes, that extracts spatio-temporal features to enforce pixel connectivity in time, and (ii) relying on an adversarial training, which constrains macro appearance. We performed a comprehensive validation using 20 different videos (2000 frames) from 20 different surgeries, achieving a mean Dice Similarity Coefficient of 0.8780±0.1383. The proposed framework has great potential to positively impact the actual surgical practice for TTTS treatment, allowing the implementation of surgical guidance systems that can enhance context awareness and potentially lower the duration of the surgeries.
Sections du résumé
BACKGROUND AND OBJECTIVES
During Twin-to-Twin Transfusion Syndrome (TTTS), abnormal vascular anastomoses in the monochorionic placenta can produce uneven blood flow between the fetuses. In the current practice, this syndrome is surgically treated by closing the abnormal connections using laser ablation. Surgeons commonly use the inter-fetal membrane as a reference. Limited field of view, low fetoscopic image quality and high inter-subject variability make the membrane identification a challenging task. However, currently available tools are not optimal for automatic membrane segmentation in fetoscopic videos, due to membrane texture homogeneity and high illumination variability.
METHODS
To tackle these challenges, we present a new deep-learning framework for inter-fetal membrane segmentation on in-vivo fetoscopic videos. The framework enhances existing architectures by (i) encoding a novel (instance-normalized) dense block, invariant to illumination changes, that extracts spatio-temporal features to enforce pixel connectivity in time, and (ii) relying on an adversarial training, which constrains macro appearance.
RESULTS
We performed a comprehensive validation using 20 different videos (2000 frames) from 20 different surgeries, achieving a mean Dice Similarity Coefficient of 0.8780±0.1383.
CONCLUSIONS
The proposed framework has great potential to positively impact the actual surgical practice for TTTS treatment, allowing the implementation of surgical guidance systems that can enhance context awareness and potentially lower the duration of the surgeries.
Identifiants
pubmed: 33647785
pii: S1361-8415(21)00054-2
doi: 10.1016/j.media.2021.102008
pii:
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
102008Informations de copyright
Copyright © 2021 Elsevier B.V. All rights reserved.
Déclaration de conflit d'intérêts
Declaration of Competing Interest No benefits in any form have been or will be received from a commercial party related directly or indirectly to the subjects of this manuscript.