Metraipolis › archive › dc_94004d2dcfc8
Detection Instead of Inversion: T1-T2 Microstructure Quantification With Detection Transformers — arXiv:2611.01790
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01790
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:40:34.151Z
- SHA-256 of the archived text
d087174b0601a08bdd7cd231f52813bdec0b79057fdd80a49d001725ff6bf773- Stable URL of this page
https://metraipolis.com/documento/dc_94004d2dcfc8
How to cite
Detection Instead of Inversion: T1-T2 Microstructure Quantification With Detection Transformers — arXiv:2611.01790 — arXiv (en), https://arxiv.org/abs/2611.01790 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_94004d2dcfc8 (Metraipolis archive dc_94004d2dcfc8, sha256 d087174b0601a08bdd7cd231f52813bdec0b79057fdd80a49d001725ff6bf773)
BibTeX
@misc{dc94004d2dcfc8,
title = {Detection Instead of Inversion: T1-T2 Microstructure Quantification With Detection Transformers — arXiv:2611.01790},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01790},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_94004d2dcfc8; sha256 d087174b0601a08bdd7cd231f52813bdec0b79057fdd80a49d001725ff6bf773},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01790. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
T1-T2 correlation MRI has strong potential to quantify microstructural compartments without imposing a biological model. Traditionally, full T1-T2 spectra per voxel are reconstructed with an ill-conditioned and time-consuming Inverse Laplace Transform. We propose to view this challenge as an object detection task: A Detection Transformer (DETR) takes 64 TI/TE signals and directly predicts a set of compartments specified by T1, T2, and signal fraction. We achieve a mean average precision mAP@10 of 76.8% on simulated data, outperforming both our previous model design (53.8%) and regularized NNLS (66.1%). We show that our DETR approach outperforms NNLS in almost every setting across compartment count, compartmental signal fraction, and SNR. Reconstruction is orders of magnitude faster than NNLS. The results are fully reproducible from our public code: this http URL Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG); Medical Physics (physics.med-ph). Pagina del lavoro: https://arxiv.org/abs/2611.01790 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T18:12:54.744Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).