AnatomIQ: An Open-Source Toolkit for Automated Background Detection in Medical Imaging

Abstract

Manual background selection for contrast-to-noise ratio (CNR) calculations in CT image quality assessment is time-consuming, operator-dependent, and compromises reproducibility. Advanced metrics such as Noise Power Spectrum (NPS) and Task Transfer Function (TTF) traditionally require dedicated phantom acquisitions, adding cost, radiation exposure, and workflow disruption. We developed AnatomIQ, an open-source Python toolkit that automates background detection and performs phantom-free NPS and TTF analysis directly on patient anatomy. Automated background detection uses tissue-specific Hounsfield unit thresholding and morphological filtering, paired with a web interface for click-to-select lesion identification from PACS screenshots. Reported metrics include CNR, signal-to-noise ratio, detectability indices, and dose-normalized figures of merit with automated optimization recommendations. NPS quantifies noise texture from automatically detected uniform tissue regions, while TTF leverages natural circular anatomical structures (e.g., trachea, vessels) as edge phantoms, together characterizing the resolution-noise trade-off without dedicated phantom scans. Analysis takes 2-3 minutes per case, with CNR computed in under 10 seconds and NPS/TTF available on demand. Automated detection reliably identified valid regions across anatomical sites, including head-and-neck scans, a near-worst-case test of uniform-region availability. Both NPS and TTF pipelines were validated against phantom-derived references, confirming that in vivo measurements reflect genuine anatomical texture and resolution rather than pipeline artifacts. By eliminating operator variability and phantom requirements, AnatomIQ enables practical continuous quality monitoring and evidence-based reconstruction optimization. The toolkit is open-source, with optional commercial licensing for academic and clinical use.

MyTm: An Automated Melting Temperature Calculation Toolkit
Y. S. Huang, H. X. Song, Y. Sun +7
arXiv30 Sep 2026PreprintarXiv licenceFull textPhysical chemistry Applied physics & instrumentationarXiv
Domain Adaptation against Background Sculpting in Anomaly Detection at the LHC
Vincent Benne, Marie Hein, Michael Krämer +3
arXiv15 Sep 2026PreprintCC BY 4.0Full textHigh-energy & particle physicsarXiv
Using Geometric Deep Learning for the Detection of the Diffuse Supernova Neutrino Background in Water-Cherenkov Detectors
Matthieu Melennec, Andrew D Santos, Thomas Mueller +1
HAL8 Oct 2026PreprintCC BY 4.0Full textHigh-energy & particle physicsHALarXiv
Detection and Characterization of the Cosmological Neutrino Background by EPR Spectroscopy on Molecular Hydrino with Implications for Telecommunications
Wilfred R. Hagen, Randell L. Mills
ChemRxiv12 Oct 2026PreprintCC BYFull textAtomic, molecular & optical physicsChemRxiv
Automated CR-39 pit detection for energy and angular characterization of laser-driven ion beams
Wei Lin, Tzu-Yao Huang, Shih-Fan Yang +10
arXiv28 Oct 2026PreprintCC BY 4.0Full textApplied physics & instrumentation Plasma physicsarXiv

Cite

BibTeX RIS

BibTeX

@misc{carballeira2026anatomiq,
  title = {{AnatomIQ: An Open-Source Toolkit for Automated Background Detection in Medical Imaging}},
  author = {Rafael Carballeira and Hayley A. Cash and Marthony L. Robins},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.01686},
  eprint = {2610.01686},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.01686},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - AnatomIQ: An Open-Source Toolkit for Automated Background Detection in Medical Imaging
AU  - Rafael Carballeira
AU  - Hayley A. Cash
AU  - Marthony L. Robins
PY  - 2026
DA  - 2026/10/01
PB  - arXiv
DO  - 10.48550/arxiv.2610.01686
UR  - https://arxiv.org/abs/2610.01686
AB  - Manual background selection for contrast-to-noise ratio (CNR) calculations in CT image quality assessment is time-consuming, operator-dependent, and compromises reproducibility. Advanced metrics such as Noise Power Spectrum (NPS) and Task Transfer Function (TTF) traditionally require dedicated phantom acquisitions, adding cost, radiation exposure, and workflow disruption. We developed AnatomIQ, an open-source Python toolkit that automates background detection and performs phantom-free NPS and TTF analysis directly on patient anatomy. Automated background detection uses tissue-specific Hounsfield unit thresholding and morphological filtering, paired with a web interface for click-to-select lesion identification from PACS screenshots. Reported metrics include CNR, signal-to-noise ratio, detectability indices, and dose-normalized figures of merit with automated optimization recommendations. NPS quantifies noise texture from automatically detected uniform tissue regions, while TTF leverages natural circular anatomical structures (e.g., trachea, vessels) as edge phantoms, together characterizing the resolution-noise trade-off without dedicated phantom scans. Analysis takes 2-3 minutes per case, with CNR computed in under 10 seconds and NPS/TTF available on demand. Automated detection reliably identified valid regions across anatomical sites, including head-and-neck scans, a near-worst-case test of uniform-region availability. Both NPS and TTF pipelines were validated against phantom-derived references, confirming that in vivo measurements reflect genuine anatomical texture and resolution rather than pipeline artifacts. By eliminating operator variability and phantom requirements, AnatomIQ enables practical continuous quality monitoring and evidence-based reconstruction optimization. The toolkit is open-source, with optional commercial licensing for academic and clinical use.
ER  -

Abstract

Related

Cite