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

Deep neural networks (DNNs) have promoted the development of computer aideddiagnosis (CAD) systems for fundus diseases, helping ophthalmologists reducemissed diagnosis and misdiagnosis rate. However, the majority of CAD systemsare data-driven but lack of medical prior knowledge which can beperformance-friendly. In this regard, we innovatively proposed ahuman-in-the-loop (HITL) CAD system by leveraging ophthalmologists'eye-tracking information, which is more efficient and accurate. Concretely, theHITL CAD system was implemented on the multiple instance learning (MIL), whereeye-tracking gaze maps were beneficial to cherry-pick diagnosis-relatedinstances. Furthermore, the dual-cross-attention MIL (DCAMIL) network wasutilized to curb the adverse effects of noisy instances. Meanwhile, bothsequence augmentation module and domain adversarial module were introduced toenrich and standardize instances in the training bag, respectively, therebyenhancing the robustness of our method. We conduct comparative experiments onour newly constructed datasets (namely, AMD-Gaze and DR-Gaze), respectively forthe AMD and early DR detection. Rigorous experiments demonstrate thefeasibility of our HITL CAD system and the superiority of the proposed DCAMIL,fully exploring the ophthalmologists' eye-tracking information. Theseinvestigations indicate that physicians' gaze maps, as medical prior knowledge,is potential to contribute to the CAD systems of clinical diseases.

Eye tracking guided deep multiple instance learning with dual cross-attention for fundus disease detection