arXiv:2511.14918v1 Announce Type: new 
Abstract: Chest X-ray radiography (CXR) is an essential medical imaging technique for disease diagnosis. However, as 2D projectional images, CXRs are limited by structural superposition and hence fail to capture 3D anatomies. This limitation makes representation learning and disease diagnosis challenging. To address this challenge, we propose a novel CXR world model named X-WIN, which distills volumetric knowledge from chest computed tomography (CT) by learning to predict its 2D projections in latent space. The core idea is that a world model with internalized knowledge of 3D anatomical structure can predict CXRs under various transformations in 3D space. During projection prediction, we introduce an affinity-guided contrastive alignment loss that leverages mutual similarities to capture rich, correlated information across projections from the same volume. To improve model adaptability, we incorporate real CXRs into training through masked image modeling and employ a domain classifier to encourage statistically similar representations for real and simulated CXRs. Comprehensive experiments show that X-WIN outperforms existing foundation models on diverse downstream tasks using linear probing and few-shot fine-tuning. X-WIN also demonstrates the ability to render 2D projections for reconstructing a 3D CT volume.

تعتبر الأشعة السينية للصدر (CXR) تقنية تصوير طبية أساسية لتشخيص الأمراض، ولكن طبيعتها ثنائية الأبعاد تحد من التقاط الهياكل التشريحية ثلاثية الأبعاد. للتغلب على هذه القيود، تم تطوير نموذج جديد يسمى X-WIN، الذي يتنبأ بالإسقاطات ثنائية الأبعاد من بيانات التصوير المقطعي المحوسب (CT) ثلاثي الأبعاد. يستخدم هذا النموذج خسارة محاذاة تباينية موجهة بالقرابة لتحسين تعلم المعلومات المرتبطة عبر الإسقاطات، بهدف تحسين تشخيص الأمراض وتعلم التمثيلات.

La radiografía de tórax (CXR) es una técnica de imagen esencial para el diagnóstico de enfermedades, pero su naturaleza 2D limita la captura de estructuras anatómicas en 3D. Para abordar esta limitación, se ha desarrollado un nuevo modelo llamado X-WIN, que predice proyecciones 2D a partir de datos de tomografía computarizada (CT) en 3D. Este modelo utiliza una pérdida de alineación contrastiva guiada por afinidad para mejorar el aprendizaje de información correlacionada entre las proyecciones, con el objetivo de mejorar el diagnóstico de enfermedades y el aprendizaje de representaciones.

La radiographie thoracique (CXR) est une technique d'imagerie essentielle pour le diagnostic des maladies, mais sa nature 2D limite la capture des structures anatomiques en 3D. Pour surmonter cette limitation, un nouveau modèle nommé X-WIN a été développé, qui prédit les projections 2D à partir des données de tomographie par ordinateur (CT) en 3D. Ce modèle utilise une perte d'alignement contrastif guidée par affinité pour améliorer l'apprentissage des informations corrélées entre les projections, visant à améliorer le diagnostic des maladies et l'apprentissage de la représentation.

Chest X-ray radiography (CXR) is a vital imaging technique for diagnosing diseases, but its 2D nature limits the capture of 3D anatomical structures. To overcome this, a new model named X-WIN has been developed, which predicts 2D projections from 3D chest computed tomography (CT) data. This model utilizes an affinity-guided contrastive alignment loss to enhance the learning of correlated information across projections, aiming to improve disease diagnosis and representation learning.

X-WIN: Building Chest Radiograph World Model via Predictive Sensing

arXiv:2601.08078v1 Announce Type: new 
Abstract: Deep learning-based automatic medical image segmentation plays a critical role in clinical diagnosis and treatment planning but remains challenging in few-shot scenarios due to the scarcity of annotated training data. Recently, self-supervised foundation models such as DINOv3, which were trained on large natural image datasets, have shown strong potential for dense feature extraction that can help with the few-shot learning challenge. Yet, their direct application to medical images is hindered by domain differences. In this work, we propose DINO-AugSeg, a novel framework that leverages DINOv3 features to address the few-shot medical image segmentation challenge. Specifically, we introduce WT-Aug, a wavelet-based feature-level augmentation module that enriches the diversity of DINOv3-extracted features by perturbing frequency components, and CG-Fuse, a contextual information-guided fusion module that exploits cross-attention to integrate semantic-rich low-resolution features with spatially detailed high-resolution features. Extensive experiments on six public benchmarks spanning five imaging modalities, including MRI, CT, ultrasound, endoscopy, and dermoscopy, demonstrate that DINO-AugSeg consistently outperforms existing methods under limited-sample conditions. The results highlight the effectiveness of incorporating wavelet-domain augmentation and contextual fusion for robust feature representation, suggesting DINO-AugSeg as a promising direction for advancing few-shot medical image segmentation. Code and data will be made available on https://github.com/apple1986/DINO-AugSeg.

تم اقتراح إطار عمل جديد يسمى DINO-AugSeg لتحسين تقسيم الصور الطبية في سيناريوهات قليلة الأمثلة من خلال الاستفادة من ميزات ذاتية الإشراف تعتمد على DINOv3. يتناول هذا النهج تحدي ندرة بيانات التدريب المعلّمة في البيئات السريرية، باستخدام تعزيز الميزات على مستوى الموجات ودمج المعلومات السياقية لتحسين دقة التقسيم عبر مختلف طرق التصوير مثل التصوير بالرنين المغناطيسي والأشعة المقطعية.

