arXiv:2511.20732v1 Announce Type: cross 
Abstract: Medical AI systems face catastrophic forgetting when deployed in clinical settings, where models must learn new imaging protocols while retaining prior diagnostic capabilities. This challenge is particularly acute for medical vision-language models that must preserve complex cross-modal alignments between medical images and clinical terminology across diverse imaging modalities. We introduce Prompt- Aware Adaptive Elastic Weight Consolidation (PA-EWC), a novel continual learning approach that addresses catastrophic forgetting through prompt-guided parameter specialization. Our method systematically categorizes model parameters based on their functional roles in processing visual-descriptive, spatial-guided, and medical-semantic information, enabling targeted protection of critical knowledge while allowing adaptation to new clinical requirements. PA-EWC incorporates adaptive Fisher Information computation with gradient stability analysis and develops weighted complexity metrics based on medical terminology density. We evaluate our approach across five medical imaging datasets (Kvasir-SEG, ISIC 2018, CheXlocalize, BUSI, CAMUS) representing diverse modalities including endoscopy, dermoscopy, radiography, and ultrasound. Experimental results demonstrate that PA-EWC reduces catastrophic forgetting by up to 17.58% compared to baseline methods, with performance improvements of 4.30% on chest X-ray pathology localization and 6.06% on polyp segmentation.

تم تقديم نهج جديد يسمى التوحيد المرن التكيفي المستند إلى الموجهات (PA-EWC) لمواجهة النسيان الكارثي في نماذج الرؤية-اللغة الطبية. تتيح هذه الطريقة للنماذج التكيف مع بروتوكولات التصوير الجديدة مع الاحتفاظ بالقدرات التشخيصية الأساسية من خلال تصنيف معلمات النموذج بناءً على أدوارها الوظيفية.

Se ha introducido un nuevo enfoque llamado Consolidación Elástica Adaptativa Sensible a Prompts (PA-EWC) para abordar el olvido catastrófico en modelos de visión-lenguaje médico. Este método permite que los modelos se adapten a nuevos protocolos de imagen mientras retienen capacidades diagnósticas esenciales al categorizar los parámetros del modelo según sus roles funcionales.

Une nouvelle approche appelée Consolidation Élastique Adaptative Sensible aux Prompts (PA-EWC) a été introduite pour lutter contre l'oubli catastrophique dans les modèles de vision-langage médical. Cette méthode permet aux modèles de s'adapter à de nouveaux protocoles d'imagerie tout en conservant des capacités de diagnostic essentielles en catégorisant les paramètres du modèle en fonction de leurs rôles fonctionnels.

A novel approach called Prompt-Aware Adaptive Elastic Weight Consolidation (PA-EWC) has been introduced to tackle catastrophic forgetting in medical vision-language models. This method allows models to adapt to new imaging protocols while retaining essential diagnostic capabilities by categorizing model parameters based on their functional roles.

Prompt-Aware Adaptive Elastic Weight Consolidation for Continual Learning in Medical Vision-Language Models

arXiv:2512.02198v1 Announce Type: new 
Abstract: Multifractal analysis has revealed regularities in many self-seeding phenomena, yet its use in modern deep learning remains limited. Existing end-to-end multifractal methods rely on heavy pooling or strong feature-space decimation, which constrain tasks such as semantic segmentation. Motivated by these limitations, we introduce two inductive priors: Monofractal and Multifractal Recalibration. These methods leverage relationships between the probability mass of the exponents and the multifractal spectrum to form statistical descriptions of encoder embeddings, implemented as channel-attention functions in convolutional networks.
  Using a U-Net-based framework, we show that multifractal recalibration yields substantial gains over a baseline equipped with other channel-attention mechanisms that also use higher-order statistics. Given the proven ability of multifractal analysis to capture pathological regularities, we validate our approach on three public medical-imaging datasets: ISIC18 (dermoscopy), Kvasir-SEG (endoscopy), and BUSI (ultrasound).
  Our empirical analysis also provides insights into the behavior of these attention layers. We find that excitation responses do not become increasingly specialized with encoder depth in U-Net architectures due to skip connections, and that their effectiveness may relate to global statistics of instance variability.

تقدم دراسة جديدة طرق إعادة ضبط متعددة الكسريات لتحسين الشبكات العصبية المستخدمة في تقسيم الصور الطبية، وخاصة ضمن إطار U-Net. تتناول هذه الطريقة القيود المفروضة على التقنيات متعددة الكسريات الموجودة التي تعتمد غالبًا على التجميع الثقيل، مما يحسن التمثيل الإحصائي لتضمينات المشفر من خلال وظائف الانتباه القنوي.

Un nuevo estudio presenta métodos de recalibración multifractal para mejorar las redes neuronales utilizadas en la segmentación de imágenes médicas, específicamente dentro de un marco U-Net. Este enfoque aborda las limitaciones de las técnicas multifractales existentes que a menudo dependen de un fuerte pooling, mejorando así la representación estadística de las incrustaciones del codificador a través de funciones de atención por canal.

Une nouvelle étude présente des méthodes de recalibrage multifractal pour améliorer les réseaux neuronaux utilisés dans la segmentation d'images médicales, spécifiquement au sein d'un cadre U-Net. Cette approche répond aux limitations des techniques multifractales existantes qui reposent souvent sur un fort pooling, améliorant ainsi la représentation statistique des embeddings d'encodeur grâce à des fonctions d'attention par canal.

A new study introduces Multifractal Recalibration methods for enhancing neural networks used in medical imaging segmentation, specifically within a U-Net framework. This approach addresses limitations in existing multifractal techniques that often rely on heavy pooling, thereby improving the statistical representation of encoder embeddings through channel-attention functions.

Prompt-Aware Adaptive Elastic Weight Consolidation for Continual Learning in Medical Vision-Language Models

Was this article worth reading? Share it

Twofold Health

Nudge AI

Https