Upload app.py with huggingface_hub

app.py

@@ -3,6 +3,7 @@ BrainConnect-ASD — Scanner-site-invariant ASD detection from fMRI.
 """
 from __future__ import annotations
 
+import io
 from pathlib import Path
 
 import numpy as np
@@ -68,12 +69,92 @@ def get_models():
         _models.append((site, task))
     return _models
 
+# ── gradient saliency ──────────────────────────────────────────────────────
+
+def _compute_saliency(bw_t: torch.Tensor, adj_t: torch.Tensor, models) -> np.ndarray:
+    """Gradient of p(ASD) w.r.t. adjacency matrix, averaged over ensemble."""
+    maps = []
+    for _, task in models:
+        adj = adj_t.clone().requires_grad_(True)
+        logits = task.model(bw_t, adj)
+        p = torch.softmax(logits, -1)[0, 1]
+        p.backward()
+        maps.append(adj.grad[0].abs().detach().numpy())
+    sal = np.mean(maps, axis=0)        # (200, 200)
+    sal = (sal + sal.T) / 2            # symmetrize
+    return sal
+
+
+def _saliency_figure(sal: np.ndarray, p_mean: float):
+    import matplotlib
+    matplotlib.use("Agg")
+    import matplotlib.pyplot as plt
+    from PIL import Image
+
+    thresh  = np.percentile(sal, 95)
+    sal_top = np.where(sal >= thresh, sal, 0.0)
+
+    roi_imp = sal.sum(1)
+    top20   = roi_imp.argsort()[-20:][::-1]
+
+    verdict_color = (
+        "#e63946" if p_mean > 0.6 else
+        "#2dc653" if p_mean < 0.4 else
+        "#f4a261"
+    )
+
+    fig, axes = plt.subplots(1, 2, figsize=(14, 5.5))
+    fig.patch.set_facecolor("#0d0d0d")
+
+    # ── Left: FC edge saliency heatmap ──
+    ax = axes[0]
+    ax.set_facecolor("#111")
+    im = ax.imshow(sal_top, cmap="inferno", aspect="auto", interpolation="nearest")
+    ax.set_title("FC Edge Saliency  (top 5% connections)", color="#ccc", fontsize=11, pad=10)
+    ax.set_xlabel("ROI index", color="#777", fontsize=9)
+    ax.set_ylabel("ROI index", color="#777", fontsize=9)
+    ax.tick_params(colors="#555", labelsize=8)
+    cb = plt.colorbar(im, ax=ax, fraction=0.046, pad=0.04)
+    cb.ax.yaxis.set_tick_params(color="#555", labelsize=7)
+    plt.setp(cb.ax.yaxis.get_ticklabels(), color="#666")
+    for spine in ax.spines.values():
+        spine.set_color("#333")
+
+    # ── Right: top-20 ROI importance bar chart ──
+    ax2 = axes[1]
+    ax2.set_facecolor("#111")
+    ax2.barh(
+        range(20), roi_imp[top20],
+        color=verdict_color, alpha=0.75, edgecolor="none",
+    )
+    ax2.set_yticks(range(20))
+    ax2.set_yticklabels([f"ROI {i:03d}" for i in top20], fontsize=8, color="#ccc")
+    ax2.set_xlabel("Cumulative gradient magnitude", color="#777", fontsize=9)
+    ax2.set_title("Top-20 ROIs by Prediction Influence", color="#ccc", fontsize=11, pad=10)
+    ax2.tick_params(colors="#555", labelsize=8)
+    ax2.invert_yaxis()
+    for spine in ["top", "right"]:
+        ax2.spines[spine].set_visible(False)
+    for spine in ["bottom", "left"]:
+        ax2.spines[spine].set_color("#333")
+
+    fig.suptitle(
+        f"Gradient Saliency  ·  p(ASD) = {p_mean:.3f}  ·  Ensemble of {len(_models)} LOSO models",
+        color="#888", fontsize=10, y=1.02,
+    )
+
+    plt.tight_layout()
+    buf = io.BytesIO()
+    plt.savefig(buf, format="png", dpi=120, bbox_inches="tight", facecolor="#0d0d0d")
+    plt.close(fig)
+    buf.seek(0)
+    return Image.open(buf).copy()
+
 # ── inference ──────────────────────────────────────────────────────────────
 
