Code and Dataset for: Deep Learning-Assisted Asbestos Screening in Soil: A Hierarchical Statistical Approach to Error Propagation
Abstract
This repository provides the comprehensive implementation and data supporting the research on AI-assisted asbestos screening. Contents: AI Implementation: Source code for the two-stage Mask R-CNN model (Detectron2) and the rotation-assisted recovery algorithm (ORB/RANSAC). Statistical Framework: Python scripts for hierarchical error propagation. Dataset: ~1000 annotated PLM images of chrysotile-positive and negative control soil samples
Fields of Study & Subjects
Advanced Neural Network Applications
Occupational and environmental lung diseases
Machine Learning in Materials Science
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 1 March 2026
- Language
- EN