English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Purpose: Ureteroscopy is an efficient endoscopic minimally invasive techniquefor the diagnosis and treatment of upper tract urothelial carcinoma (UTUC).During ureteroscopy, the automatic segmentation of the hollow lumen is ofprimary importance, since it indicates the path that the endoscope shouldfollow. In order to obtain an accurate segmentation of the hollow lumen, thispaper presents an automatic method based on Convolutional Neural Networks(CNNs).  Methods: The proposed method is based on an ensemble of 4 parallel CNNs tosimultaneously process single and multi-frame information. Of these, twoarchitectures are taken as core-models, namely U-Net based in residualblocks($m_1$) and Mask-RCNN($m_2$), which are fed with single still-frames$I(t)$. The other two models ($M_1$, $M_2$) are modifications of the formerones consisting on the addition of a stage which makes use of 3D Convolutionsto process temporal information. $M_1$, $M_2$ are fed with triplets of frames($I(t-1)$, $I(t)$, $I(t+1)$) to produce the segmentation for $I(t)$.  Results: The proposed method was evaluated using a custom dataset of 11videos (2,673 frames) which were collected and manually annotated from 6patients. We obtain a Dice similarity coefficient of 0.80, outperformingprevious state-of-the-art methods.  Conclusion: The obtained results show that spatial-temporal information canbe effectively exploited by the ensemble model to improve hollow lumensegmentation in ureteroscopic images. The method is effective also in presenceof poor visibility, occasional bleeding, or specular reflections.

Using spatial-temporal ensembles of convolutional neural networks for lumen segmentation in ureteroscopy