Twin-to-Twin Transfusion Syndrome (TTTS) is a rare pathology that may affect monochorionic twin pregnancies. TTTS depends on the unbalanced blood transfer from one twin (the donor) to the other (the recipient) through abnormal placental vascular anastomoses. Currently, the treatment for TTTS consists of the photo-ablation of abnormal anastomoses in fetoscopic laser surgery.
Residual anastomoses still represent a major complication, and their identification is not a trivial task. Visual challenges such as small field of view, amniotic fluid turbidity, low-resolution imaging, and unfavourable views are due to the position of the insertion site for the tools.
Recently, the first multi-centre large-scale dataset to improve the current state-of-the-art in segmentation and registration in fetoscopy has been presented. However, there is no work in the literature on anastomosis detection to date. There are also no available datasets for this task.
This work aims to develop a deep-learning-based framework for anastomosis detection in intra-operative fetoscopic videos. Considering the challenges of labelling anastomoses, we propose a weakly-supervised strategy by training a multi-task convolutional neural network (CNN) for (i) segmenting vessels in the fetoscopy frame and (ii) classifying frames as containing anastomoses or not. Anastomosis detection is accomplished by relying on class activation mapping (CAM).