arXiv:2511.17828v1 Announce Type: new 
Abstract: Foundation models hold promise for specialized medical imaging tasks, though their effectiveness in breast imaging remains underexplored. This study leverages BiomedCLIP as a foundation model to address challenges in model generalization. BiomedCLIP was adapted for automated BI-RADS breast density classification using multi-modality mammographic data (synthesized 2D images, digital mammography, and digital breast tomosynthesis). Using 96,995 images, we compared single-modality (s2D only) and multi-modality training approaches, addressing class imbalance through weighted contrastive learning. Both approaches achieved similar accuracy (multi-modality: 0.74, single-modality: 0.73), with the multi-modality model offering broader applicability across different imaging modalities and higher AUC values consistently above 0.84 across BI-RADS categories. External validation on the RSNA and EMBED datasets showed strong generalization capabilities (AUC range: 0.80-0.93). GradCAM visualizations confirmed consistent and clinically relevant attention patterns, highlighting the models interpretability and robustness. This research underscores the potential of foundation models for breast imaging applications, paving the way for future extensions for diagnostic tasks.

أظهرت دراسة حديثة تكيف نموذج BiomedCLIP الأساسي لتصوير الثدي، مع التركيز على التصنيف الآلي لكثافة الثدي BI-RADS باستخدام مجموعة بيانات متنوعة تضم 96,995 صورة. قارن البحث بين أساليب التدريب ذات النمط الواحد والمتعدد، محققًا مستويات دقة مشابهة مع تسليط الضوء على قابلية تطبيق النموذج متعدد الأنماط وقدرته القوية على التعميم عبر أنماط التصوير المختلفة.

Un estudio reciente ha adaptado el modelo de fundación BiomedCLIP para la imagenología mamaria, centrándose en la clasificación automatizada de la densidad mamaria BI-RADS utilizando un conjunto de datos diverso de 96,995 imágenes. La investigación comparó enfoques de entrenamiento de modalidad única y multimodal, logrando niveles de precisión similares mientras destacaba la mayor aplicabilidad del modelo multimodal y sus fuertes capacidades de generalización a través de diferentes modalidades de imagenología.

Une étude récente a adapté le modèle de fondation BiomedCLIP pour l'imagerie mammaire, en se concentrant sur la classification automatisée de la densité mammaire BI-RADS à l'aide d'un ensemble de données diversifié de 96 995 images. La recherche a comparé les approches d'entraînement à modalité unique et multimodale, atteignant des niveaux de précision similaires tout en soulignant l'applicabilité plus large du modèle multimodal et ses fortes capacités de généralisation à travers différentes modalités d'imagerie.

A recent study has adapted the BiomedCLIP foundation model for breast imaging, focusing on automated BI-RADS breast density classification using a diverse dataset of 96,995 images. The research compared single-modality and multi-modality training approaches, achieving similar accuracy levels while highlighting the multi-modality model's broader applicability and strong generalization capabilities across different imaging modalities.

Toward explainable AI approaches for breast imaging: adapting foundation models to diverse populations

arXiv:2511.18425v1 Announce Type: new 
Abstract: Pneumonia remains a leading global cause of mortality where timely diagnosis is critical. We introduce LungX, a novel hybrid architecture combining EfficientNet's multi-scale features, CBAM attention mechanisms, and Vision Transformer's global context modeling for enhanced pneumonia detection. Evaluated on 20,000 curated chest X-rays from RSNA and CheXpert, LungX achieves state-of-the-art performance (86.5 percent accuracy, 0.943 AUC), representing a 6.7 percent AUC improvement over EfficientNet-B0 baselines. Visual analysis demonstrates superior lesion localization through interpretable attention maps. Future directions include multi-center validation and architectural optimizations targeting 88 percent accuracy for clinical deployment as an AI diagnostic aid.

تم تقديم LungX، وهي بنية هجينة جديدة تجمع بين EfficientNet وVision Transformer، لتحسين دقة الكشف عن الالتهاب الرئوي، حيث حققت دقة 86.5% وAUC قدره 0.943 على مجموعة بيانات تضم 20,000 صورة أشعة سينية للصدر. هذا التطور مهم، حيث أن التشخيص في الوقت المناسب للالتهاب الرئوي أمر حيوي لتقليل معدلات الوفيات المرتبطة بالمرض.

LungX, una nueva arquitectura híbrida que combina EfficientNet y Vision Transformer, ha sido presentada para mejorar la precisión en la detección de neumonía, logrando un 86.5% de precisión y un AUC de 0.943 en un conjunto de datos de 20,000 radiografías de tórax. Este desarrollo es crucial, ya que un diagnóstico oportuno de la neumonía es vital para reducir las tasas de mortalidad asociadas a la enfermedad.

