Oncology/Hematology

Beyond handcrafted radiomics in oncologic imaging: Innovations in deep, explainable, multi-site and multi-omics radiomics approaches.

Radiomics seeks to convert medical images into quantitative biomarkers capable of capturing tumor phenotype, microenvironment, and underlying biology. Over the past fifteen years, the field has expanded beyond handcrafted radiomic features toward deep radiomics, multi-site radiomics, and multi-omics integration, while the need for interpretability has become increasingly central. The aim of this a...

Automating classification of treatment responses to combined targeted therapy and immunotherapy in HCC.

Tyrosine kinase inhibitor (TKI) combined with immunotherapy regimens are now widely used for treating advanced hepatocellular carcinoma (HCC), but their clinical efficacy is limited to a subset of patients. Considering that the vast majority of advanced HCC patients lose the opportunity for liver resection and thus cannot provide tumor tissue samples, we leveraged the clinical and image data to co...

Multi-view deep learning for automated lymphoma staging from 18F-FDG PET/CT: physician-level accuracy with high-throughput workflow.

Automatic Detection of Subcellular-Scale Metabolic Dynamics via Spontaneous-Stimulated Raman Spatial Colocalization.

Cellular structural heterogeneity and low intrinsic contrast in label-free bright-field imaging hinder accurate localization of subcellular structures...

Radiomics analysis of MRI improves prediction of lymph node metastasis in laryngeal squamous cell carcinoma.

OBJECTIVE: To explore the role of multi-sequence magnetic resonance imaging (MRI) images in preoperative prediction of lymph node metastasis in laryng...

Potential mechanisms of Si-Wu-Tang against esophageal squamous cell carcinoma: A machine learning pharmacological study.

The purpose of this study is to explore the potential mechanism of Si-Wu-Tang (SWT) against esophageal squamous cell carcinoma (ESCC). Initially, 18 a...

Generative artificial intelligence for patient education material on gastric cancer prevention.

BACKGROUND:  This study assessed the effectiveness of large language models (LLMs) in generating lay summaries for patient education on the management...

Integrative transcriptomic and machine learning framework reveals candidate genes and potential mechanisms of aflatoxin B1 exposure in breast cancer.

Aflatoxin B1 (AFB1), a known mycotoxin and environmental hazard, has been linked to breast cancer, yet the exact biological pathways remain poorly cha...

Pathomic model to predict the expression of UQCRH and overall survival of lung adenocarcinoma patients.

Interpreting cancer genetics through a two-step "evolutionary cascade hypothesis": bridging neutral and selective perspectives.

BACKGROUND: DNA mutations are the fundamental engines of cancer, driving its initiation and progression. The forces that fuel malignancy are also the ...

Prognostic pan-cancer and single-cancer models: A large-scale analysis using a real-world clinico-genomic database.

Prognostic models in oncology have a profound impact on personalized cancer care and patient profiling, but tend to be heterogeneously developed and i...

Computational assessment of the relationship between metabolism and histone methylation in cancer cells.

Aberrant histone methylation and metabolic alterations are key hallmarks of cancer. Metabolic reprogramming during tumorigenesis could impact the hist...

Interpretable machine learning based on intratumoral and peritumoral ultrasound radiomics for predicting central lymph node metastasis in papillary thyroid carcinoma.

OBJECTIVES: This retrospective and single-center study aimed to develop machine learning (ML) model integrating clinical features, ultrasound (US) fea...

eccDNA2Ca: an ensemble deep learning framework for interpretable prediction of cancer-associated extrachromosomal circular DNA.

BACKGROUND: Extrachromosomal circular DNA (eccDNA) is increasingly recognized as a critical driver of oncogene amplification, therapeutic resistance, ...

Towards real time AI-augmented fluorescence-guided surgery: Evidence and translational readiness across neurosurgical, gynaecological, and thoracic oncology.

Fluorescence-guided surgery (FgS) is increasingly used across oncologic specialties to enhance intraoperative visualisation of tumour tissue and lymph...

AI Co-Scientists Move to the Front Lines of Cancer Research.

Artificial intelligence systems are beginning to function as "co-scientists" in cancer research, generating drug candidates, prioritizing immunotherap...

Prediction model for ctDNA detectability in liquid comprehensive genomic profiling of advanced pancreatic cancer based on Japanese real-world data.

BACKGROUND: Circulating tumor DNA (ctDNA) is sometimes undetectable in liquid comprehensive genomic profiling (CGP) of advanced-stage pancreatic cance...

A simplified co-culture reveals altered cardiotoxic responses to doxorubicin in hPSC-derived cardiomyocytes in the presence of endothelial cells.

Cardiotoxicity is a significant challenge in cancer therapies, particularly with doxorubicin, a widely used anthracycline. More predictive in vitro mo...

Early detection of female-specific cancers using longitudinal healthcare records with a multichannel convolutional neural network.

OBJECTIVES: Female-specific cancers, including breast, ovarian, cervical and uterine malignancies, lack comprehensive early detection approaches, part...

The use of advanced machine learning to predict outcomes after atezolizumab plus bevacizumab for advanced hepatocellular carcinoma: a retrospective cohort study.

BACKGROUND: Combination immune checkpoint inhibitors are recommended as first-line therapy for advanced hepatocellular carcinoma. However, only a thir...