Package: dicomtk.ai Title: AI Agents, MCP Tooling, and Clinical NLP for 'DICOM' Imaging Version: 0.2.0 Authors@R: c( person("Yee How", "Lau", email = "lauyeehow1986@gmail.com", role = c("aut", "cre", "cph"))) Description: Satellite Artificial Intelligence ('AI') and clinical natural language processing toolkit for 'dicomtk'. Provides 'ellmer'-based clinical imaging agents with unbypassable monotonic de-identification guardrails, a Model Context Protocol ('MCP') server via 'mcptools', a pluggable REST and offline backend registry for segmentation models ('TotalSegmentator' by Wasserthal et al. (2023) , 'nnU-Net', 'VISTA3D', and 'MedSAM2' by Ma et al. (2024) ), Integrating the Healthcare Enterprise AI Results ('IHE AIR') standardized 'DICOM SEG' and 'TID 1500' outputs, radiology report de-identification and weak-label extraction, 'RadLex' and 'LOINC-RSNA' protocol harmonisation, and 'DuckDB' vector similarity search. License: GPL (>= 2) URL: https://lauyeehow1986-hub.github.io/dicomtk.ai/, https://github.com/lauyeehow1986-hub/dicomtk.ai BugReports: https://github.com/lauyeehow1986-hub/dicomtk.ai/issues Depends: R (>= 4.1.0) Imports: dicomtk (>= 0.4.0), ellmer (>= 0.4.0), mcptools (>= 0.2.0), duckdb (>= 1.0.0), DBI (>= 1.2.0), httr2 (>= 1.0.0), curl, jsonlite (>= 1.8.0), tibble (>= 3.0.0), cli (>= 3.6.0), rlang (>= 1.1.0), stats, utils Suggests: testthat (>= 3.0.0), tesseract, withr, knitr, rmarkdown Encoding: UTF-8 LazyData: true Roxygen: list(markdown = TRUE) RoxygenNote: 7.3.3 VignetteBuilder: knitr Config/testthat/edition: 3 Config/pak/sysreqs: make libicu-dev libssl-dev zlib1g-dev Repository: https://lauyeehow1986-hub.r-universe.dev Date/Publication: 2026-11-14 15:26:17 UTC RemoteUrl: https://github.com/lauyeehow1986-hub/dicomtk.ai RemoteRef: main RemoteSha: bee54d8893066e26c656c28584e008778b96d055 NeedsCompilation: no Packaged: 2026-11-14 15:53:59 UTC; root Author: Yee How Lau [aut, cre, cph] Maintainer: Yee How Lau