rpotter6298
252 lines
9.4 KiB
Python
252 lines
9.4 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
validate_siamese.py — Validate the trained siamese network against Task06
|
|
held-out test patients.
|
|
|
|
Runs both connected-components and edge-ranking clustering (known K) on the
|
|
test set and reports metrics + assignment heatmaps.
|
|
|
|
Usage:
|
|
conda activate fundus_imaging
|
|
python scripts/clustering_validation/validate_siamese.py
|
|
python scripts/clustering_validation/validate_siamese.py --threshold 0.95 --tag v2
|
|
"""
|
|
|
|
import os, sys, json, argparse
|
|
import numpy as np
|
|
import matplotlib
|
|
matplotlib.use("Agg")
|
|
import matplotlib.pyplot as plt
|
|
|
|
os.environ["OMP_NUM_THREADS"] = "1"
|
|
os.environ["OPENBLAS_NUM_THREADS"] = "1"
|
|
os.environ["MKL_NUM_THREADS"] = "1"
|
|
|
|
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.dirname(
|
|
os.path.abspath(__file__)))))
|
|
from classes import SiamesePatientMatcher
|
|
from sklearn.metrics import adjusted_rand_score, normalized_mutual_info_score
|
|
|
|
ROOT = os.path.dirname(os.path.dirname(os.path.dirname(
|
|
os.path.abspath(__file__))))
|
|
MODELS_DIR = os.path.join(ROOT, "models")
|
|
RESULTS_DIR = os.path.join(ROOT, "results", "clustering_validation")
|
|
PLOTS_DIR = os.path.join(ROOT, "plots")
|
|
PNG_DIR = os.path.join(ROOT, "features", "task06_pngs", "test")
|
|
VOLUME_DIR = os.path.join(os.path.dirname(ROOT), "Task06_Lung", "imagesTr")
|
|
SEED = 42
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Helpers
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def cluster_purity_stats(y_true, y_pred):
|
|
purities = []
|
|
overall_correct = 0
|
|
for c in np.unique(y_pred):
|
|
mask = y_pred == c
|
|
_, counts = np.unique(y_true[mask], return_counts=True)
|
|
purities.append(counts.max() / mask.sum())
|
|
overall_correct += counts.max()
|
|
purities = np.array(purities)
|
|
return {
|
|
"overall": float(overall_correct / len(y_true)),
|
|
"median": float(np.median(purities)),
|
|
"mean": float(np.mean(purities)),
|
|
"frac_gt_70": float((purities > 0.7).mean()),
|
|
"frac_gt_90": float((purities > 0.9).mean()),
|
|
}
|
|
|
|
|
|
def patient_capture_stats(y_true, y_pred):
|
|
captures = []
|
|
for p in np.unique(y_true):
|
|
mask = y_true == p
|
|
p_clusters = y_pred[mask]
|
|
_, counts = np.unique(p_clusters, return_counts=True)
|
|
captures.append(counts.max() / mask.sum())
|
|
captures = np.array(captures)
|
|
return {
|
|
"median": float(np.median(captures)),
|
|
"mean": float(np.mean(captures)),
|
|
"frac_gt_50": float((captures > 0.5).mean()),
|
|
}
|
|
|
|
|
|
|
|
|
|
def score_manifest(manifest, y_true_map):
|
|
"""Score a manifest against ground-truth patient IDs."""
