Other Cancers

Pan-cancer analysis of single-cell profiles with polygenic signals reveals genetic influences on tumor immunity across cancers.

Inherited genetic variation can weaken the ability of the immune system to detect and eliminate malignant cells, limiting the effectiveness of cancer immunotherapy. However, how germline polymorphisms shape the tumor immune microenvironment across cancers remains unclear. Here, we present a polygenic analysis framework that integrates single-cell RNA sequencing with GWAS summary statistics across ...

A multi-level attention CNN-transformer based framework for the detection of brain tumor using regional dual-score explainability.

Deep learning models for brain tumor diagnosis often lack interpretability beyond qualitative visual heatmaps. Clinicians require not only tumor localization but also quantitative assessment of explanation quality and diagnostic relevance, capabilities absent in conventional explainability methods. This paper introduces a classification-explainability framework addressing these limitations. The Mu...

Immune Checkpoint Inhibitor-Associated Cardiovascular Toxicity: Mechanisms, Clinical Manifestations, and Clinical Impact.

Immune checkpoint inhibitors (ICIs) represent a class of novel anticancer agents that enhance T cell-mediated recognition and elimination of tumor cel...

Bioinformatic and experimental analysis reveals ITGA5 as a driver of ovarian clear cell carcinoma progression and platinum resistance.

UNLABELLED: Ovarian clear cell carcinoma (OCCC) is a clinically aggressive subtype of epithelial ovarian cancer with limited therapeutic options. Here...

Performance of a self-attention-based model in the task of differentiating clear cell renal cell carcinoma from other renal tumors: variable Vision Transformer (vViT).

OBJECTIVES: To examine the performance of the variable Vision Transformer (vViT) in comparison with that of convolutional neural networks (CNNs) in th...

Prognostic Significance of Baseline 18F-FDG PET/CT Parameters in Combination with an Artificial Intelligence-Based Pleural Effusion Segmentation Model for Malignant Pleural Effusion.

OBJECTIVES: We aimed to use an artificial intelligence (AI)-based pleural effusion segmentation model on baseline 18F-FDG positron emission tomography...

Development and validation of an MRI-based deep learning system for triple-class ER expression classification in breast cancer: a large-scale multicenter study.

BACKGROUND: Estrogen receptor (ER) expression is a key prognostic and predictive marker in breast cancer. The 2020 ASCO/CAP guidelines classify tumors...

Single-cell analysis reveals that NRG1/3-ERBB4 signaling affects metabolic reprogramming and immune escape in Wilms tumor.

BACKGROUND: Wilms tumor presents a heterogeneous tumor microenvironment. This study aimed to characterize the tumor microenvironment and identify prog...

Precise Staging of Diabetic Retinopathy Through Machine Learning Analysis of Leakage Source Characteristics: A Radiomics-Driven Approach Integrating OCT-A and FFA.

INTRODUCTION: Evaluating retinal fundus image for diabetic retinopathy (DR) assessment is used to reduce the risk of blindness among diabetic patients...

Mechanism of UBE2T regulating endometrial cancer proliferation through m6A modification.

Endometrial cancer (EC) is a prevalent malignancy in women. UBE2T, a member of the E2 ubiquitin-conjugating enzyme family, has emerged as a potential ...

Artificial intelligence-based vascular pattern profiling predicts prognosis and therapeutic response in hepatocellular carcinoma.

BACKGROUND: Hepatocellular carcinoma (HCC) is characterized by active angiogenesis and heterogeneous vascular patterns. However, vascular pattern prof...

Development and Validation of a Deep Learning-enabled Single Breath-hold Abbreviated MRI Protocol for Hepatocellular Carcinoma Diagnosis.

Purpose To develop a deep learning-enabled single breath-hold abbreviated MRI (DL-SBH-aMRI) protocol for hepatocellular carcinoma (HCC) diagnosis. Mat...

Tumor-preserving Deformable Registration of Longitudinal Breast DCE MRI during Neoadjuvant Chemotherapy.

Purpose To develop a deep learning-based deformable registration method for breast dynamic contrast-enhanced (DCE) MRI that preserves tumor regions wh...

Cytokine-induced killer (CIK) Cells-associated transcriptome signature reveals the potential immunomodulatory role of TNFSF14 in clear cell renal cell carcinoma.

Among adoptive immune cell therapies, cytokine-induced killer cell (CIK) therapy has demonstrated clear therapeutic relevance in multiple cancers, par...

PFAS is associated with perineural invasion in triple-negative breast cancer with a potential role for Cathepsin D dysregulation: a multi-omics and experimental study.

Per- and polyfluoroalkyl substances (PFAS) are persistent pollutants linked to breast cancer (BC), but their role in perineural invasion (PNI) of trip...

Targeting tumor-associated G-protein coupled receptors: beyond single-axis inhibition toward multidimensional regulation.

G protein-coupled receptors (GPCRs) serve as central hubs in tumor signal transduction and microenvironment regulation. However, their therapeutic exp...

Evaluation of 2D and 3D nnU-Net models with two-label and three-label strategies for automatic segmentation and total metabolic tumor volume estimation of metastatic differentiated thyroid carcinoma on FDG-PET/CT.

PURPOSE: To evaluate the segmentation performance and total metabolic tumor volume (TMTV) prediction accuracy of 2D and 3D nnU-Net models under two-la...

Predicting resistance to neoadjuvant chemotherapy in osteosarcoma using machine learning with clinical data and T2-weighted MRI radiomics.

OBJECTIVES: Identifying patients at risk of chemoresistant osteosarcoma enables risk-adapted management. This study aimed to predict chemoresistant os...

Deep Learning Algorithm Based on Contrast-Enhanced Ultrasound Potentially Optimizes Treatment Strategies for Solitary Primary Hepatocellular Carcinoma.

OBJECTIVE: We aimed to propose a prognostic framework using a dual-branch Vision Transformer (ViT) deep learning (DL) architecture for stratifying rec...

Enhancing esophageal cancer detection using a deep learning framework and a novel spectrum-aided vision enhancer for virtual narrow band imaging.

Esophageal cancer is a highly aggressive malignancy where early detection is critical for survival. However, early-stage lesions typically present sub...