LungX, une nouvelle architecture hybride combinant EfficientNet et Vision Transformer, a été introduite pour améliorer la précision du diagnostic de la pneumonie, atteignant 86,5 % de précision et un AUC de 0,943 sur un ensemble de données de 20 000 radiographies thoraciques. Ce développement est crucial car un diagnostic rapide de la pneumonie est vital pour réduire les taux de mortalité associés à cette maladie.

LungX, a new hybrid architecture combining EfficientNet and Vision Transformer, has been introduced to enhance pneumonia detection accuracy, achieving 86.5% accuracy and a 0.943 AUC on a dataset of 20,000 chest X-rays. This development is crucial as timely diagnosis of pneumonia is vital for reducing mortality rates associated with the disease.

LungX: A Hybrid EfficientNet-Vision Transformer Architecture with Multi-Scale Attention for Accurate Pneumonia Detection

arXiv:2511.17158v1 Announce Type: cross 
Abstract: Objectives: To evaluate the association between pretreatment MRI descriptors and breast cancer (BC) pathological complete response (pCR) to neoadjuvant chemotherapy (NAC). Materials \& Methods: Patients with BC treated by NAC with a breast MRI between 2016 and 2020 were included in this retrospective observational single-center study. MR studies were described using the standardized BI-RADS and breast edema score on T2-weighted MRI. Univariable and multivariable logistic regression analyses were performed to assess variables association with pCR according to residual cancer burden. Random forest classifiers were trained to predict pCR on a random split including 70% of the database and were validated on the remaining cases. Results: Among 129 BC, 59 (46%) achieved pCR after NAC (luminal (n=7/37, 19%), triple negative (TN) (n=30/55, 55%), HER2+ (n=22/37, 59%). Clinical and biological items associated with pCR were BC subtype (p<0.001), T stage 0/I/II (p=0.008), higher Ki67 (p=0.005) and higher tumor-infiltrating lymphocytes levels (p=0.016). Univariate analysis showed that the following MRI features, oval or round shape (p=0.047), unifocality (p=0.026), non-spiculated margins (p=0.018), no associated non-mass enhancement (NME) (p = 0.024) and a lower MRI size (p = 0.031) were significantly associated with pCR. Unifocality and non-spiculated margins remained independently associated with pCR at multivariable analysis. Adding significant MRI features to clinicobiological variables in random forest classifiers significantly increased sensitivity (0.67 versus 0.62), specificity (0.69 versus 0.67) and precision (0.71 versus 0.67) for pCR prediction. Conclusion: Non-spiculated margins and unifocality are independently associated with pCR and can increase models performance to predict BC response to NAC. Clinical Relevance Statement: A multimodal approach integrating pretreatment MRI features with clinicobiological predictors, including TILs, could be employed to develop machine learning models for identifying patients at risk of non-response. This may enable consideration of alternative therapeutic strategies to optimize treatment outcomes

أجرت دراسة حديثة تقييمًا للعلاقة بين أوصاف التصوير بالرنين المغناطيسي قبل العلاج والاستجابة المرضية الكاملة (pCR) لدى مرضى سرطان الثدي الذين يخضعون للعلاج الكيميائي المساعد. شملت التحليل الرجعي 129 مريضًا تم علاجهم بين عامي 2016 و2020، وكشفت أن 46% منهم حققوا pCR، مع ملاحظات لوجود اختلافات ملحوظة بين أنواع سرطان الثدي.

Un estudio reciente evaluó la asociación entre los descriptores de resonancia magnética (RM) previos al tratamiento y la respuesta patológica completa (pCR) en pacientes con cáncer de mama que recibieron quimioterapia neoadyuvante. El análisis retrospectivo incluyó a 129 pacientes tratados entre 2016 y 2020, revelando que el 46% alcanzó pCR, con diferencias significativas observadas entre los subtipos de cáncer de mama.

Une étude récente a évalué l'association entre les descripteurs IRM prétraitement et la réponse pathologique complète (pCR) des patientes atteintes de cancer du sein subissant une chimiothérapie néoadjuvante. L'analyse rétrospective a inclus 129 patientes traitées entre 2016 et 2020, révélant que 46 % avaient atteint la pCR, avec des différences significatives notées selon les sous-types de cancer du sein.

A recent study evaluated the association between pretreatment MRI descriptors and the pathologic complete response (pCR) of breast cancer patients undergoing neoadjuvant chemotherapy. The retrospective analysis included 129 patients treated between 2016 and 2020, revealing that 46% achieved pCR, with significant differences noted across breast cancer subtypes.

Toward explainable AI approaches for breast imaging: adapting foundation models to diverse populations

Was this article worth reading? Share it

Attentive AI

Portfolio Backtest

Republiclabs.ai