Find the papers that actually matter

Postoperative liver cancer relapse remains a formidable clinical challenge. Photothermal therapy (PTT) holds promise by eliminating residual malignancies and activating antitumor immunity; notably, tumor cells persistently reconstitute proteostasis and survive by integrated stress response (ISR)-mediated heat shock protein 90 (HSP90) activation to constrain PTT efficacy. To address this limitation, we engineered a self-reinforced photothermal-immunomodulation strategy based on electrospun nanofiber scaffolds co-loaded with black phosphorus nanosheets (BPNSs) and the HSP90 inhibitor 17-DMAG. These nanofiber scaffolds exhibited robust hydrophobicity, efficient photothermal conversion, and near-infrared (NIR) responsive controlled drug release. Under NIR irradiation, the nanofiber scaffolds leveraged BPNSs to generate stable PTT while liberating 17-DMAG to amplify proteotoxicity, forcibly redirecting the ISR from pro-survival adaptation toward robust apoptosis and immunogenic cell death (ICD). Consequently, prominently exposed damage-associated molecular patterns potentiated tumor immunogenicity and remodeled immune microenvironment by dendritic cells maturation, cytotoxic T lymphocytes (CTLs) priming, and immunosuppressive populations reprogramming. Crucially, subsequent synergy with anti-PD-L1 reinvigorated CTLs and established durable immune memory. Systematic validation confirmed this localized strategy uniquely integrates precision photothermal energy conversion with potent ISR-ICD cascade, effectively synergizing with anti-PD-L1 to suppress postoperative liver cancer relapse and metastasis, thereby holding substantial translational potential for clinical oncology.

Intrahepatic cholangiocarcinoma (iCCA), a highly lethal subtype of liver cancer with increasing incidence and poor prognosis, displays profound molecular heterogeneity that limits therapeutic efficacy. Combining multi-omics with pathological subtyping in iCCA, we identified a strong association between the most aggressive molecular subtype and the large-duct pathological type, characterized by aberrant mucin overexpression and prominent myeloid cell infiltration. Through integrative analysis, MUC16 was identified as a key molecular marker specifically enriched in large-duct type intrahepatic cholangiocarcinoma (L-iCCA). Functional modulation of MUC16 markedly inhibited L-iCCA cell proliferation and migration. Furthermore, high-throughput drug screening identified the small-molecule compound OSMI-1 as a potent suppressor of MUC16 expression. Using primary iCCA cell lines and patient-derived organoids (PDOs), we confirmed that OSMI-1 inhibits L-iCCA cell proliferation and migration by downregulating MUC16. Mechanistically, OSMI-1 suppresses MUC16 expression by disrupting the transcriptional complex formed between OGT and IRF1. Employing a genetically engineered L-iCCA mouse model, we further validated the crucial role of MUC16 in tumor progression and neutrophil infiltration, demonstrated that OSMI-1 synergized with gemcitabine, effectively inhibiting L-iCCA growth. This study presents a pathological subtype-based precision therapeutic strategy for L-iCCA, thereby providing a foundation for novel translational approaches to the personalized management of this disease.

The evaluation of therapeutic response to cyclin-dependent kinase 4/6 (CDK4/6) inhibitors in hormone receptor-positive (HR+), HER2-negative (HER2-) breast cancer currently relies on anatomical imaging, which suffers from significant delays. To enable early and direct visualization of drug activity, we developed a near-infrared-II (NIR-II) fluorescent molecular probe, HSA-ICi, by conjugating a CDK4/6 inhibitor (Palbociclib or Ribociclib) with ICG and facilitating its self-assembly with human serum albumin. This probe demonstrated specific targeting to the CDK4/6-cyclin D complex, excellent biocompatibility, and high tumor accumulation in preclinical models. Crucially, HSA-ICi allowed non-invasive monitoring of pharmacodynamic response: a significant decrease in tumor fluorescence signal was detected via NIR-II imaging as early as one week after treatment initiation, preceding any measurable change in tumor volume by caliper or magnetic resonance imaging (MRI). This early signal reduction correlated with decreased pRB and Ki-67 expression in tumor tissues. Furthermore, the probe could distinguish between CDK4/6 inhibitor-sensitive and -resistant tumors, with resistant models showing a consistently low signal. Our findings establish HSA-ICi as a promising tool for the early assessment of therapeutic efficacy and the identification of resistance, potentially facilitating timely treatment adaptation for patients with HR+/HER2-breast cancer.

