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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Kidney stones represent a considerable burden for public health-care systems.Ureteroscopy with laser lithotripsy has evolved as the most commonly usedtechnique for the treatment of kidney stones. Automated segmentation of kidneystones and laser fiber is an important initial step to performing any automatedquantitative analysis of the stones, particularly stone-size estimation, thathelps the surgeon decide if the stone requires more fragmentation. Factors suchas turbid fluid inside the cavity, specularities, motion blur due to kidneymovements and camera motion, bleeding, and stone debris impact the quality ofvision within the kidney and lead to extended operative times. To the best ofour knowledge, this is the first attempt made towards multi-class segmentationin ureteroscopy and laser lithotripsy data. We propose an end-to-end CNN-basedframework for the segmentation of stones and laser fiber. The proposed approachutilizes two sub-networks: HybResUNet, a version of residual U-Net, that usesresidual connections in the encoder path of U-Net and a DVFNet that generatesDVF predictions which are then used to prune the prediction maps. We alsopresent ablation studies that combine dilated convolutions, recurrent andresidual connections, ASPP and attention gate. We propose a compound lossfunction that improves our segmentation performance. We have also provided anablation study to determine the optimal data augmentation strategy. Ourqualitative and quantitative results illustrate that our proposed methodoutperforms SOTA methods such as UNet and DeepLabv3+ showing an improvement of5.2% and 15.93%, respectively, for the combined mean of DSC and JI in ourinvivo test dataset. We also show that our proposed model generalizes better ona new clinical dataset showing a mean improvement of 25.4%, 20%, and 11% overUNet, HybResUNet, and DeepLabv3+, respectively, for the same metric.

Multi-class motion-based semantic segmentation for ureteroscopy and laser lithotripsy