Résumé

The 2021 ImageCLEF concept detection and caption prediction task follows similar challenges that werealready run from 2017–2020. The objective is to extract UMLS-concept annotations and/or captionsfrom the image data that are then compared against the original text captions of the images. The usedimages are clinically relevant radiology images and the describing captions were created by medicalexperts. In the caption prediction task, lexical similarity with the original image captions is evaluatedwith the BLEU-score. In the concept detection task, UMLS (Unified Medical Language System) termsare extracted from the original text captions and compared against the predicted concepts in a multi-label way. The F1-score was used to assess the performance. The 2021 task has been conducted incollaboration with the Visual Question Answering task and used the same images. The task attracteda strong participation with 25 registered teams. In the end 10 teams submitted 75 runs for the two subtasks. Results show that there is a variety of used techniques that can lead to good prediction resultsfor the two tasks. In comparison to earlier competitions, more modern deep learning architectures likeEfficientNets and Transformer-based architectures for text or images were used.

Détails

Actions

PDF