Clinical pathways are disseminated as visual flowcharts where spatial topology, arrow direction, colour coding, and font weight encode critical triage logic that remains inaccessible to computational systems. We present PathWISE, a five-phase pipeline combining four LLM-based agents with a deterministic depth-first search auditor and a Java compiler critic, transforming these non-computable artefacts into validated, executable HL7 Clinical Quality Language (CQL) libraries deployable as FHIR CDS Hooks services. Purpose-built agents extract flowchart structure into a typed directed graph, perform deterministic path enumeration, conduct a structured semantic audit of every node's computability, generate terminology-constrained CQL definitions verified by the official Java CQL-to-ELM compiler, and produce routing logic covering 100% of enumerated patient journeys. Demonstrated across five UK NHS cancer pathways (colorectal, lung, skin, upper GI, and breast), PathWISE audits up to 183 nodes (182 under the Hybrid configuration), identifies 544 structured governance findings across four issue categories, achieves 100% syntactic compilation success, with UNCOMPUTABLE nodes receiving false placeholders that preserve compilability while surfacing governance gaps for clinical review, and produces zero hallucinated terminology codes for dictionary-covered concepts. Critically, PathWISE confines non-deterministic LLM inference to knowledge extraction while deterministic graph mathematics and a standard compiler underpin every verification step.

Urgent suspected colorectal cancer (CRC) referrals create operational bottlenecks because semi-structured clinical documents often require manual review and transcription. The original RAPTOR system used Large Language Models for structured extraction but relied on a separate OCR stage, making it vulnerable to handwriting, layout variation, and loss of visual evidence linkage. We present RAPTOR+, a multimodal extension that uses Vision-Language Models (VLMs) for end-to-end referral understanding. We evaluate fine-tuned VLMs, commercial and open-source zero-shot VLMs, and the original OCR-based pipeline on 223 clinically curated CRC urgent referral forms. We also introduce a grounding-aware evaluation framework that measures both extraction accuracy and evidence localisation. Results show a clear grounding gap in zero-shot models. Gemini 2.5 Flash achieved 92.6% Reading Accuracy but only 1.2% Strict Safety. In contrast, fine-tuned Qwen3-VL-8B achieved 96.1% Reading Accuracy and 60.6% Strict Safety, substantially improving verifiable evidence grounding. These findings show that task-specific fine-tuning is essential for reliable, auditable clinical document understanding. RAPTOR+ enables extracted referral decisions to be linked to visual evidence, supporting safer and more efficient cancer referral triage.

Pathological assessment guides lung cancer diagnosis, treatment selection, and prognostic evaluation, yet current CPath approaches rely on task-specific models for isolated objectives. Although pan-cancer foundation models offer versatility, they lack subspecialty-level depth and have not been evaluated across clinical workflows or prospectively validated in real-world settings. We introduce PulmoFoundation, a multi-center, prospectively validated, randomized controlled trial (RCT)-evaluated foundation model for comprehensive lung pathology assessment across pre-operative, intra-operative, and post-operative care. Built upon Virchow2 via subspecialty-specific pretraining using ~40,000 diagnostic H&E-stained whole-slide images (WSIs), PulmoFoundation was systematically evaluated on ~26,000 WSIs across 32 clinically relevant tasks. In addition to accurately predicting molecular markers and patient survival, our model achieves clinical-grade performance in core diagnostic tasks across biopsy, frozen section, and surgical resection slides. In a registered prospective study of 1,357 patients across 11 diagnostic tasks, our model achieved an average AUC of 92.3%. Using pre-specified triage thresholds, PulmoFoundation could reduce additional second-review burden for 68.8% of biopsies and 83.0% of frozen sections, and defer 44.5% of IHC stain orders, with PPVs of 1.0, 0.991, and 0.966. Beyond prospective validation, we conducted a crossover RCT with eight pathologists, in which AI assistance improved diagnostic accuracy across 4,928 case-reader pairs (91.7% w/ AI vs. 83.8% w/o AI). AI assistance also reduced median diagnostic time by 19.6%, increased diagnostic confidence by 8.7%, and improved inter-rater agreement from moderate (kappa = 0.56) to substantial (kappa = 0.76). Together, these evaluations support PulmoFoundation as a clinically validated decision-support system for lung pathology.

