Pathology

A hypergraph-based model for tumor prognosis using local and global information fusion on H&E-stained histology images.

Prognostic variables play a critical role in guiding clinical treatment decisions for cancer patients. However, extracting prognostic information from gigapixel histopathology slides remains a significant challenge. While attention-based deep learning models trained on histologic images have been extensively investigated, existing approaches often fail to effectively model slide-level contextual i...

Cellflow: Advancing pathological image augmentation from spatial views to temporal trajectories.

Deep learning has advanced pathological image analysis but remains constrained by limited annotated data, especially for fine-grained diagnostic tasks such as tumor subtyping, grading, and cellularity assessment. While data augmentation alleviates this issue, existing methods are restricted to spatial manipulations that lack morphological plausibility and overlook the temporal attributes of pathol...

Toward genomic personalization of breast cancer radiotherapy: foundations, challenges, and a roadmap for clinical integration.

Personalizing radiotherapy dose in breast cancer remains a major unmet need, as current treatment paradigms rely on uniform prescriptions that overloo...

A deep learning model based on ultrasound imaging to differentiate malignant from benign pleural effusion: a multicenter cohort study.

Multi-angle, cross-domain fusion strategy enhances automated insect identification and hierarchical categorization: a case study on assassin bugs (Hemiptera: Reduviidae).

Automated insect identification systems hold significant value for biodiversity monitoring, pest management, citizen science initiatives and systemati...

Noninvasive Staging of Hepatic Fibrosis in Patients with Autoimmune Liver Disease Using Deep Learning.

RATIONALE AND OBJECTIVES: Accurate staging of hepatic fibrosis is essential for guiding immunosuppressive and antifibrotic therapies. However, percuta...

Multi-omics characterization of benzo[a]pyrene toxicity networks identifies SERPINE1 and STK3 as prognostic biomarkers and therapeutic targets in head and neck squamous cell carcinoma.

Benzo[a]pyrene (BaP), a ubiquitous environmental carcinogen predominantly found in tobacco smoke and air pollution, plays a pivotal role in head and n...

Establishing an Evidence-based Modern Breast MRI Program.

Breast MRI has evolved over the past several decades into a cornerstone of breast imaging. Historically, dynamic contrast-enhanced (DCE) MRI has serve...

Development and Validation of a Computational Histology Artificial Intelligence-Powered Predictive Biomarker for Selection of Chemotherapy in Advanced Pancreatic Cancer.

PURPOSE: Predictive biomarkers to guide selection of first-line chemotherapy for advanced pancreatic ductal adenocarcinoma (PDAC) are an unmet clinica...

Selective multimodal deep learning for reliable breast cancer subtype classification from histopathology and genomic data.

Accurate classification of breast cancer subtypes is critical for personalized treatment planning and prognostic assessment. While histopathology ...

Multi-modal AI for opportunistic screening, staging and progression risk stratification of steatotic liver disease.

The global rise in steatotic liver disease poses a significant public health challenge. While non-contrast computed tomography scans hold promise for ...

Heterogeneous graph neural networks reveal molecular mechanisms of folate deficiency in placental insufficiency through multiomics integration.

Placental insufficiency affects five to ten% of pregnancies worldwide, and folate deficiency has emerged as a key contributing factor. The molecular p...

HMI-LUSC: A Histological Hyperspectral Imaging Dataset for Lung Squamous Cell Carcinoma.

Hyperspectral imaging (HSI) is a three-dimensional imaging technique that integrates spectroscopy and imaging. When combined with microscopy, hyperspe...

A novel deep learning model for automated diagnosis of oral squamous cell carcinoma and related leukoplakia in pathological images.

BACKGROUND: Oral squamous cell carcinoma (OSCC) is the sixth most common type of cancer worldwide. Its diagnosis and treatment rely on pathological se...

Efficacy of artificial intelligence-assisted upper gastrointestinal endoscopy for neoplasm detection: a systematic review and meta-analysis of randomized controlled trials.

BACKGROUND AND AIMS: EGD remains the primary diagnostic modality for evaluating lesions of the upper gastrointestinal (UGI) tract. This meta-analysis ...

Artificial intelligence in biomaterials for oral oncology.

Oral cancer and oral potentially malignant disorders (OPMDs) remain a significant challenge in diagnosis and therapy, primarily due to inherent limita...

Comprehensive dataset on macro-porous PVDF flat sheet membranes for membrane distillation: Materials characteristics, morphology and performance data.

This data article presents a structured dataset from the transfer of a proven PVDF hollow-fiber formulation to macro-porous PVDF flat sheet membranes ...

Unveiling hidden variables in stressed bacteria.

Phenotypic heterogeneity is a defining feature of bacterial stress responses, long framed as irreducible noise arising from stochastic molecular event...

Evaluation of KU-F40 automated microscope for parasitology: when artificial intelligence meets old school microscopy.

Intestinal parasitic infections (IPIs) have a worldwide distribution and have a major impact on health, work capacity, and economy in many countries. ...

Toward Integration of Molecular Measures and Artificial Intelligence-Based Assessments With Clinical End Points in Inflammatory Bowel Disease.

Multimodal profiling of inflammatory bowel disease (IBD) patient tissue and blood samples has revealed the disease spectrum in unprecedented detail, a...