flair-to-t1-mri-synthesis

FLAIR → T1 MRI Synthesis with Explainable Residual GANs

What this solves

In clinical MRI workflows, a patient may have a FLAIR scan but not a T1-weighted scan — re-acquiring is costly, time-consuming, or sometimes impossible. This model synthesises a high-fidelity T1-weighted image directly from a FLAIR scan using a conditional GAN, eliminating the need for an additional acquisition.

Beyond synthesis quality, existing models are black boxes. We embed Grad-CAM into the generator, producing voxel-level saliency maps that show which FLAIR regions drove each T1 synthesis — making the model usable in interpretability-sensitive settings.

---

Output

---

Architecture

7-component generator loss:

$$\mathcal{L}G = \mathcal{L}{adv} + 10\mathcal{L}{L1} + 10\mathcal{L}{MS\text{-}SSIM} + 10\mathcal{L}{percep} + 10\mathcal{L}{feat} + 20\mathcal{L}{edge} + 5\mathcal{L}{contrast}$$

Edge loss ($\lambda=20$) combines Sobel + Laplacian at two scales to preserve anatomical boundaries. Perceptual loss uses VGG19 at relu1_2, relu2_2, relu3_4.

---

Results

BraTS 2021 held-out test — 251 subjects

BraTS 2023 GLI external validation — 219 subjects (unseen distribution)

95% CIs via bootstrap resampling (1,000 iterations).

vs. baselines (same train/test split, BraTS 2021)

5× fewer parameters than Pix2Pix, +12% SSIM and −29% MAE over CycleGAN.

---

Training evolution

All 6 versions are in this repo under resnet9/v1/ → resnet9/v6/.

Trained on NVIDIA L4 · 600 cumulative epochs · 4.11 hours · mixed precision FP16/FP32.

---

Usage

from huggingface_hub import hf_hub_download
import torch

# Load V6 — best model
path = hf_hub_download(
    repo_id="atchusg/flair-to-t1-mri-synthesis",
    filename="resnet9/v6/generator.pth"
)

# Instantiate architecture (copy models.py from GitHub)
from models import ResNet9Generator

gen = ResNet9Generator(in_channels=3, out_channels=3)
gen.load_state_dict(torch.load(path, map_location="cpu"))
gen.eval()

# Inference
# flair: torch.Tensor of shape (B, 3, 256, 256), values in [-1, 1]
with torch.no_grad():
    synthetic_t1 = gen(flair)

Code & training scripts: GitHub

---

Repo structure

resnet9/
  v1/ → v6/
    generator.pth          # Generator weights only (11.4M params)
    training_report.json   # Full metrics, hyperparams, CI
baselines/
  pix2pix/
  cyclegan/
  attentiongan/
    generator.pth
    training_report.json