Deep Placental Vessel Segmentation for Fetoscopic Mosaicking

TL;DR

This paper presents a deep learning-based method for placental vessel segmentation in fetoscopic videos, improving mosaicking accuracy and robustness, and introduces a new dataset for benchmarking in vivo fetoscopy vessel segmentation and registration.

Contribution

It introduces the first in vivo fetoscopic vessel segmentation dataset and demonstrates a U-Net based approach for effective vessel segmentation and registration in fetoscopic videos.

Findings

Vessel intensity-based registration outperforms image intensity-based methods.

Drift accumulation is minimized even in long sequences up to 400 frames.

The proposed method provides a robust framework for fetoscopic vessel mapping.

Abstract

During fetoscopic laser photocoagulation, a treatment for twin-to-twin transfusion syndrome (TTTS), the clinician first identifies abnormal placental vascular connections and laser ablates them to regulate blood flow in both fetuses. The procedure is challenging due to the mobility of the environment, poor visibility in amniotic fluid, occasional bleeding, and limitations in the fetoscopic field-of-view and image quality. Ideally, anastomotic placental vessels would be automatically identified, segmented and registered to create expanded vessel maps to guide laser ablation, however, such methods have yet to be clinically adopted. We propose a solution utilising the U-Net architecture for performing placental vessel segmentation in fetoscopic videos. The obtained vessel probability maps provide sufficient cues for mosaicking alignment by registering consecutive vessel maps using the direct intensity-based technique. Experiments on 6 different in vivo fetoscopic videos demonstrate that the vessel intensity-based registration outperformed image intensity-based registration approaches showing better robustness in qualitative and quantitative comparison. We additionally reduce drift accumulation to negligible even for sequences with up to 400 frames and we incorporate a scheme for quantifying drift error in the absence of the ground-truth. Our paper provides a benchmark for fetoscopy placental vessel segmentation and registration by contributing the first in vivo vessel segmentation and fetoscopic videos dataset.