Tri-Reader: An Open-Access, Multi-Stage AI Pipeline for First-Pass Lung Nodule Annotation in Screening CT

2026-01-27

AI Summary

This study addresses the low efficiency of initial lung nodule screening in lung cancer CT scans and the heavy burden of manual annotation by proposing an open-source, end-to-end multi-stage AI pipeline. For the first time, this system integrates pulmonary segmentation, high-sensitivity nodule detection, and malignancy classification into a unified workflow. Built upon open-source models trained on multiple public datasets, the pipeline achieves high sensitivity while substantially reducing false positives and the number of candidate nodules. Experimental results across multiple internal and external datasets demonstrate that its performance approaches that of expert radiologists and exhibits strong cross-institutional generalizability, making it well-suited for efficient preclinical triage in lung cancer screening scenarios.

Technology Category

• Computer Vision: Segmentation
• Humans and AI: Crowd Sourcing and Human Computation
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Using multiple open-access models trained on public datasets, we developed Tri-Reader, a comprehensive, freely available pipeline that integrates lung segmentation, nodule detection, and malignancy classification into a unified tri-stage workflow. The pipeline is designed to prioritize sensitivity while reducing the candidate burden for annotators. To ensure accuracy and generalizability across diverse practices, we evaluated Tri-Reader on multiple internal and external datasets as compared with expert annotations and dataset-provided reference standards.

Problem

• lung nodule annotation
• screening CT
• AI pipeline
• sensitivity
• candidate burden

Innovation

• multi-stage AI pipeline
• lung nodule annotation
• open-access models
• malignancy classification
• sensitivity optimization