Bootstrapped Physically-Primed Neural Networks for Robust T2 Distribution Estimation in Low-SNR Pancreatic MRI

Hadas Ben Atya; Nicole Abramenkov; Noa Mashiah; Luise Brock; Daphna Link Sourani; Ram Weiss; Moti Freiman

cs.LGMar 14, 2026

Bootstrapped Physically-Primed Neural Networks for Robust T2 Distribution Estimation in Low-SNR Pancreatic MRI

Authors: Hadas Ben Atya, Nicole Abramenkov, Noa Mashiah, Luise Brock, Daphna Link Sourani, Ram Weiss, Moti Freiman

Organizations: Faculty of Biomedical Engineering, Technion – Israel Institute of Technology, Haifa, Israel · Pattern Recognition Lab, Friedrich-Alexander-Universität, Erlangen, Germany. · The May-Blum-Dahl MRI Research Center, Faculty of Biomedical Engineering, Technion- IIT, Haifa, Israel · Department of Pediatrics A, Rambam Healthcare Campus, Haifa, Israel

Abstract

Estimating multi-component T2 relaxation distributions from Multi-Echo Spin Echo (MESE) MRI is a severely ill-posed inverse problem, traditionally solved using regularized non-negative least squares (NNLS). In abdominal imaging, particularly the pancreas, low SNR and residual uncorrelated noise challenge classical solvers and deterministic deep learning models. We introduce a bootstrap-based inference framework for robust distributional T2 estimation that performs stochastic resampling of the echo train and aggregates predictions across multiple subsets. This treats the acquisition as a distribution rather than a fixed input, yielding variance-reduced, physically consistent estimates and converting deterministic relaxometry networks into probabilistic ensemble predictors. Applied to the P2T2 architecture, our method uses inference-time bootstrapping to smooth noise artifacts and enhance fidelity to the underlying relaxation distribution. Noninvasive pancreatic evaluation is limited by location and biopsy risks, highlighting the need for biomarkers capable of capturing early pathophysiological changes. In type 1 diabetes (T1DM), progressive beta-cell destruction begins years before overt hyperglycemia, yet current imaging cannot assess early islet decline. We evaluate clinical utility via a test-retest reproducibility study (N=7) and a T1DM versus healthy differentiation task (N=8). Our approach achieves the lowest Wasserstein distances across repeated scans and superior sensitivity to physiology-driven shifts in the relaxation-time distribution, outperforming NNLS and deterministic deep learning baselines. These results establish inference-time bootstrapping as an effective enhancement for quantitative T2 relaxometry in low-SNR abdominal imaging.

Figures & tables

Figure 1: Representative $T_{2}$ distribution estimation workflow (Control Subject). Left: Axial MRI slice (TE=77.4 ms) with the pancreatic ROI centroid indicated. Center: Signal decay analysis: The model accurately fits the physical decay curve ( $R^{2}=0.986$ ), matching the predicted signal (line) to the observed echoes (dots). Right: Regional $T_{2}$ distribution analysis. Faint colored curves show the final bootstrapped $T_{2}$ distributions for individual pixels within the ROI, illustrating local spatial heterogeneity. The solid black curve denotes the spatially averaged distribution across the ROI. Dashed lines depict the Gaussian decomposition of this average into Short- $T_{2}$ (red) and Long- $T_{2}$ (blue) components.

Figure 2: Comparison of the evaluated model architectures. The baseline MIML directly maps signals to $T_{2}$ distributions; P2T2 incorporates the explicit TE encoding; and the proposed Bootstrapped-P2T2 adds inference-time resampling and ensemble averaging to improve robustness and stability.

Figure 3: Test–retest stability across anatomical regions. Boxplots show the Wasserstein distance ( $W_{1}$ ) between repeated scans for the pancreatic body and tail. The proposed Bootstrapped-P2T2 model (red) exhibits consistently lower median error and reduced variance compared with the deterministic P2T2 (green) and baseline MIML (blue), demonstrating improved robustness and repeatability across both regions.

