PyTorch implementation of Grouped SSD (GSSD) and GSSD++ for focal liver lesion detection from multi-phase CT images (MICCAI 2018, IEEE TETCI 2021)

MediScan: AI-powered bone fracture detection system achieving 99.8% accuracy through deep learning. Features real-time X-ray analysis, transparent Grad-CAM visualizations, and clinical integration tools. Built with Python/FastAPI backend and responsive HTML/CSS frontend, making advanced medical diagnostics more accessible to healthcare providers.

Sparrow AI - API for disease diagnostics

Flask based web app with five machine learning models on the 10 most common disease prediction, covid19 prediction, breast cancer, chronic kidney disease and heart disease predictions with their symptoms as inputs or medical report (pdf format) as input.

Medical Diagnostic Module Programmed with Python and using Fuzzy Logic

A medical diagnosis system

Medical Diagnosis system using Prolog

Machine learning models for detection of diseases.

Quick Android app for medical diagnosis, currently just using Endless Medical API

Egészségügyi szűrőprogramok, orvosi tesztek eredményességének vizsgálata.

Machine learning model in Julia classifies patients with Diabetes Mellitus, Diabetic Retinopathy, and Diabetic Nephropathy using biomarkers Hornerin and SFN, plus clinical features like age and diabetic duration, for diagnostic applications.

This project uses data mining and ML to enhance liver disease detection. Analyzing clinical markers like bilirubin and enzymes from the ILPD dataset , I compared six models. Random Forest proved most accurate at 72.57% , offering a non-invasive tool for early diagnosis and better patient care.

"Advanced ternary logic framework for processing uncertainty in computational decision systems—solving the fundamental limitation of binary logic in real-world applications."

Advanced machine learning system for diabetes risk prediction using clinical biomarkers and patient health data

AI-driven disease prediction model based on symptoms using machine learning.

CancerGuardian is a machine learning-powered web app that helps predict breast cancer diagnoses based on cytology measurements. 🩺✨ Built with Streamlit, Scikit-Learn, and Plotly, this tool visualizes tumor characteristics and provides predictions using a trained model. 🚀

MRI brain tumor classifier using deep learning. CNN architecture for binary classification of brain scans with comprehensive preprocessing, augmentation, and performance evaluation.

Machine Learning Modeling for Diabetes Screening and Diagnostics

ML for MRI image classification, Intelligent Systems course (3rd year, 2nd semester)

An AI-powered medical assistant that uses machine learning and deep learning to classify diabetes, detect pneumonia and diabetic retinopathy from images, and provides intelligent health consultation via a Gemini 2.5 Flash chatbot.

ML for early diagnosis of Alzheimer's disease. Results and jupyter notebook published on GitHub pages.

A Clinical Decision Support System (CDSS) for psychiatric/neurological triage, powered by AI and synthetic data.

This repository features cutting-edge machine learning applications in healthcare, addressing diverse challenges such as dermatological lesion detection, ECG signal categorization, gland segmentation in colorectal cancer, pathological myopia prediction, and pneumothorax identification.

CancerGuardian is a machine learning-powered web app that helps predict breast cancer diagnoses based on cytology measurements. 🩺✨ Built with Streamlit, Scikit-Learn, and Plotly, this tool visualizes tumor characteristics and provides predictions using a trained model. 🚀

AI-driven heart disease prediction model using machine learning for early diagnosis.

A machine learning project for diagnosing hyperthyroidism using thyroid function test data, symptoms, and medical history. Applied Multinomial Naive Bayes, SVM, Random Forest, and MLP classifiers with data cleaning, visualizations, and model evaluation to enhance medical diagnostics and support clinical decision-making.

A deep learning model built with TensorFlow for the rapid, non-invasive classification of Type 2 Diabetes using Raman spectroscopy data. Achieves 93.75% accuracy with 100% recall for diabetic cases.

Perform partial verification bias correction for estimates of accuracy measures in diagnostic accuracy studies

Web-based UI and backend for a fingerprint-capacitance POCT device (Multicap Dx) for HIV/HBV/HCV antigen detection.

MedAI - AI-powered medical diagnostic assistant with intelligent symptom analysis and health guidance