-@torch.no_grad()
-def run_gcn(file_path: str | None) -> tuple[str, str, str]:
+def run_gcn(file_path: str | None):
     if file_path is None:
-        return "", "", ""
+        return "", "", "", None
 
     path = Path(file_path)
     try:
@@ -92,23 +173,33 @@ def run_gcn(file_path: str | None) -> tuple[str, str, str]:
         else:
             bold = np.loadtxt(path, dtype=np.float32)
             if bold.ndim != 2 or bold.shape[1] != 200:
-                return f"⚠️ Error: expected (T×200) array, got {bold.shape}", "", ""
+                return f"⚠️ Error: expected (T×200) array, got {bold.shape}", "", "", None
             bw_t, adj_t = preprocess(bold)
     except Exception as e:
-        return f"⚠️ Error loading file: {e}", "", ""
+        return f"⚠️ Error loading file: {e}", "", "", None
 
     models = get_models()
+
+    # ── Ensemble inference (no grad) ──
     per_model = []
-    for site, task in models:
-        logits = task(bw_t, adj_t)
-        p = torch.softmax(logits, -1)[0, 1].item()
-        per_model.append((site, p))
+    with torch.no_grad():
+        for site, task in models:
+            logits = task(bw_t, adj_t)
+            p = torch.softmax(logits, -1)[0, 1].item()
+            per_model.append((site, p))
 
     p_mean    = float(np.mean([p for _, p in per_model]))
     consensus = sum(1 for _, p in per_model if p > 0.5)
     conf      = max(p_mean, 1 - p_mean) * 100
 
-    # ── Verdict ──
+    # ── Gradient saliency ──
+    try:
+        sal = _compute_saliency(bw_t, adj_t, models)
+        sal_img = _saliency_figure(sal, p_mean)
+    except Exception:
+        sal_img = None
+
+    # ── Verdict card ──
     if p_mean > 0.6:
         verdict = f"""<div style="background:#1a1a2e;border-left:6px solid #e63946;padding:24px 28px;border-radius:12px;margin-bottom:8px">
 <div style="font-size:2rem;font-weight:800;color:#e63946;letter-spacing:1px">ASD INDICATED</div>
@@ -183,14 +274,14 @@ def run_gcn(file_path: str | None) -> tuple[str, str, str]:
 <span style="color:#444;margin-top:6px;display:block">Clinical report generation: Qwen2.5-7B fine-tuned on AMD Instinct MI300X (coming soon)</span>
 </div></div>"""
 
-    return verdict, ensemble, report
+    return verdict, ensemble, report, sal_img
 
 
 # ── UI ─────────────────────────────────────────────────────────────────────
 
 css = """
 body { background: #0d0d0d; }
-.gradio-container { max-width: 900px; margin: auto; }
+.gradio-container { max-width: 960px; margin: auto; }
 """
 
 with gr.Blocks(title="BrainConnect-ASD", css=css, theme=gr.themes.Base()) as demo:
@@ -209,14 +300,21 @@ with gr.Blocks(title="BrainConnect-ASD", css=css, theme=gr.themes.Base()) as dem
 
     file_input = gr.File(label="Upload CC200 fMRI file (.1D or .npz)", type="filepath")
 
-    verdict_html   = gr.HTML()
-    ensemble_html  = gr.HTML()
-    report_html    = gr.HTML()
+    verdict_html  = gr.HTML()
+    ensemble_html = gr.HTML()
+
+    with gr.Row():
+        report_html = gr.HTML()
+
+    gr.HTML("<div style='color:#888;font-size:0.8rem;text-transform:uppercase;letter-spacing:2px;margin:24px 0 8px'>Gradient Saliency — which brain connections drove this prediction</div>")
+    saliency_img = gr.Image(label="FC Edge Saliency & ROI Importance", type="pil")
+
+    report_html2 = gr.HTML()
 
     file_input.change(
         fn=run_gcn,
         inputs=file_input,
-        outputs=[verdict_html, ensemble_html, report_html],
+        outputs=[verdict_html, ensemble_html, report_html2, saliency_img],
     )
 
     gr.HTML("""