Apex
Digital Labs
Surgical AI Labelling Framework
A comprehensive framework for data annotation in surgical robotics, designed to optimize the development of ML models for surgical robots.
AI researcher and entrepreneur with expertise in computer vision and machine learning for medical applications.
Featured Endeavor
Surgical AI Labelling Framework
A comprehensive framework for data annotation in surgical robotics, designed to optimize the development of ML models for surgical robots.
Endeavor Roadmap
Phase 1: Epistemic Scoring (2 years)
Recommender System for Medical Image Annotation
A recommender system that assesses the difficulty of medical images by assigning them an epistemic score, helping data annotators prioritize which images require more attention.
- Developing algorithms for low-dimensional medical images like X-rays
- Validating algorithms through partnerships with leading healthcare providers
- Expanding to high-dimensional images like MRIs and CT scans
- Launching a web-based application for robotics companies to rank medical images
Phase 2: Spatial Prompts (3 years)
Auto-Segmentation with User Prompts
Developing auto-segmentation algorithms that utilize various types of user prompts to guide the model in accurately segmenting images by highlighting key areas of interest.
- Implementing positive and negative click prompts for initial segmentation
- Adding bounding box prompts to provide greater context and precision
- Incorporating scribble prompts to capture complex shapes and intricate details
- Significantly enhancing the accuracy and effectiveness of the segmentation process
Phase 3: Multi-Modal Prompts (5 years)
Text-Vision Integration for Medical Image Segmentation
Developing an auto-segmentation algorithm that integrates textual descriptions with visual data to improve the segmentation of medical images.
- Preprocessing textual descriptions using NLP techniques
- Encoding text into numerical representations using pre-trained models like BERT or GPT
- Aligning and fusing textual embeddings with visual prompts through a multi-modal decoder
- Calculating attention scores to optimize the segmentation process
Interactive Demo
Experience Our Surgical AI Labelling Framework
Try our interactive demo to see how our framework can improve your medical image annotation workflow.
Stay Updated
Subscribe to our newsletter to receive updates about our latest developments and features.