{"id":31967710,"url":"https://github.com/fitushar/triannot","last_synced_at":"2026-02-19T06:02:51.872Z","repository":{"id":317258815,"uuid":"1066643106","full_name":"fitushar/TriAnnot","owner":"fitushar","description":"Tri-Reader: An Open-Access, Multi-Stage AI Pipeline for First-Pass Lung Nodule Annotation in Screening CT","archived":false,"fork":false,"pushed_at":"2026-01-28T08:33:45.000Z","size":4353,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-01-28T23:51:10.540Z","etag":null,"topics":["annotation-tool","computed-tomography"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/fitushar.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-29T19:06:52.000Z","updated_at":"2026-01-28T08:48:57.000Z","dependencies_parsed_at":null,"dependency_job_id":"98ea7e39-7990-40c9-9565-ee3bb3f775da","html_url":"https://github.com/fitushar/TriAnnot","commit_stats":null,"previous_names":["fitushar/triannot"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/fitushar/TriAnnot","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fitushar%2FTriAnnot","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fitushar%2FTriAnnot/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fitushar%2FTriAnnot/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fitushar%2FTriAnnot/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/fitushar","download_url":"https://codeload.github.com/fitushar/TriAnnot/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fitushar%2FTriAnnot/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29604552,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-19T05:11:50.834Z","status":"ssl_error","status_checked_at":"2026-02-19T05:11:38.921Z","response_time":117,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["annotation-tool","computed-tomography"],"created_at":"2025-10-14T18:41:02.565Z","updated_at":"2026-02-19T06:02:51.865Z","avatar_url":"https://github.com/fitushar.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Tri-Reader\n\n\u003cdiv align=\"center\"\u003e\n\n\n**Tri-Reader: An Open-Access, Multi-Stage AI Pipeline for First-Pass Lung Nodule Annotation in Screening CT**\n\n[![License: CC BY-NC 4.0](https://img.shields.io/badge/License-CC%20BY--NC%204.0-lightgrey.svg)](https://creativecommons.org/licenses/by-nc/4.0/)\n[![Docker](https://img.shields.io/badge/Docker-ft42%2Fpins%3Alatest-2496ED?logo=docker)](https://hub.docker.com/r/ft42/pins)\n[![Python](https://img.shields.io/badge/Python-3.9+-green.svg)](https://python.org)\n[![Medical Imaging](https://img.shields.io/badge/Medical-Imaging-red.svg)](https://simpleitk.org)\n[![PyTorch](https://img.shields.io/badge/PyTorch-2.8.0-orange.svg)](https://pytorch.org)\n[![MONAI](https://img.shields.io/badge/MONAI-1.4.0-blue.svg)](https://monai.io)\n[![PiNS](https://img.shields.io/badge/PiNS-1.0.0-blue.svg)](https://github.com/fitushar/PiNS)\n[![CaNA](https://img.shields.io/badge/CaNA-1.0.0-cyan.svg)](https://github.com/fitushar/CaNA)\n\u003c/div\u003e\n\nUsing multiple open-access models trained on public datasets, we developed Tri-Reader, a\ncomprehensive, freely available pipeline that integrates lung segmentation, nodule detection, and\nmalignancy classification into a unified tri-stage workflow. The pipeline is designed to\nprioritize sensitivity while reducing the candidate burden for annotators. To ensure accuracy and\ngeneralizability across diverse practices, we evaluated Tri-Reader on multiple internal and external\ndatasets as compared with expert annotations and dataset-provided reference standards \n\n### Citation Manuscript \n\n[![arXiv](https://img.shields.io/badge/arXiv-2405.04605-\u003ccolor\u003e.svg)](https://arxiv.org/pdf/2601.19380)\n\n```ruby\n@misc{tushar2026trireaderopenaccessmultistageai,\n      title={Tri-Reader: An Open-Access, Multi-Stage AI Pipeline for First-Pass Lung Nodule Annotation in Screening CT}, \n      author={Fakrul Islam Tushar and Joseph Y. Lo},\n      year={2026},\n      eprint={2601.19380},\n      archivePrefix={arXiv},\n      primaryClass={cs.CV},\n      url={https://arxiv.org/abs/2601.19380}, \n}\n```\n\n**Tri-Reader** tri-stage workflow for first-pass lung nodule annotation in screening CT.\nAfter lung segmentation (VISTA3D) removes extra-pulmonary candidates, Stage 1 performs consensus\nCADe using two complementary detection models (CADe-ROIonly and the false-positive–aware\nCADe-FPaware trained via strategic hard-negative mining); candidates detected by both are promoted\nto confidence = 1.0. Stage 2 applies ensemble malignancy scoring to disagreement candidates using\ntwo CADx classifiers trained on complementary distributions (DLCS24-CADxr50SWS and LUNA25-\nCADxr50); candidates with an averaged $CADx ≥ 0.10$ are promoted (confidence = 0.5). Stage 3 retains\nremaining candidates meeting $CADe ≥ 0.20$ (confidence = 0.2), yielding a single merged candidate list\nwith tiered confidence intended to reduce annotator workload while preserving sensitivity; an optional\nrule-based NLP module can link report-derived descriptors to candidates when radiology reports are\navailable.\n\n\n\n\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://github.com/fitushar/TriAnnot/blob/main/assert/WorkflowDiagram.png\" alt=\"Triannot_lworkflow\" width=\"800\"\u003e\n\u003c/p\u003e\n\n\n**Below candidate review panel for SAMPLE_0124 (68-year-old; Intgmultiomics cohort, SAMPLE_0124.nii).**\nThe leftmost tile is the dataset-provided ground-truth nodule; the remaining tiles are additional candidates proposed by our pipeline. Each tile shows the axial CT slice (left) and a magnified ROI (right); the yellow square marks the candidate location. The header above each tile reports ANod (annotation-consensus score), CADx (malignancy probability), CADe (detector confidence), Lrg.ax (largest axis, mm), lobar location, and slice index. Frame color follows the cancer-risk scale shown in the bottom bar (\u003c0.25, ≥0.25, ≥0.50, ≥0.75).\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://github.com/fitushar/TriAnnot/blob/main/assert/SAMPLE_0124_candidates.png\" alt=\"SAMPLE_0124_candidates\" width=\"1200\"\u003e\n\u003c/p\u003e\n\n\n\n## 🚀 Updates\n\n- **[1] 09/30/2025** - 📢 Created Github and Huggingface repo\n- **[2] 28/01/2025** - 📂 Mnauscript (Pre-print) [![arXiv](https://img.shields.io/badge/arXiv-2405.04605-\u003ccolor\u003e.svg)](https://arxiv.org/pdf/2601.19380)\n- **[3]** - 📂 Public release of **19K NLST CT Annotations** ![Coming Soon](https://img.shields.io/badge/Status-Coming%20Soon-orange).\n- **[4]** - 📂 Public release of **CT RATE Validation Dataset Annotations** ![Coming Soon](https://img.shields.io/badge/Status-Coming%20Soon-orange).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffitushar%2Ftriannot","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffitushar%2Ftriannot","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffitushar%2Ftriannot/lists"}