Oncology/Hematology

Deep learning based on multiparametric MRI for differentiating benign from malignant PI-RADS 3 prostate lesions: a dual-center study.

To address the diagnostic challenge of indeterminate PI-RADS 3 prostate lesions, we developed a non-invasive deep learning radiomics model using multiparametric MRI. This dual-center retrospective study included 382 patients. Lesions on T2WI, DWI, and ADC were segmented and standardized. Deep learning features were extracted via ResNet101, and radiomics features were selected using minimum Redunda...

Multidimensional proteomics and explainable AI feature selection identify cross-platform lung cancer molecular signature in blood plasma.

BACKGROUND: Lung cancer is the leading cause of cancer mortality worldwide despite the availability of low-dose computed tomography (LDCT) for screening in high-risk populations. METHODS: To develop an approach and identify blood-based protein signatures for lung cancer that can be deployed across platforms, we combined data-independent acquisition mass-spectrometry (DIA-MS) and proximity extensio...

Artificial intelligence for the prediction of prognosis in colorectal cancer patients using routine blood indices.

Overall survival (OS) of colorectal cancer (CRC) patients remains suboptimal, especially in advanced disease. This study aimed to construct and valida...

The SALV-Dataset Registry: An Expertly Curated Digital Clinicopathological Dataset for Salivary Gland Tumor Research and AI-Assisted Diagnostic Tools.

UNLABELLED: Salivary gland tumors are rare and morphologically diverse, posing both diagnostic and scientific challenges. This study presents the firs...

Deconstructing cancer in 3D: models, mechanisms, and personalized solutions.

Three-dimensional (3D) cancer models, notably patient-derived organoids (PDOs), address the critical limitations of traditional preclinical systems, i...

Ferroptosis-related gene EPAS1 suppresses breast cancer progression by inhibiting M2 macrophage polarization.

OBJECTIVE: To investigate the role of the ferroptosis-related gene EPAS1 in breast cancer progression and its impact on macrophage polarization. METHO...

Comprehensive benchmarking of deep learning architectures for multiclass histopathological classification of oral epithelial lesions.

BACKGROUND: Accurate histopathological differentiation of normal oral epithelium, oral epithelial dysplasia (OED) and oral squamous cell carcinoma (OS...

Deep learning models built from PSMA PET of the primary tumor can predict synchronous and metachronous prostate cancer metastases.

OBJECTIVE: The objective was to develop prognostic models that included convolutional neural networks (CNN) derived from 18F-DCFPyL (PSMA) PET imaging...

A decision-oriented framework for genomic testing across the prostate cancer continuum.

Genomic testing is now embedded in contemporary prostate cancer care, yet the clinical meaning of different genomic platforms varies substantially by ...

AI in esophageal cancer: advances, barriers to clinical translation, and perspectives for digital health.

BACKGROUND: Esophageal cancer (EC) remains one of the leading causes of cancer-related mortality worldwide. Accurate staging, treatment planning, and ...

Stem cell research and regenerative medicine: meeting report from the Royan International Stem Cell Congress 2025.

The 21st Royan International Stem Cell Congress (3-5 September 2025, Tehran, Iran) convened the global stem cell community to assess the accelerating ...

A systemic immune signature stratifies early-stage breast cancer patients and reveals soluble IL-2RA and PD-1 as potential independent prognostic biomarkers.

BACKGROUND: Breast cancer (BC) is the most common cancer in women and the leading cause of cancer-related death worldwide. Systemic immune dysregulati...

A novel deep learning network for small bowel ulcerative lesion detection and differential diagnosis on double-balloon endoscopy images.

Differentiating small bowel ulcerative diseases (SBUDs) on double-balloon endoscopy (DBE) is challenging. We aimed to develop an artificial intelligen...

Computational exploration of quercetin derivatives from Azadirachta indica leaf as threonine tyrosine kinase inhibitors for potential lung and pancreatic cancer treatment.

Lung and pancreatic adenocarcinomas account for substantial cancer-related mortality worldwide, with current therapeutic efficacy severely limited by ...

Understanding resistance in glioblastoma: insights into personalized and targeted therapeutic strategies.

Glioblastoma multiforme (GBM) is the most common and aggressive primary malignant brain tumor. Despite combined treatments, including surgical removal...

Machine Learning-Based Prediction of Independent Ambulation Following Intramedullary Spinal Cord Tumor Resection.

BACKGROUND AND OBJECTIVES: Intramedullary spinal cord tumor (IMSCT) resection carries a high risk of postoperative neurological deficit because of neu...

Predicting Treatment Response After Total Neoadjuvant Therapy for Locally Advanced Rectal Cancer.

OBJECTIVE: To develop a predictive model for pathological complete response (pCR) after total neoadjuvant therapy (TNT) to inform selection for watch-...

Peristaltic transport and thermodynamic analysis of hybrid nanofluids in porous media using physics-informed neural networks.

This study presents the wavelet-based physics-informed neural networks (PINNs) simulation to analyse entropy generation in hybrid nanofluid peristalti...

Decoding Occult Cervical Lymph Node Metastasis in Head and Neck Squamous Cell Carcinoma: From AI-Driven Multimodal Fusion to Clinical Translation.

PURPOSE OF REVIEW: This review examines the limitations of conventional macroscopic approaches in detecting occult cervical lymph node metastasis (OCL...

3D chromatin architecture-related genes orchestrate LUAD evolution and therapy resistance: insights from integrative machine learning and spatial single-cell mapping.

BACKGROUND: Lung adenocarcinoma (LUAD) is a prevalent and lethal malignancy. The three-dimensional (3D) chromatin architecture significantly influence...