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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

In this work, we propose a deep U-Net based model to tackle the challengingtask of prostate cancer segmentation by aggressiveness in MRI based on weakscribble annotations. This model extends the size constraint loss proposed byKervadec et al. 1 in the context of multiclass detection and segmentation task.This model is of high clinical interest as it allows training on prostatebiopsy samples and avoids time-consuming full annotation process. Performanceis assessed on a private dataset (219 patients) where the full ground truth isavailable as well as on the ProstateX-2 challenge database, where only biopsyresults at different localisations serve as reference. We show that we canapproach the fully-supervised baseline in grading the lesions by using only6.35% of voxels for training. We report a lesion-wise Cohen's kappa score of0.29 $\pm$ 0.07 for the weak model versus 0.32 $\pm$ 0.05 for the baseline. Wealso report a kappa score (0.276 $\pm$ 0.037) on the ProstateX-2 challengedataset with our weak U-Net trained on a combination of ProstateX-2 and ourdataset, which is the highest reported value on this challenge dataset for asegmentation task to our knowledge.

Learning to segment prostate cancer by aggressiveness from scribbles in bi-parametric MRI