Katalog Plus
Bibliothek der Frankfurt UAS
Bald neuer Katalog: sichern Sie sich schon vorab Ihre persönlichen Merklisten im Nutzerkonto: Anleitung.
Dieses Ergebnis aus BASE kann Gästen nicht angezeigt werden.  Login für vollen Zugriff.

In-hoc Concept Representations to Regularise Deep Learning in Medical Imaging

Title: In-hoc Concept Representations to Regularise Deep Learning in Medical Imaging
Authors: Corbetta, Valentina; Dijkstra, Floris Six; Beets-Tan, Regina; Kervadec, Hoel; Wickstrøm, Kristoffer; Silva, Wilson; Sub AI Technology for Life; Sub Biology AI Technology For Life
Publication Year: 2025
Subject Terms: SDG 3 - Good Health and Well-being
Description: Deep learning models in medical imaging often achieve strong in-distribution performance but struggle to generalise under distribution shifts, frequently relying on spurious correlations instead of clinically meaningful features. We introduce LCRReg, a novel regularisation approach that leverages Latent Concept Representations (LCRs) (e.g., Concept Activation Vectors (CAVs)) to guide models toward semantically grounded representations. LCRReg requires no concept labels in the main training set and instead uses a small auxiliary dataset to synthesise high-quality, disentangled concept examples. We extract LCRs for predefined relevant features, and incorporate a regularisation term that guides a Convolutional Neural Network (CNN) to activate within latent subspaces associated with those concepts. We evaluate LCRReg across synthetic and real-world medical tasks. On a controlled toy dataset, it significantly improves robustness to injected spurious correlations and remains effective even in multi-concept and multiclass settings. On the diabetic retinopathy binary classification task, LCRReg enhances performance under both synthetic spurious perturbations and out-of-distribution (OOD) generalisation. Compared to baselines, including multitask learning, linear probing, and post-hoc concept-based models, LCRReg offers a lightweight, architecture-agnostic strategy for improving model robustness without requiring dense concept supervision.
Document Type: book part
File Description: application/pdf
Language: English
Relation: https://dspace.library.uu.nl/handle/1874/483443
Availability: https://dspace.library.uu.nl/handle/1874/483443
Rights: info:eu-repo/semantics/OpenAccess
Accession Number: edsbas.E1E0B42F
Database: BASE