Pathology

Differential Attention Feature Aggregator (DAFE) for Advanced Melanoma Detection.

Melanoma is a highly aggressive form of skin cancer with a significant mortality rate. Over the past two decades, its incidence has been on the rise and is projected to increase further in the future. Early treatment has a higher survival rate. Currently, dermatologists rely on visual inspection followed by biopsy to diagnose melanoma, but there is considerable variability in diagnostic accuracy a...

An optimized graph neural network approach for robust and explainable IoT intrusion detection against adversarial attacks.

The swift incorporation of cutting edge technologies has expanded the range for a potential adversary to conduct adaptive attacks against systems and despite progress in detection, machine learning based security remains vulnerable, highlighting the need for more robust and reliable defense methods. Existing DDoS detection techniques are not resilient against adaptive adversarial manipulation and ...

A Unified Deep Learning Framework for Instance Segmentation Across Diverse Cytological Stains.

OBJECTIVE: Assess whether a single instance-segmentation model can operate robustly across multiple cytological stains, avoiding stain-specific pipeli...

Artificial Intelligence in Breast Cancer Lymph Node Evaluation: Is Neoadjuvant Chemotherapy the Achilles' Heel?

CONTEXT.—: Artificial intelligence (AI) has demonstrated high accuracy in detecting lymph node (LN) metastases in treatment-naïve invasive breast canc...

Single-cell and bulk omics uncover fibroblast heterogeneity and HSPH1 as a key driver in Barrett's esophagus to esophageal adenocarcinoma progression.

BACKGROUND: Esophageal adenocarcinoma (EAC) is a highly aggressive malignancy with poor prognosis, often evolving from Barrett's esophagus (BE). Under...

An Interpretable Deep-Learning Approach for Efficient CEST Parameter Quantification: Importance-Ranked Saturation Transfer MRI Protocol.

PURPOSE: An optimal design of saturation-transfer MR fingerprinting (ST-MRF) sequences is essential to accelerate imaging and improve tissue quantific...

Near-infrared imaging-based high-content analysis for label-free assessment of internal cellular heterogeneity in spheroid.

Non-invasive analysis of spheroid quality was essential because spheroids better recapitulated in vivo-like cell-cell and cell-extracellular matrix (E...

STAID: A Self-Refining Deep Learning Framework for Spatial Cell-Type Deconvolution with Biologically Informed Modeling.

Spatial transcriptomics provides high-throughput measurement of gene expression while retaining spatial context; however, inferring accurate cell-type...

Geometry of the cumulant series in diffusion MRI.

Water diffusion gives rise to micron-scale sensitivity of diffusion MRI (dMRI) to cellular-level tissue structure. Precision medicine and quantitative...

Artificial intelligence model predicts malignant transformation of oral leukoplakia and optimizes interventions.

PURPOSE: Oral leukoplakia (OL), the most common oral potentially malignant disorder (OPMD), poses a significant risk for transformation to oral squamo...

Integrating machine learning and single-cell sequencing to reveal the role of kinase-related genes in subtype classification and prognostic significance of lung squamous cell carcinoma.

BACKGROUND: Lung squamous cell carcinoma (LUSC) exhibits poor prognosis and a highly complex tumor immune microenvironment (TIME), creating an urgent ...

Advanced computer-aided diagnosis for age-related macular degeneration: integrating segmentation and feature extraction for precise diagnosis.

Age-related Macular Degeneration (AMD) is a leading cause of vision loss globally; necessitating early detection and precise diagnosis for effective i...

Explainable artificial intelligence with pyramid vision transformer model for multi-class malignant cell classification on cytology slides.

Digital pathology involves the digitisation of histology slides, which is vital in modern healthcare, especially for cancer detection and diagnosis. S...

Photon absorption remote sensing (PARS): comprehensive absorption imaging enabling label-free biomolecule characterization and mapping.

Label-free optical absorption microscopy techniques continue to evolve as promising tools for label-free histopathological imaging of cells and tissue...

Integration of transcriptome and DNA methylation reveals the mechanism of cilia-related genes in recurrent miscarriage.

Recurrent miscarriage (RM), a complex pregnancy disorder with largely undefined molecular mechanisms, has been associated with epigenetic abnormalitie...

AI as a differentiated cognitive partner in medical education: a comparative study of popular science versus research-based curriculum extensions in histology and embryology.

OBJECTIVE: This study compared the efficacy of Popular Science (PS) and Research-Based (RS) curriculum extensions in a Histology and Embryology course...

Deep learning based on CD3 histological slides for prediction of colon cancer outcome: analysis of three international stage III colon cancer cohorts.

Prognostic stratification in stage III colon cancer remains poor, despite treatment advances. Tumor-infiltrating lymphocytes, particularly CD3+ T cell...

Machine learning and multi-dimensional transcriptomics reveal the key molecular network of benzo(a)pyrene/NNK in promoting laryngeal cancer and develop prognostic models.

Benzo(a)pyrene (BaP) and 4-(methylnitrosamino)-1-(3-pyridyl)-1-butanone (NNK), as typical environmental carcinogens, are widely present in tobacco smo...

AI-predicted spatial transcriptomics unlocks breast cancer biomarkers from pathology.

Spatial transcriptomics (ST) assays are transforming our understanding of tumor heterogeneity, but their high cost limits their application in large-s...

Three Data-Driven Lip Soft-Tissue Phenotypes and Their Dento-Skeletal Associations in Orthodontic Patients: An Exploratory Unsupervised Learning Study.

BACKGROUND: Conventional facial diagnosis emphasizes skeletal and dental measures while lip features are assessed piecemeal. We aimed to identify data...