Leveraging uncertainty information from deep neural networks for disease detection

Christian Leibig; Vaneeda Allken; Murat Seçkin Ayhan; Philipp Berens; Siegfried Wahl

doi:10.1101/084210

CARVIEW

MOTORHOMES

Select Language

HTTP/2 301 date: Mon, 19 Jan 2026 09:05:24 GMT content-length: 0 location: https://doi.org/10.1101/084210 server: cloudflare vary: Origin expires: Tue, 20 Jan 2026 09:05:23 GMT permissions-policy: interest-cohort=(),browsing-topics=() cf-cache-status: DYNAMIC nel: {"report_to":"cf-nel","success_fraction":0.0,"max_age":604800} strict-transport-security: max-age=31536000; includeSubDomains; preload report-to: {"group":"cf-nel","max_age":604800,"endpoints":[{"url":"https://a.nel.cloudflare.com/report/v4?s=uJ81fIdnRHlKRT0FGK3y7iX%2FzM9SujAE66KEdT%2BlLHyHQ%2Fo0kdpl9MssDfxqcGE%2BpiT0Jv0g%2BTP7t6zau20is%2F%2BqupJwvA%3D%3D"}]} cf-ray: 9c052b8bb9011ec2-BLR alt-svc: h3=":443"; ma=86400 HTTP/2 302 date: Mon, 19 Jan 2026 09:05:24 GMT content-type: text/html;charset=utf-8 location: https://biorxiv.org/lookup/doi/10.1101/084210 server: cloudflare vary: Origin vary: Accept expires: Mon, 19 Jan 2026 09:11:00 GMT permissions-policy: interest-cohort=(),browsing-topics=() cf-cache-status: DYNAMIC nel: {"report_to":"cf-nel","success_fraction":0.0,"max_age":604800} strict-transport-security: max-age=31536000; includeSubDomains; preload report-to: {"group":"cf-nel","max_age":604800,"endpoints":[{"url":"https://a.nel.cloudflare.com/report/v4?s=jaRto7nYWsZz3zVQt235QuBS2A%2FYAhyMs0nRUgjdsV%2FKt%2FpSkzGBxWRQwnp2CGyLGYDAj1QHCHUKUxvmil3JbOQxXzAcmQ%3D%3D"}]} cf-ray: 9c052b8d5b961ec2-BLR alt-svc: h3=":443"; ma=86400 HTTP/1.1 302 Found Date: Mon, 19 Jan 2026 09:05:24 GMT Content-Type: text/html; charset=iso-8859-1 Transfer-Encoding: chunked Connection: keep-alive server: cloudflare location: https://www.biorxiv.org/lookup/doi/10.1101/084210 cf-cache-status: DYNAMIC Nel: {"report_to":"cf-nel","success_fraction":0.0,"max_age":604800} Report-To: {"group":"cf-nel","max_age":604800,"endpoints":[{"url":"https://a.nel.cloudflare.com/report/v4?s=XF59tiYsbEgAIvDyuS%2F040wSbc5xW447VwjQulX%2F7s8qnVpWuologBPvdVeunQcMO%2FXF%2Bocsx8NvszB1QOKE5yOgcb0xKDWldYVe"}]} CF-RAY: 9c052b8dd94092de-BOM alt-svc: h3=":443"; ma=86400 HTTP/2 301 date: Mon, 19 Jan 2026 09:05:25 GMT content-type: text/html; charset=UTF-8 location: https://www.biorxiv.org/content/10.1101/084210v3 cf-ray: 9c052b912f7cb155-BLR x-content-type-options: nosniff x-content-type-options: nosniff x-drupal-cache: MISS expires: Mon, 19 Jan 2026 09:35:25 GMT cache-control: public, max-age=1800 x-varnish-ttl: pragma: no-cache vary: Accept-Encoding x-highwire-sitecode: biorxiv x-highwire-smart-code: biorxiv_production x-varnish: 1899164143 x-varnish-cache: via: 1.1 varnish cf-cache-status: EXPIRED set-cookie: __cf_bm=8StJIPngLfNqBKOnUJ4FdmKkinKoc8SIagM0J91UTko-1768813525-1.0.1.1-2aEGDrRLmsDWJA.k9hFPTHBkFA4FDuKFF1hlglEOZFiM1ALvh6M3kSDP_x.ucWGboONd5h59WtL_FsDz2iO414.dd_v9cC.dW7iHX8pTwyA; path=/; expires=Mon, 19-Jan-26 09:35:25 GMT; domain=.www.biorxiv.org; HttpOnly; Secure; SameSite=None server: cloudflare HTTP/2 200 date: Mon, 19 Jan 2026 09:05:27 GMT content-type: text/html; charset=utf-8 content-encoding: gzip x-content-type-options: nosniff x-content-type-options: nosniff x-drupal-cache: MISS expires: Sun, 19 Nov 1978 05:00:00 GMT cache-control: no-cache, must-revalidate set-cookie: SSESS1dd6867f1a1b90340f573dcdef3076bc=Jaq-NWMwEkD0BO-marvpxP6pjUNt22NH44tGoPixM80; expires=Wed, 11-Feb-2026 12:38:45 GMT; path=/; domain=.biorxiv.org; secure; HttpOnly content-language: en x-frame-options: SAMEORIGIN x-generator: Drupal 7 (https://drupal.org) link: ; rel="canonical",; rel="shortlink" vary: Accept-Encoding x-highwire-sitecode: biorxiv x-highwire-smart-code: biorxiv_production x-varnish: 701284353 age: 0 via: 1.1 varnish x-varnish-ttl: x-varnish-cache: cf-cache-status: DYNAMIC server: cloudflare cf-ray: 9c052b951f6bb155-BLR Leveraging uncertainty information from deep neural networks for disease detection | bioRxiv

Abstract

Deep learning (DL) has revolutionized the field of computer vision and image processing. In medical imaging, algorithmic solutions based on DL have been shown to achieve high performance on tasks that previously required medical experts. However, DL-based solutions for disease detection have been proposed without methods to quantify and control their uncertainty in a decision. In contrast, a physician knows whether she is uncertain about a case and will consult more experienced colleagues if needed. Here we evaluate drop-out based Bayesian uncertainty measures for DL in diagnosing diabetic retinopathy (DR) from fundus images and show that it captures uncertainty better than straightforward alternatives. Furthermore, we show that uncertainty informed decision referral can improve diagnostic performance. Experiments across different networks, tasks and datasets show robust generalization. Depending on network capacity and task/dataset difficulty, we surpass 85% sensitivity and 80% specificity as recommended by the NHS when referring 0%–20% of the most uncertain decisions for further inspection. We analyse causes of uncertainty by relating intuitions from 2D visualizations to the high-dimensional image space. While uncertainty is sensitive to clinically relevant cases, sensitivity to unfamiliar data samples is task dependent, but can be rendered more robust.

The copyright holder for this preprint is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. It is made available under a CC-BY-NC 4.0 International license.