Inter-foetus Membrane Segmentation for TTTS Using Adversarial Networks
| Autor: | Alessandro Casella, Elena De Momi, Leonardo S. Mattos, Sara Moccia, Dario Paladini, Emanuele Frontoni |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Adult
Laser surgery Databases Factual Computer science medicine.medical_treatment 0206 medical engineering Extraembryonic Membranes Biomedical Engineering Intraoperative-image segmentation 02 engineering and technology Models Biological Fetoscopy Pregnancy Encoding (memory) Image Processing Computer-Assisted medicine Humans Minimally Invasive Surgical Procedures Segmentation Adversarial networks Deep learning Artificial neural network medicine.diagnostic_test business.industry Pattern recognition Fetofetal Transfusion 020601 biomedical engineering Identification (information) Female Laser Therapy Neural Networks Computer Noise (video) Artificial intelligence Tomography X-Ray Computed business |
| Popis: | Twin-to-Twin Transfusion Syndrome is commonly treated with minimally invasive laser surgery in fetoscopy. The inter-foetal membrane is used as a reference to find abnormal anastomoses. Membrane identification is a challenging task due to small field of view of the camera, presence of amniotic liquid, foetus movement, illumination changes and noise. This paper aims at providing automatic and fast membrane segmentation in fetoscopic images. We implemented an adversarial network consisting of two Fully-Convolutional Neural Networks. The former (the segmentor) is a segmentation network inspired by U-Net and integrated with residual blocks, whereas the latter acts as critic and is made only of the encoding path of the segmentor. A dataset of 900 images acquired in 6 surgical cases was collected and labelled to validate the proposed approach. The adversarial networks achieved a median Dice similarity coefficient of 91.91% with Inter-Quartile Range (IQR) of 4.63%, overcoming approaches based on U-Net (82.98%-IQR: 14.41%) and U-Net with residual blocks (86.13%-IQR: 13.63%). Results proved that the proposed architecture could be a valuable and robust solution to assist surgeons in providing membrane identification while performing fetoscopic surgery. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|