Update README.md

README.md

@@ -1,59 +1,96 @@
 
 Model Card Template
+
 Date effective: March 2026
+
 Owner: ORA, Internal Policy & Practice 
+
 INSTRUCTIONS: Create a copy of this template for your model. CELA frontline approval is required before publication.
+
 Model summary
+
 Developer	Microsoft Research, Health Futures
+
 Description	PSIRNet accelerates PSIR LGE cardiac MR imaging by eightfold or more while preserving diagnostic image quality.
+
 Model architecture	This model is an instantiation of the variational network architecture (an unrolled method used to solve inverse problems).
+
 Parameters	•	PSIRNet: 845 million trainable parameters
+
 Inputs	Inputs to model are four 4D tensors [B, C, H, W] for batch, channel, height and width. 
+
 Context length	Not applicable
+
 Outputs	Output tensor is in the shape of [B, C, H, W].
+
 GPUs	64x MI300x
+
 Training time	7 days
+
 Public data summary (or summaries)	Not applicable
+
 Dates	Aug 2025
+
 Status	Jan 2018 - Dec 2020
+
 Release date
+
 Release date in the EU (if different)	Mar 2026 
+
 License	MIT license
+
 Model dependencies:	N/A
+
 List and link to any additional related assets	N/A
+
 Acceptable use policy	N/A
  
 1. Model overview
 PSIRNet is a physics-guided, end-to-end deep learning reconstruction model for free-breathing late gadolinium enhancement (LGE) cardiac MRI that produces a phase-sensitive inversion recovery (PSIR) image (with surface coil correction) from a single interleaved inversion-recovery/proton-density (IR/PD) acquisition, replacing the typical MOCO PSIR workflow that relies on 8–24 averages.
+
 1.1 Alignment approach
 This model was trained from scratch and did not require an alignment step.
+
 2. Usage
+
 2.1 Primary use cases
 This model is only suited to reconstruct PSIR LGE cardiac MR images.
+
 2.2 Out-of-scope use cases
 This model shall not be used for any out-of-scope use cases.
+
 2.3 Distribution channels
 Model source code is available at https://github.com/microsoft/psirnet
 Pre-trained models are available at https://huggingface.co/microsoft/psirnet
+
 2.4 Input formats
 Inputs to model are four 4D tensor [B, C, H, W] for batch, channel , height and width. 
+
 2.5 Technical requirements and integration guidance
 Recommend GPU should have >=16GB memory. NVIDIA A100 or newer GPUs are the best.
+
 2.6 Responsible AI considerations
 This model is for the very dedicated using scenario. Only domain experts with good knowledge of MR imaging should deploy the model. No explicit responsible AI considerations are involved.
+
 3. Data overview
+
 3.1 Training, testing, and validation datasets
 Data from the National Institutes of Health Cardiac MRI Raw Data Repository, hosted by the Intramural Research Program of the National Heart Lung and Blood Institute, were curated with the required ethical and/or secondary audit use approvals or guidelines permitting the retrospective analysis of anonymized data without requiring written informed consent for secondary usage for the purpose of technical development, protocol optimization, and/or quality control. The data was fully anonymized and used for training without exclusion. Data were split on a per-patient basis to prevent leakage in network training: all slices from a given patient were assigned to a single partition—640,000 slices (42,822 patients) for training, the remainder 160,653 slices (13,095 patients) for validation and testing—with no patient overlap across splits.
+
 4. Quality and performance evaluation
 The model was evaluated quantitatively on an external test set using image-similarity metrics (SSIM, PSNR, and NRMSE). Qualitative analysis was performed by two expert cardiologists using a 5-point Likert scale. 
+
 4.1 Long context
 Not relevant
 
 4.2 Safety evaluation and red-teaming
 Model outputs were compared to clinical target images. The standard quality metrics were computed.
+
 5. Tracked capability evaluations
 This model is not a frontier model.
+
 6. Requests for additional information may be directed to MSFTAIActRequest@microsoft.com.  
+
 7. Appendix
 None