|
|
preds, truths = [], []
|
|
for pred_pid, fnames in manifest.items():
|
|
for f in fnames:
|
|
preds.append(pred_pid)
|
|
truths.append(y_true_map.get(f, f"unknown_{f}"))
|
|
y_true = np.array(truths)
|
|
y_pred = np.array(preds)
|
|
purity = cluster_purity_stats(y_true, y_pred)
|
|
capture = patient_capture_stats(y_true, y_pred)
|
|
ari = adjusted_rand_score(y_true, y_pred)
|
|
nmi = normalized_mutual_info_score(y_true, y_pred)
|
|
return {"ARI": ari, "NMI": nmi,
|
|
"cluster_purity": purity, "patient_capture": capture,
|
|
"y_true": y_true, "y_pred": y_pred}
|
|
|
|
|
|
def plot_assignment_matrix(y_true, y_pred, out_path, title):
|
|
true_patients = sorted(np.unique(y_true))
|
|
pred_clusters = sorted(np.unique(y_pred))
|
|
matrix = np.zeros((len(true_patients), len(pred_clusters)))
|
|
for i, p in enumerate(true_patients):
|
|
for j, c in enumerate(pred_clusters):
|
|
matrix[i, j] = ((y_true == p) & (y_pred == c)).sum()
|
|
matrix_norm = matrix / (matrix.sum(axis=1, keepdims=True) + 1e-8)
|
|
|
|
fig, ax = plt.subplots(figsize=(max(14, len(pred_clusters) * 0.22),
|
|
max(10, len(true_patients) * 0.18)))
|
|
cmap = plt.cm.YlOrRd.copy()
|
|
cmap.set_under('white')
|
|
im = ax.imshow(matrix_norm, aspect="auto", cmap=cmap, vmin=1e-6, vmax=1)
|
|
ax.set_xticks(range(len(pred_clusters)))
|
|
ax.set_xticklabels([f"c{c}" for c in pred_clusters], fontsize=6, rotation=90)
|
|
ax.set_yticks(range(len(true_patients)))
|
|
ax.set_yticklabels(true_patients, fontsize=7)
|
|
ax.set_xlabel("Predicted cluster"); ax.set_ylabel("True patient")
|
|
ax.set_title(title, fontsize=11)
|
|
plt.colorbar(im, ax=ax, label="Fraction of patient's slices")
|
|
plt.tight_layout()
|
|
os.makedirs(os.path.dirname(out_path), exist_ok=True)
|
|
plt.savefig(out_path, dpi=150)
|
|
plt.close()
|
|
print(f" Heatmap → {out_path}")
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Main
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def main():
|
|
ap = argparse.ArgumentParser()
|
|
ap.add_argument("--model", default=os.path.join(MODELS_DIR, "siamese_resnet18.pt"))
|
|
ap.add_argument("--backbone", default="resnet18")
|
|
ap.add_argument("--threshold", type=float, default=0.9)
|
|
ap.add_argument("--tag", default="", help="Append tag to output filenames")
|
|
ap.add_argument("--full", action="store_true",
|
|
help="Run on full NIfTI dataset (leaked training data).")
|
|
args = ap.parse_args()
|
|
tag = f"_{args.tag}" if args.tag else ""
|
|
|
|
os.makedirs(RESULTS_DIR, exist_ok=True)
|
|
os.makedirs(PLOTS_DIR, exist_ok=True)
|
|
|
|
# ---- Load test PNGs ----
|
|
if args.full:
|
|
tag = (tag or "") + "_full"
|
|
from classes import NiftiSliceDataset
|
|
VOL = os.path.join(os.path.dirname(ROOT), "Task06_Lung", "imagesTr")
|
|
ds = NiftiSliceDataset(VOL, random_slices=False, seed=SEED, rotate_deg=90)
|
|
ds.load_all_slices(stride=1)
|
|
# Export full PNGs to temp dir
|
|
import tempfile
|
|
tmpdir = tempfile.mkdtemp(prefix="task06_full_")
|
|
full_paths, full_pids, _ = ds.export_pngs(tmpdir)
|
|
test_paths = full_paths
|
|
test_pids = np.array(full_pids)
|
|
print(f" FULL dataset: {len(test_paths)} slices, {len(np.unique(test_pids))} patients")
|
|
print(f" (includes training data — leakage expected for siamese)")
|
|
else:
|
|
manifest_path = os.path.join(PNG_DIR, "manifest.json")
|
|
if not os.path.exists(manifest_path):
|
|
print(f"Test PNGs not found at {PNG_DIR}")
|
|
print("Run train_siamese.py first to generate the test set.")
