Our research underpins 5C Network's Generalised Medical AI framework and Hybrid Intelligence approach to radiology.
Showing 10 out of 10 results
Click tags to filter research publications
Comprehensive survey of 20+ AI models for CT/MRI imaging. Identifies 3 critical gaps — the 3D processing gap, the MRI data desert, and the report generation chasm — and proposes a hybrid architecture for clinically viable AI radiology.
Read PaperA comprehensive multi-site study evaluating autonomous AI systems for multi-pathology detection in chest X-rays within the Indian healthcare system. This research demonstrates the effectiveness of AI-driven diagnostic tools in diverse clinical settings across India, addressing the critical need for scalable radiology solutions in resource-constrained environments.
Read Full ArticleThis study presents a novel vision-language model approach for acute tuberculosis diagnosis, combining chest X-ray imaging with clinical data for enhanced diagnostic accuracy. The multimodal framework demonstrates significant improvements in TB detection rates, particularly in early-stage identification and differential diagnosis scenarios.
Read Full ArticleA comprehensive deep learning framework for automated MRI spine pathology detection, designed to work effectively across diverse clinical settings and patient populations. The system incorporates advanced neural network architectures and attention mechanisms to identify subtle spinal abnormalities with high sensitivity and specificity.
Read Full ArticleThis research advances chronic tuberculosis diagnostics through innovative vision-language models, creating a multimodal framework for precision analysis. The approach combines advanced computer vision techniques with natural language processing to improve diagnostic accuracy for chronic TB cases, addressing a critical gap in current diagnostic methodologies.
Read Full ArticleA comprehensive multi-site study evaluating AI-driven pathology detection and osteoarthritis grading from knee X-ray images. The research demonstrates the effectiveness of automated systems in identifying joint pathologies and grading osteoarthritis severity, providing valuable tools for orthopedic diagnosis and treatment planning.
Read Full ArticleThis study presents advanced 3D convolutional neural networks for improved detection of intracranial bleeding in CT imaging. The research focuses on emergency radiology applications, where rapid and accurate detection of intracranial hemorrhage is critical for patient outcomes and treatment decisions.
Read Full ArticleA comprehensive study on AI and deep learning applications for automated segmentation and quantitative measurement of spinal structures in MRI. The research provides tools for precise anatomical analysis, supporting clinical decision-making in spinal surgery and treatment planning.
Read Full ArticleThis research presents a deep learning-based automated workflow for accurate segmentation and measurement of abdominal organs in CT scans. The system provides comprehensive organ analysis capabilities, supporting diagnostic workflows and treatment planning in abdominal imaging.
Read Full ArticleA deep learning-based ensemble system for automated shoulder fracture detection in clinical radiographs. This research addresses the critical need for rapid and accurate fracture identification in emergency and orthopedic settings, providing valuable decision support tools for clinicians.
Read Full ArticleExplore our research across key areas of AI in radiology. Each page provides an in-depth look at the methods, findings, and clinical implications.
Multi-site study on autonomous chest X-ray pathology detection across India's healthcare system.
Multimodal approach combining imaging with clinical data for improved TB detection and differential diagnosis.
Deep learning framework for automated spine pathology detection using attention mechanisms across diverse clinical settings.
3D CNNs for rapid intracranial hemorrhage detection in CT imaging for emergency department triage.
Ensemble deep learning system for automated fracture identification in emergency and orthopedic radiographs.
Interpretable AI methods with attention visualization and saliency mapping for radiologist trust and adoption.
Multi-site model training without sharing patient data, enabling collaborative AI across India's hospital network.
Automated segmentation and measurement of spinal structures in MRI for clinical decision support.
Adapting diagnostic AI for pediatric imaging with age-specific normalization and specialized approaches.
Automated organ segmentation and measurement in CT scans for diagnostic workflows and treatment planning.
