A Simple Improvement to PIP-Net for Medical Image Anomaly Detection

Simple item page
dc.contributor.authorKobayashi, Yukien_US
dc.contributor.authorYamaguchi, Yasushien_US
dc.contributor.editorCaputo, Arielen_US
dc.contributor.editorGarro, Valeriaen_US
dc.contributor.editorGiachetti, Andreaen_US
dc.contributor.editorCastellani, Umbertoen_US
dc.contributor.editorDulecha, Tinsae Gebrechristosen_US
dc.date.accessioned2024-11-11T12:48:08Z
dc.date.available2024-11-11T12:48:08Z
dc.date.issued2024
dc.description.abstractThe application of AI technology in domains requiring decision accountability, such as healthcare, has increased the demand for model interpretability. The part-prototype model is a well-established interpretable approach for image recognition, with PIP-Net demonstrating strong classification performance and high interpretability in multiclass classification tasks. However, PIP-Net assumes the presence of class-specific prototypes. This assumption does not hold for tasks like anomaly detection, where no local features are exclusive to the normal class. To address this, we propose an architecture that learns only the scores corresponding to the anomaly class for each prototype. This approach is based on more reasonable assumptions for anomaly detection than PIP-Net and enables concise inference using fewer prototypes. Evaluation of this approach using the MURA dataset, a large dataset of bone X-rays, revealed that the proposed architecture achieved better anomaly detection performance than the original PIP-Net with fewer prototypes.en_US
dc.description.sectionheadersAI and Image Processing
dc.description.seriesinformationSmart Tools and Applications in Graphics - Eurographics Italian Chapter Conference
dc.identifier.doi10.2312/stag.20241337
dc.identifier.isbn978-3-03868-265-3
dc.identifier.issn2617-4855
dc.identifier.pages7 pages
dc.identifier.urihttps://doi.org/10.2312/stag.20241337
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/stag20241337
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titleA Simple Improvement to PIP-Net for Medical Image Anomaly Detectionen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
stag20241337.pdf
Size:
474.87 KB
Format:
Adobe Portable Document Format
Download
Collections
Italian Chapter Conference 2024 - Smart Tools and Apps in Graphics