Oncology/Hematology

Leveraging Large Language Models to Direct Automated PET/CT Tumour Segmentation in Retrospective Data: an Agentic Framework Method

Automated medical image segmentation using deep learning requires large labelled datasets, presenting barriers for rare cancers like sarcoma. We developed an agentic framework integrating LLM analysis of radiologist reports with nnUNet segmentation for 18F-FDG PET/CT imaging data (N=60, 134 studies), aiming to improve automated tumour segmentation for retrospective data. LLM interpretation was opt...

Mechanosensitive TRPV4 immunohistochemistry improves deep learning-based grading of ductal carcinoma in situ beyond H&E morphology

Ductal carcinoma in situ (DCIS) is a non-invasive breast cancer spanning a biologic continuum from atypical ductal hyperplasia (ADH) to high-grade lesions with variable risk of progression to invasive ductal carcinoma (IDC), yet diagnostic accuracy remains limited when based on morphologic assessment via hematoxylin and eosin (H&E) alone. TRPV4, a mechanosensitive ion channel we previously demonst...

Beyond Annotation: Leveraging Raw RNA-seq Reads via Foundation Models for Multi-Cancer Early Detection

Early cancer detection substantially improves patient survival, yet conventional screening methods are directed at single anatomical sites and inadequ...

Clustering high-cost patients in England using machine learning: a population-based cohort study

To identify clusters of high-cost patients in England based on diagnoses and sociodemographic characteristics to inform targeted population health man...

ExCaPT: Explainable Cancer Prediction with Transformer-based models

Cancer remains one of the most significant global health challenges. De-spite advances in treatment, early detection remains a critical concern. The i...

Operational Survival Deficit of Neoadjuvant Chemotherapy in Early-Stage Breast Cancer: A Target Trial Emulation and Causal Machine Learning Study

Neoadjuvant chemotherapy (NAC) is the standard of care for locally advanced breast cancer. However, the disconnect between efficacy in randomized tria...

OpenSlideFM: A Computationally Efficient Multi-Scale Foundation Model for Computational Pathology

Computational pathology increasingly relies on foundation models pre-trained on large-scale histopathology datasets, but existing models require subst...

Predicting the efficacy of Recombinant Human Thrombopoietin in Treating Cancer Therapy-Related Thrombocytopenia:based on stacking ensemble methods

The project aimed to develop a data-driven approach for predicting platelet recovery in cancer treatment–induced thrombocytopenia (CTIT) patients rece...

A method for lung cancer detection and staging from a drop of blood plasma via Raman spectroscopy of well-based samples (ROWS)

We present a new method for lung pathology detection in blood plasma, including lung cancer staging. Raman spectroscopy uses inelastically scattered l...

A Global Atlas of Digital Dermatology to Map Innovation and Disparities

The adoption of artificial intelligence in dermatology promises democratized access to healthcare, but model reliability depends on the quality and co...

Integrating Artificial Intelligence and Precision Medicine to Characterize JAK-STAT Pathway Alterations in FOLFOX-Treated Colorectal Cancer in Disproportionately Affected Groups

Early-onset colorectal cancer (EOCRC) continues to rise, with the steepest increases observed among Hispanic/Latino (H/L) populations, underscoring th...

Artificial Intelligence-Driven Precision Oncology Uncovers Prognostic Significance of RTK-RAS Alterations in FOLFOX-Treated Early-Onset Colorectal Cancer

The incidence of early-onset colorectal cancer (EOCRC; <50 years) is rising rapidly among populations. Although alterations in the RTK-RAS signaling p...

Machine Learning-Based Identification of Blood Biomarkers that Distinguish Precachectic and Cachectic Patients with Pancreatic Ductal Adenocarcinoma

Identification of minimally invasive biomarkers of different stages of cachexia (Ca), and precachexia (PCa) in particular, might help clinicians in tr...

Non-temporal tree-based models outperform temporal deep learning models in the prediction of chemotherapy-induced side effects from longitudinal laboratory data

The increasing availability of electronic health records (EHRs) provides opportunities to apply machine learning (ML) methods in support of clinical d...

Personalized Risk Stratification in Colon Cancer using Radiomic-Based Predictive Models

Colon Cancer (CC) is among the most frequently diagnosed malignancies and a leading cause of cancer-related death worldwide. Five-year survival varies...

Research on the Diagnostic Value and Immune Microenvironment Regulatory Mechanism of FOLR3 Gene in Endometrial Cancer Based on Multi-omics Data Algorithms

FOLR3 serves as an important member of the folate metabolic pathway and plays a crucial role in various malignant tumors. However, the expression patt...

Conversational Artificial Intelligence-Based Integration of Clinical and Genomic Data Identifies MAPK Alterations in Colorectal Cancer

Colorectal cancer (CRC) exhibits marked heterogeneity across age, ancestry, and treatment context, underscored by the rising incidence of early-onset ...

Integrative AI Model Combining Radiomics and Phenomics to Predict Survival in Non-Small Cell Lung Cancer Patients Treated with Immunotherapy Containing Regimen

Immunotherapy has improved outcomes in non-small cell lung cancer (NSCLC), but only a subset of patients achieves durable survival benefit. Convention...

Sensitive and Specific Early-Stage Breast Cancer Detection using Deep Proteome Profiling from Plasma

Proteome-guided liquid biopsy tests hold immense promise for the future of early cancer detection. Our previous published work has shown strong perfor...

A novel open access multimodal dataset of nodule imaging and circulating proteome from a lung cancer screening cohort

Low-dose computed tomography (LDCT) lung cancer screening has significantly enhanced early detection and patient survival rates in the population at r...