Se ha propuesto un nuevo marco llamado DINO-AugSeg para mejorar la segmentación de imágenes médicas en escenarios de pocos ejemplos, aprovechando características auto-supervisadas basadas en DINOv3. Este enfoque aborda el desafío de la escasez de datos de entrenamiento anotados en entornos clínicos, utilizando una augmentación de características a nivel de wavelet y una fusión guiada por información contextual para mejorar la precisión de la segmentación en diversas modalidades de imagen como MRI y CT.

Un nouveau cadre nommé DINO-AugSeg a été proposé pour améliorer la segmentation d'images médicales en quelques exemples en s'appuyant sur des caractéristiques auto-supervisées basées sur DINOv3. Cette approche répond au défi du manque de données d'entraînement annotées dans les milieux cliniques, en utilisant une augmentation des caractéristiques au niveau des ondelettes et une fusion guidée par des informations contextuelles pour améliorer la précision de la segmentation à travers diverses modalités d'imagerie telles que l'IRM et le CT.

A novel framework named DINO-AugSeg has been proposed to enhance few-shot medical image segmentation by leveraging DINOv3-based self-supervised features. This approach addresses the challenge of limited annotated training data in clinical settings, utilizing wavelet-based feature-level augmentation and contextual information-guided fusion to improve segmentation accuracy across various imaging modalities such as MRI and CT.

Exploiting DINOv3-Based Self-Supervised Features for Robust Few-Shot Medical Image Segmentation

arXiv:2601.08334v1 Announce Type: new 
Abstract: Automated machine learning (AutoML) frameworks can lower technical barriers for predictive and prognostic model development in radiomics by enabling researchers without programming expertise to build models. However, their effectiveness in addressing radiomics-specific challenges remains unclear. This study evaluates the performance, efficiency, and accessibility of general-purpose and radiomics-specific AutoML frameworks on diverse radiomics classification tasks, thereby highlighting development needs for radiomics. Ten public/private radiomics datasets with varied imaging modalities (CT/MRI), sizes, anatomies and endpoints were used. Six general-purpose and five radiomics-specific frameworks were tested with predefined parameters using standardized cross-validation. Evaluation metrics included AUC, runtime, together with qualitative aspects related to software status, accessibility, and interpretability. Simplatab, a radiomics-specific tool with a no-code interface, achieved the highest average test AUC (81.81%) with a moderate runtime (~1 hour). LightAutoML, a general-purpose framework, showed the fastest execution with competitive performance (78.74% mean AUC in six minutes). Most radiomics-specific frameworks were excluded from the performance analysis due to obsolescence, extensive programming requirements, or computational inefficiency. Conversely, general-purpose frameworks demonstrated higher accessibility and ease of implementation. Simplatab provides an effective balance of performance, efficiency, and accessibility for radiomics classification problems. However, significant gaps remain, including the lack of accessible survival analysis support and the limited integration of feature reproducibility and harmonization within current AutoML frameworks. Future research should focus on adapting AutoML solutions to better address these radiomics-specific challenges.

أظهرت دراسة حديثة تقييمًا لأداء وكفاءة وإمكانية الوصول إلى أطر التعلم الآلي الآلي (AutoML) في مجال الراديوميات، مع التركيز على قدرتها على مساعدة الباحثين الذين لا يمتلكون مهارات برمجية في تطوير نماذج تنبؤية. اختبرت الدراسة ستة أطر عامة وخمسة أطر محددة للراديوميات عبر عشرة مجموعات بيانات متنوعة، مما يكشف عن الحاجة إلى مزيد من التطوير المخصص لتحديات الراديوميات.

Un estudio reciente evaluó el rendimiento, la eficiencia y la accesibilidad de los marcos de aprendizaje automático automatizado (AutoML) en el campo de la radiómica, centrándose en su capacidad para ayudar a investigadores sin habilidades de programación a desarrollar modelos predictivos. El estudio probó seis marcos de propósito general y cinco marcos específicos de radiómica en diez conjuntos de datos diversos, revelando la necesidad de un mayor desarrollo adaptado a los desafíos de la radiómica.

Une étude récente a évalué la performance, l'efficacité et l'accessibilité des cadres d'apprentissage automatique automatisé (AutoML) dans le domaine de la radiomique, en se concentrant sur leur capacité à aider les chercheurs sans compétences en programmation à développer des modèles prédictifs. L'étude a testé six cadres à usage général et cinq cadres spécifiques à la radiomique sur dix ensembles de données divers, révélant le besoin de développements supplémentaires adaptés aux défis de la radiomique.

A recent study evaluated the performance, efficiency, and accessibility of automated machine learning (AutoML) frameworks in the field of radiomics, focusing on their ability to assist researchers without programming skills in developing predictive models. The study tested six general-purpose and five radiomics-specific frameworks across ten diverse datasets, revealing the need for further development tailored to radiomics challenges.

X-WIN: Building Chest Radiograph World Model via Predictive Sensing

Was this article worth reading? Share it

LucidQuery AI

ClassX

AIPortalX

Artefacts.ai

VECTARY

Deptho.ai

Ready to build your own newsroom?