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

Identifying the type of kidney stones can allow urologists to determine theircause of formation, improving the prescription of appropriate treatments todiminish future relapses. Currently, the associated ex-vivo diagnosis (known asMorpho-constitutional Analysis, MCA) is time-consuming, expensive and requiresa great deal of experience, as it requires a visual analysis component that ishighly operator dependant. Recently, machine learning methods have beendeveloped for in-vivo endoscopic stone recognition. Deep Learning (DL) basedmethods outperform non-DL methods in terms of accuracy but lack explainability.Despite this trade-off, when it comes to making high-stakes decisions, it'simportant to prioritize understandable Computer-Aided Diagnosis (CADx) thatsuggests a course of action based on reasonable evidence, rather than a modelprescribing a course of action. In this proposal, we learn Prototypical Parts(PPs) per kidney stone subtype, which are used by the DL model to generate anoutput classification. Using PPs in the classification task enables case-basedreasoning explanations for such output, thus making the model interpretable. Inaddition, we modify global visual characteristics to describe their relevanceto the PPs and the sensitivity of our model's performance. With this, weprovide explanations with additional information at the sample, class and modellevels in contrast to previous works. Although our implementation's averageaccuracy is lower than state-of-the-art (SOTA) non-interpretable DL models by1.5 %, our models perform 2.8% better on perturbed images with a lower standarddeviation, without adversarial training. Thus, Learning PPs has the potentialto create more robust DL models.

Deep Prototypical-Parts Ease Morphological Kidney Stone Identification and are Competitively Robust to Photometric Perturbations