arXiv:2611.01790 · v1

Detection Instead of Inversion: T1-T2 Microstructure Quantification With Detection Transformers

首次提交 2026-11-01 18:50

版本更新 2026-11-01 18:50

雷达观测 2026-11-04 23:43

摘要

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: github.com/SebastianEndtTHI/t1t2-detr

作者备注：4 pages, 3 figures, 1 table; For submission to IEEE ISBI 2027; Code: https://github.com/SebastianEndtTHI/t1t2-detr