Slic-Seg: A minimally interactive segmentation of the placenta from sparse and motion-corrupted fetal MRI in multiple views

Abstract

HighlightsMinimal user interaction is needed for a good segmentation of the placenta.Random forests with high level features improved the segmentation.Higher accuracy than state-of-the-art interactive segmentation methods.Co-segmentation of multiple volumes outperforms single sparse volume based method.

In vivo placental MRI shape and textural features predict fetal growth restriction and postnatal outcome

“…39 To the best of our knowledge, only two methods currently exist tackling the problem of automatic 39 or semi-automatic placenta segmentation on MR data. 40 In Alansary et al, 39 the authors reported an accuracy of 71.95 6 19.79% for healthy fetuses and 66.89 6 15.35% for a cohort mixing FGR fetuses. The semi-automated segmentation proposed in Wang et al 40 presented better results on healthy fetuses taking advantage of multiple views of the same placenta.…”

“…Automation of placental segmentation on MRI data remains a challenging task due to its variability in shape, orientation, position, and appearance . To the best of our knowledge, only two methods currently exist tackling the problem of automatic or semi‐automatic placenta segmentation on MR data . In Alansary et al, the authors reported an accuracy of 71.95 ± 19.79% for healthy fetuses and 66.89 ± 15.35% for a cohort mixing FGR fetuses.…”

“…In Alansary et al, the authors reported an accuracy of 71.95 ± 19.79% for healthy fetuses and 66.89 ± 15.35% for a cohort mixing FGR fetuses. The semi‐automated segmentation proposed in Wang et al presented better results on healthy fetuses taking advantage of multiple views of the same placenta. However, our study protocol only included a single orientation acquisition; therefore, we believed manual segmentations would provide the most optimal results.…”

GIFT-Cloud: A data sharing and collaboration platform for medical imaging research

“…However, such an image-based diagnosis and surgical planning system requires robust and accurate segmentation of fetal and maternal organs from MRI images acquired during the diagnostic phase. To assist with this, we have developed an advanced computational method for semi-automated organ segmentation, focussing initially on the placenta [24] . The ongoing development and assessment of this method requires recurring testing and validation with new data.…”

“…The hospital Gateway internally stores the mapping between patient ID and pseudonymised research ID for future reference. Researchers retrieve the anonymised data using software integrated with GIFT-Cloud, perform the segmentation using Slic-Seg [24] and upload the resulting segmentation mask to the server. The clinicians can access and evaluate the resulting segmentation through the GIFT-Cloud web interface or by downloading the data to their own systems.…”