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

We hypothesize that probabilistic voxel-level classification of anatomy andmalignancy in prostate MRI, although typically posed as near-identicalsegmentation tasks via U-Nets, require different loss functions for optimalperformance due to inherent differences in their clinical objectives. Weinvestigate distribution, region and boundary-based loss functions for bothtasks across 200 patient exams from the publicly-available ProstateX dataset.For evaluation, we conduct a thorough comparative analysis of model predictionsand calibration, measured with respect to multi-class volume segmentation ofthe prostate anatomy (whole-gland, transitional zone, peripheral zone), as wellas, patient-level diagnosis and lesion-level detection of clinicallysignificant prostate cancer. Notably, we find that distribution-based lossfunctions (in particular, focal loss) are well-suited for diagnostic orpanoptic segmentation tasks such as lesion detection, primarily due to theirimplicit property of inducing better calibration. Meanwhile, (with theexception of focal loss) both distribution and region/boundary-based lossfunctions perform equally well for anatomical or semantic segmentation tasks,such as quantification of organ shape, size and boundaries.

Anatomical and Diagnostic Bayesian Segmentation in Prostate MRI $-$Should Different Clinical Objectives Mandate Different Loss Functions?