The paper introduces AMPLIFAI, the first public dataset of multiphase abdominal CT scans annotated with LI-RADS categories and segmented for three key LI-RADS features: arterial phase hyperenhancement, washout, and enhancing capsule. It outlines the dataset’s composition, curation process, and annotation pipeline following the Datasheets for Datasets format to promote transparency and reproducibility. The dataset aims to support the development of AI models for automated hepatocellular carcinoma diagnosis using the biopsy‑free, imaging‑based LI‑RADs framework.
arXiv:2607. 03253v1 Announce Type: cross Abstract: As hematoxylin & eosin (H&E) staining constitutes the primary entry point in routine diagnostic workflows, computer-aided diagnosis from whole-slide H&E images is of particular clinical relevance.
arXiv:2606. 16991v1 Announce Type: cross Abstract: Multiphasic contrast-enhanced CT (CECT) is widely used for abdominal lesion characterization, yet it carries inherent risks of contrast-induced nephropathy, escalates acquisition burden, and heavily contributes to radiologist workload.
This study investigates deep learning and explainable AI methods to diagnose hepatocellular carcinoma (HCC) and identify diagnostic and prognostic biomarkers across five disease stages using a transcriptomic dataset built via semi‑supervised learning. The best model used 15 genes selected by SelectKBest, achieving 90.74% accuracy, while a 20‑gene model had the lowest loss of 0.3187. SHAP‑based XAI highlighted DNAJB14 as the most influential gene, and functional validation showed that inhibiting DNAJB14 reverses key malignant traits of HCC cells.
The paper presents a systematic evaluation of six unsupervised image‑to‑image generative models for virtual Sirius Red staining of mouse liver tissue from routine H&E slides. It benchmarks these models across 54 scaling configurations on a newly released paired H&E‑to‑SR dataset, assessing perceptual, distributional, and task‑specific performance, and further trains the best models into deep ensembles to quantify epistemic uncertainty. The study finds that GAN‑based and diffusion‑based methods differ markedly across these metrics, indicating that reliable virtual staining requires reporting and selecting on all three axes simultaneously.
Merlin Plus is a new, large-scale CT dataset that provides radiologist‑created tumor masks for nine different organs, adding 1,153 per‑voxel masks and longitudinal metadata to the existing Merlin collection. The dataset was built using a report‑based active‑learning framework, where radiology reports flag tumor cases, a segmentation model generates initial masks, and radiologists review and correct them, thereby reducing annotation effort while preserving high quality. The added longitudinal data enables temporal modeling of cancer progression, supporting scalable multi‑organ cancer detection, segmentation, and longitudinal analysis in CT.
arXiv:2607. 13826v1 Announce Type: cross Abstract: Accurate determination of pancreatic ductal adenocarcinoma (PDAC) resectability relies on evaluating how the tumor interacts with major peripancreatic vessels on CT imaging, yet expert assessment often shows substantial variability.
arXiv:2608. 13939v1 Announce Type: cross Abstract: Ultrasound is the primary imaging modality for assessing thyroid nodules, and the ACR TI-RADS framework standardizes diagnosis through five ultrasound feature categories that are aggregated into five risk levels (TR1-TR5).
The article introduces a new dataset for hepatocellular carcinoma (HCC) prediction, comprising 770 patient samples with 11,150 gene expression levels each, categorized into five classes from normal tissue to various HCC stages. The dataset was constructed using XGBoost and semi‑supervised learning on three existing genomic biomarker datasets, leveraging their labels to generate new annotations. The resulting XGBoost model achieved a 96.5% classification accuracy during the semi‑supervised training process.
arXiv:2505. 07573v2 Announce Type: replace-cross Abstract: Renal mass segmentation has important potential to enhance the clinical workflow, especially in settings requiring quantitative assessments.
DINO-Med introduces a patch‑based framework that adapts natural‑image foundation models, specifically DINOv3, to multi‑modal medical imaging. The method uses training‑free registration, automated localization, and mask‑filtered patch extraction to aggregate patch‑level features into subject‑level diagnostics. In liver fibrosis staging, DINOv3 outperforms handcrafted radiomics, ResNet, and SAM‑Med2D features, achieving 78.4% accuracy for mild fibrosis (S1) and 75.8% for cirrhosis (S4) on the CARE 2025 cohort.
The paper introduces DINO-Med, a patch‑based framework that adapts natural‑image foundation models to multi‑modal medical imaging, specifically for liver fibrosis staging. It processes raw multimodal scans through training‑free registration, automated localization, and mask‑filtered patch extraction, then aggregates patch‑level insights into subject‑level diagnostics. Using the CARE 2025 Liver Track 4 cohort, the DINOv3‑based approach achieved the highest classification accuracy (78.4% for mild fibrosis and 75.8% for cirrhosis) compared to other feature representations.
arXiv:2606. 04365v1 Announce Type: cross Abstract: Radiology reports describe kidney lesions by type, size, enhancement, and attenuation, yet existing 3D methods predict only at the patient or organ level.