Synthesizing high fidelity contrast enhanced MRI is clinically valuable for safer and more efficient breast cancer screening, yet remains challenging due to complex lesion textures and heterogeneous enhancement patterns.

Despite years of methodological progress, how far AI has come in liver fibrosis staging has never been systematically evaluated under the heterogeneous, multi-center conditions that define clinical practice. To address this gap, we introduce LiFS, a large-scale dataset and benchmark derived from the MICCAI 2025 CARE-Liver challenge, comprising 610 patients across multiple centers and scanners with multi-sequence MRI. To the best of our knowledge, LiFS is the first benchmark providing complete gadoxetic acid-enhanced sequences with histopathology-confirmed annotations from diverse real-world scanners. Through systematic evaluation of 9 independently developed methods selected from 96 registered teams against in-cohort radiologist reference results, our findings address how far current AI has progressed toward clinical-level liver fibrosis staging from three complementary perspectives. First, against radiologists, the best AI methods were broadly comparable to the senior radiologist and significantly exceeded the junior radiologist in selected settings, while median AI performance generally approached junior-radiologist levels. Second, from a data perspective, cross-center heterogeneity, label imbalance, and contrast-enhanced sequence variability emerge as the dominant challenges for AI methods. Third, from a technical perspective, methodological design choices, including spatial registration, input dimensionality, multi-modal fusion strategy, and backbone architecture, appear to modulate cross-center robustness, although no single choice alone closes the gap. Overall, LiFS provides a rigorous real-world benchmark for positioning the current state of AI in liver fibrosis staging and for enabling future research on the key challenges that limit clinically reliable deployment.

Breast ultrasound imaging is an important noninvasive method for early breast cancer diagnosis, but automatic benign/malignant classification remains challenging due to tumor heterogeneity, blurred boundaries, and data imbalance. To improve feature representation and classification accuracy, this paper proposes the Cross-Stage Attention Mixture-of-Experts Network (CSA-MoE-Net). It adopts a Cross-Stage Attention-enhanced ResNet-18 as the backbone, in which the Cross-Stage Attention module adaptively recalibrates multi-level features, thereby enhancing key tumor features and suppressing redundancy. A three-branch Mixture of Experts (MoE) Block learns complementary features from the Whole Tumor Image, Tumor Core, and Boundary, and an Adaptive Gating Network fuses them to capture morphological, textural, and contextual information. The fused features are denoted as Fused Expert Feature (FEF) in the architecture. Experiments on a balanced dataset of 2,129 breast ultrasound images show that, averaged over 20 independent runs, the model achieves an accuracy of 96.33\%, precision of 94.09\%, recall of 98.53\%, F1-score of 96.25\%, and AUC of 99.50\%. Compared to the baseline ResNet-18, these metrics improve by 3.01, 0.70, 5.37, 2.98, and 5.42 percentage points, respectively. The proposed mechanism requires no invasive modification and can be seamlessly embedded into VGG-16, DenseNet-121, etc., yielding stable performance gains, thus providing reliable support for computer-aided diagnosis.

Pathology foundation models (PFMs) have advanced rapidly in recent years and support training classifiers for a range of histopathology tasks. However, their robustness across hospitals remains limited: performance often degrades when training a classifier on data from one hospital and evaluating it on another target hospital. We address this challenge by fine-tuning PFMs with a local maximum mean discrepancy (LMMD) objective that applies to two settings: domain adaptation, where unlabeled target-hospital data is available, and domain generalization, where target-hospital data is unavailable at all. Experiments at both the patch- and slide-level show consistent improvements across multiple PFMs and tasks.