Graph-based Multi-task Learning Solution for Ultrasound Spinal Bone Feature Detection

This Scoliosis Detection Application is a deep learning-based web application built using Streamlit. This project combines machine learning, image processing (OpenCV), and web development to assist in early scoliosis detection. It allows users to upload an X-ray image to determine whether the spine is Normal or affected by Scoliosis.

A PyQt5/VTK-based desktop application for visualizing and registering multimodal medical imaging data (MRI, X-Ray, and Surface Topography) to create comprehensive 3D models of the human torso for scoliosis surgical planning.

Code for the SMAScoliosis prediction model

In collaboration with Prof. Tushar Sandhan (Perception and Intelligence Lab, IITK) and Prof. Michael Gardner, MD (Professor of Orthopedic Surgery, Stanford University School of Medicine; Co-Founder, National Scoliosis Clinic)

Notebooks and Final Presentation Deck for NAPI Internship

A neural network and ensemble learning approach to predicting patient outcomes using proteomics.

Children's spine-health AI companion connecting clinical rehab plans with family follow-up

Automatic Cobb angle estimation in spine AP view X-rays using YOLOv11-Pose

OrthoCare_AI is an AI-powered orthopaedics and musculoskeletal health research platform. Content is compiled from published medical literature, clinical guidelines (AAOS, BOA, NICE, WHO), and research databases. It enables upload and analysis of reports. This open, collaborative system grows stronger with every user. Share it widely.

Interpretable deep learning for automated scoliosis assessment from spinal radiographs using landmarks, centerline geometry, and locked fusion.

Field rehabilitation screening system for posture symmetry, squat assessment, Adams testing, and cross-protocol reports

Technical lab for rehabilitation motion assessment metrics, symmetry indices, and screening evidence

AI-powered scoliosis brace monitoring web app using MediaPipe pose estimation. Tracks posture, gait, brace effectiveness, and generates clinical PDF reports. Educational platform for parents and clinicians.

ML pipeline for pathogenic variant analysis in scoliosis genes using ClinVar, gnomAD, UMAP, and KMeans clustering

Два ИИ-инструмента для раннего скрининга здоровья прямо в браузере, без сервера и без сбора данных - скрининг сколиоза/осанки (skaleoz) и оценка риска патологий печени/ХВГ (HepaIQ). Astana AI Week 2026.