|
|
sys.exit(1)
|
|
with open(manifest_path) as f:
|
|
png_manifest = json.load(f)
|
|
test_paths = png_manifest["paths"]
|
|
test_pids = np.array(png_manifest["patient_ids"])
|
|
|
|
# Short filenames for matching
|
|
test_fnames = [p.split("/")[-1].replace(".png", "") for p in test_paths]
|
|
y_true_map = {f: pid for f, pid in zip(test_fnames, test_pids)}
|
|
k = len(np.unique(test_pids))
|
|
|
|
print("=" * 60)
|
|
print(f"Siamese validation — held-out test set")
|
|
print("=" * 60)
|
|
print(f" {len(test_paths)} slices, {k} patients")
|
|
print(f" Model: {args.model}")
|
|
|
|
# ---- Load siamese model ----
|
|
print(f"\nLoading siamese model ...")
|
|
matcher = SiamesePatientMatcher(
|
|
args.model, backbone=args.backbone, input_size=224)
|
|
|
|
# ---- Connected components (no known K) ----
|
|
print(f"\n{'─'*50}")
|
|
print("Method 1: Connected components (threshold-based)")
|
|
print(f"{'─'*50}")
|
|
manifest_cc = matcher.identify_patients(
|
|
test_paths, filenames=test_fnames,
|
|
threshold=args.threshold, top_k=20, k=None)
|
|
|
|
# ---- Edge-ranking clustering (known K) ----
|
|
print(f"\n{'─'*50}")
|
|
print(f"Method 2: Edge-ranking clustering (k={k})")
|
|
print(f"{'─'*50}")
|
|
manifest_sc = matcher.identify_patients(
|
|
test_paths, filenames=test_fnames,
|
|
threshold=args.threshold, top_k=20, k=k)
|
|
|
|
# ---- Score both methods ----
|
|
results_cc = score_manifest(manifest_cc, y_true_map)
|
|
results_sc = score_manifest(manifest_sc, y_true_map)
|
|
|
|
print(f"\n{'='*60}")
|
|
print("RESULTS — Siamese patient identification")
|
|
print(f"{'='*60}")
|
|
print(f"\n{'Method':<30s} {'ARI':>7s} {'NMI':>7s} {' Purity Capture':>8s}")
|
|
print(f"{'':30s} {'':>7s} {'':>7s} {' (overall) (mean) ':>8s}")
|
|
print("-" * 60)
|
|
|
|
for name, r in [("Connected components", results_cc),
|
|
("Edge ranking (k=" + str(k) + ")", results_sc)]:
|
|
p = r["cluster_purity"]["overall"]
|
|
c = r["patient_capture"]["mean"]
|
|
print(f"{name:<30s} {r['ARI']:>7.3f} {r['NMI']:>7.3f} "
|
|
f"{p:>7.1%} {c:>7.1%}")
|
|
|
|
# ---- Save metrics ----
|
|
for suffix, r in [("cc", results_cc), ("sc", results_sc)]:
|
|
out = {k: v for k, v in r.items() if k not in ("y_true", "y_pred")}
|
|
out["method"] = suffix
|
|
out["threshold"] = args.threshold
|
|
out["n_patients"] = int(k)
|
|
out["n_slices"] = len(test_paths)
|
|
out_json = os.path.join(RESULTS_DIR, f"validate_siamese_{suffix}{tag}.json")
|
|
with open(out_json, "w") as f:
|
|
json.dump(out, f, indent=2)
|
|
print(f" Metrics → {out_json}")
|
|
|
|
# ---- Plot siamese methods ----
|
|
for name, r in [("connected_components", results_cc),
|
|
("edge_rank", results_sc)]:
|
|
p = r["cluster_purity"]["overall"]
|
|
c = r["patient_capture"]["mean"]
|
|
title = (f"Siamese Patient-Cluster Assignment ({name})\n"
|
|
f"(ARI={r['ARI']:.3f}, purity={p:.1%}, "
|
|
f"capture mean={c:.1%})")
|
|
plot_assignment_matrix(
|
|
r["y_true"], r["y_pred"],
|
|
os.path.join(PLOTS_DIR, "clustering_validation", "siamese",
|
|
f"assignment_matrix_{name}{tag}.png"),
|
|
title)
|
|
|
|
print("DONE")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|