Model / Metric	AUC $\uparrow$	Hellinger $\uparrow$	KS p-value $\downarrow$
MIML	0.823	0.287	$2.36\times 10^{-3}$
MIML Ensemble	0.794	0.246	$8.30\times 10^{-3}$
P2T2	0.693	0.237	$1.14\times 10^{-1}$
Bootstrapped-P2T2	0.800	0.427	$\mathbf{4.79\times 10^{-4}}$
Scalar T2 (Least Squares)	0.629	0.244	$9.95\times 10^{-2}$
Scalar M0 (Least Squares)	0.632	0.124	$1.37\times 10^{-1}$

Table 1: Evaluation of separation capability. Bootstrapped-P2T2 achieves the strongest statistical significance (lowest p-value) and separation (Hellinger), outperforming all baselines.

Panel of Figure 4 — Figure 4: Sensitivity analysis across models (Pancreas Body & Tail). (a) The combined Wasserstein distance plot compares all distribution-based models. The Bootstrapped-P2T2 model (far right in a) shows the distinct separation between T1DM (orange) and Controls (blue), reducing the overlap seen in other models. (b–c) Classical scalar metrics ( $T_{2}$ and $M_{0}$ ) exhibit larger overlaps between groups, highlighting the improved sensitivity gained from the full-distribution modeling in (a).

Panel of Figure 5 — Figure 5: Representative response to glucose challenge in the pancreatic tail, using the Bootstrapped-P2T2. Left: Healthy Control subject. Right: T1DM subject. Top Row: Axial MRI (10th echo) with the pancreatic tail segmentation overlaid in red. Middle Row: Average $T_{2}$ distributions ( $\bar{p}(T_{2})$ ) within the ROI before (blue) and after (orange) glucose intake. Bottom Row: Cumulative Distribution Functions (CDFs) highlighting the gap between timepoints. Note the significantly larger distributional shift in the T1DM subject compared to the stable profile of the control, indicating an altered microstructural response to metabolic stress.

Panel of Figure 6 — Figure 6: Sensitivity of Test-Retest Reliability to Bootstrap Subset Size ( $M$ ). Boxplots showing the Wasserstein distance ( $W_{1}$ ) between repeated scans for varying subset sizes $M\in\{14,16,20,24\}$ . The performance remains stable across all configurations, demonstrating that the method’s robustness is not sensitive to small variations in the resampling fraction.

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Parameter	Value
Scanner Field Strength	3.0 T
Sequence Type	Radial Multi-Echo Spin Echo (MESE)
Number of Echoes	32
Echo Spacing ( $\Delta$ TE)	7.9 ms (Test-retest) / 7.74 ms (Diabetes analysis)
Field of View (FOV)	$360\times 360$ mm
Acquisition Matrix	$208\times 208$

Appendix

Table 2: Detailed acquisition parameters derived from the image metadata and protocol.

Component Label	Biophysical Proxy	$T_{2}$ Mean Range (ms)	$T_{2}$ Std Range (ms)
Myelin	Macromolecular / Fibrosis	$[15,30]$	$[0.1,5]$
Intra-Cellular (IS)	Parenchyma (Short)	$[50,120]$	$[0.1,12]$
Extra-Cellular (ES)	Parenchyma (Long)	$[50,120]$	$[0.1,12]$
Gray Matter (GM)	Edema / Inflammation	$[60,300]$	$[0.1,12]$
Pathology	Severe Edema / Lesions	$[300,1000]$	$[0.1,5]$
CSF	Fluid / Cysts / Ducts	$[1000,2000]$	$[0.1,5]$

Appendix

Table 3: Parameter ranges used for EPG-based synthetic training data generation. The network was trained on random mixtures of these components (using Dirichlet distributions) to learn the inverse mapping for any continuous

T_{2}

distribution within the

1-2000

ms range.

