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/

Zendy Plus

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

Zendy Tools

Zendy Open

This paper tackles the challenge of forensic medical image matching (FMIM)using deep neural networks (DNNs). FMIM is a particular case of content-basedimage retrieval (CBIR). The main challenge in FMIM compared to the general caseof CBIR, is that the subject to whom a query image belongs may be affected byaging and progressive degenerative disorders, making it difficult to match dataon a subject level. CBIR with DNNs is generally solved by minimizing a rankingloss, such as Triplet loss (TL), computed on image representations extracted bya DNN from the original data. TL, in particular, operates on triplets: anchor,positive (similar to anchor) and negative (dissimilar to anchor). Although TLhas been shown to perform well in many CBIR tasks, it still has limitations,which we identify and analyze in this work. In this paper, we introduce (i) theAdaTriplet loss -- an extension of TL whose gradients adapt to differentdifficulty levels of negative samples, and (ii) the AutoMargin method -- atechnique to adjust hyperparameters of margin-based losses such as TL and ourproposed loss dynamically. Our results are evaluated on two large-scalebenchmarks for FMIM based on the Osteoarthritis Initiative and Chest X-ray-14datasets. The codes allowing replication of this study have been made publiclyavailable at \url{https://github.com/Oulu-IMEDS/AdaTriplet}.

AdaTriplet: Adaptive Gradient Triplet Loss with Automatic Margin Learning for Forensic Medical Image Matching