Magnetic Resonance Imaging

Magnetic resonance imaging uses magnetic fields and radio waves to create images of anatomy and tissue function for research and clinical care.

See all 237 papers

CrossPan: A Comprehensive Benchmark for Cross-Sequence Pancreas MRI Segmentation and Generalization
Apr 20, 2026Linkai Peng, Cuiling Sun, Zheyuan Zhang +10Image Segmentation Magnetic Resonance Imaging
Department of Radiology, Northwestern University, Chicago, USA. · Department of Electrical and Computer Engineering, Northwestern University, Evanston, USA. · Department of Computer Science, Northwestern University, Evanston, USA. +4
Beyond MSE: Rician Likelihood Denoising for Self-Supervised Cardiac $T2$ and $T1ρ$ MRI
Sep 24, 2026Nicholas A. Jacobs, Jason Mendes, Ravi Ranjan +2Self-Supervised Image Denoising Magnetic Resonance Imaging
University of Utah, Salt Lake City UT 84112, USA
PRIME-SVR: Physics-infoRmed Implicit Multi-Echo Slice-to-Volume Reconstruction for Fetal T2 mapping
Jul 22, 2026Busra Bulut, Maik Dannecker, Thomas Sanchez +14Implicit Neural Representations Image Reconstruction
Department of Medical Radiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland · CIBM Center for Biomedical Imaging, Lausanne, Switzerland · Chair for AI in Healthcare and Medicine, Technical University of Munich (TUM) and TUM University Hospital, Munich, Germany +6

Apr 20, 2026J/K move · Enter open · S save

CrossPan: A Comprehensive Benchmark for Cross-Sequence Pancreas MRI Segmentation and Generalization

Linkai Peng, Cuiling Sun, Zheyuan Zhang, Wanying Dou+9

Department of Radiology, Northwestern University, Chicago, USA. · Department of Electrical and Computer Engineering, Northwestern University, Evanston, USA. · Department of Computer Science, Northwestern University, Evanston, USA.+4

Image Segmentation Magnetic Resonance Imaging Medical Image Segmentation 3D Medical Image Segmentation Medical Image Benchmarks

Open paper AskPDF arXiv

Automatic pancreas segmentation is fundamental to abdominal MRI analysis, yet deep learning models trained on one MRI sequence often fail catastrophically when applied to another-a challenge that has received little systematic investigation. We introduce CrossPan, a multi-institutional benchmark comprising 1,386 3D scans across three routinely acquired sequences (T1-weighted, T2-weighted, and Out-of-Phase) from eight centers. Our experiments reveal three key findings. First, cross-sequence domain shifts are far more severe than cross-center variability: models achieving Dice scores above 0.85 in-domain collapse to near-zero (<0.02) when transferred across sequences. Second, state-of-the-art domain generalization methods provide negligible benefit under these physics-driven contrast inversions, whereas foundation models like MedSAM2 maintain moderate zero-shot performance through contrast-invariant shape priors. Third, semi-supervised learning offers gains only under stable intensity distributions and becomes unstable on sequences with high intra-organ variability. These results establish cross-sequence generalization-not model architecture or center diversity-as the primary barrier to clinically deployable pancreas MRI segmentation. Dataset and code are available at https://crosspan.netlify.app/.

Abstract

Magnetic Resonance Imaging

Explore similar work

CrossPan: A Comprehensive Benchmark for Cross-Sequence Pancreas MRI Segmentation and Generalization

Beyond MSE: Rician Likelihood Denoising for Self-Supervised Cardiac T2T2T2 and T1ρT1ρT1ρ MRI

PRIME-SVR: Physics-infoRmed Implicit Multi-Echo Slice-to-Volume Reconstruction for Fetal T2 mapping

Beyond MSE: Rician Likelihood Denoising for Self-Supervised Cardiac $T2$ and $T1ρ$ MRI