Add scripts for patient classification and visualization

- Created `classification.py` for comparing image-level and patient-level classification results using various CNN models.
- Implemented `create_patient_groups.py` to extract features, generate PCA/t-SNE plots, and identify patient groups via K-means clustering.
- Added `figure6.py` to generate boxplots for test accuracy across multiple seeds.
- Developed `simple_patient_tsne.py` to perform t-SNE visualization of patient groups and save results in a manifest file.
- Introduced `simple_patient_manifest.csv` to store patient IDs, classes, image counts, and associated images.

classes/visualizations.py

@@ -0,0 +1,148 @@
+"""
+Visualization utilities for feature space exploration.
+
+PCA and t-SNE plots to inspect class separability in the
+extracted feature representations.
+"""
+
+import numpy as np
+import matplotlib
+matplotlib.use("Agg")
+import matplotlib.pyplot as plt
+from sklearn.decomposition import PCA
+from sklearn.manifold import TSNE
+
+
+def plot_pca_tsne(X, Y, legend_names=None, perplexity=35,
+                  random_state=42, output_path=None, figsize=(12, 5),
+                  dpi=150):
+    """Generate side-by-side PCA and t-SNE plots of feature vectors.
+
+    Parameters
+    ----------
+    X : np.ndarray of shape (n_samples, n_features)
+        Feature matrix (e.g. VGG16 outputs).
+    Y : np.ndarray of shape (n_samples,)
+        Class labels.
+    legend_names : dict, optional
+        Mapping from raw label -> display label, e.g.
+        {"Bengin cases": "Benign", ...}.
+    perplexity : int
+        t-SNE perplexity (default 35).
+    random_state : int
+        Seed for reproducibility.
+    output_path : str, optional
+        Path to save the figure. If None, saved as "pca_tsne.png".
+    figsize : tuple
+        Figure dimensions.
+    dpi : int
+        Output resolution.
+
+    Returns
+    -------
+    fig : matplotlib Figure
+    """
+    if legend_names is None:
+        legend_names = {}
+
+    n_samples, n_features = X.shape
+
+    # --- PCA: 50D → 2D ---
+    n_pca = min(50, n_samples - 1, n_features)
+    pca_pre = PCA(n_components=n_pca, random_state=random_state)
+    X_pca50 = pca_pre.fit_transform(X)
+
+    pca_2d = PCA(n_components=2, random_state=random_state)
+    X_pca2 = pca_2d.fit_transform(X_pca50)
+    explained_variance = pca_2d.explained_variance_ratio_ * 100
+
+    # --- t-SNE: 50D → 2D ---
+    tsne = TSNE(
+        n_components=2,
+        perplexity=perplexity,
+        learning_rate="auto",
+        init="pca",
+        random_state=random_state
+    )
+    X_tsne = tsne.fit_transform(X_pca50)
+
+    # --- Plot ---
+    fig, axes = plt.subplots(1, 2, figsize=figsize)
+    unique_classes = np.unique(Y)
+
+    for class_name in unique_classes:
+        idx = Y == class_name
+        label = legend_names.get(class_name, class_name)
+
+        axes[0].scatter(
+            X_pca2[idx, 0], X_pca2[idx, 1],
+            label=label, alpha=0.7, s=8
+        )
+    axes[0].set_xlabel(f"PC1 ({explained_variance[0]:.1f}%)")
+    axes[0].set_ylabel(f"PC2 ({explained_variance[1]:.1f}%)")
+    axes[0].set_title("PCA")
+    axes[0].legend(markerscale=2)
+
+    for class_name in unique_classes:
+        idx = Y == class_name
+        label = legend_names.get(class_name, class_name)
+
+        axes[1].scatter(
+            X_tsne[idx, 0], X_tsne[idx, 1],
+            label=label, alpha=0.7, s=8
+        )
+    axes[1].set_xlabel("t-SNE dimension 1")
+    axes[1].set_ylabel("t-SNE dimension 2")
+    axes[1].set_title("t-SNE")
+    axes[1].legend(markerscale=2)
+
+    plt.tight_layout()
+
+    if output_path is None:
+        output_path = "pca_tsne.png"
+    plt.savefig(output_path, dpi=dpi)
+    plt.close()
+    print(f"  Saved PCA/t-SNE plot to {output_path}")
+
+    return fig
+
+
+def plot_cv_accuracy(cv_results, split_type="", output_path=None,
+                     figsize=(7, 5), dpi=150):
+    """Plot cross-validation accuracy vs number of selected features.
+
+    Parameters
+    ----------
+    cv_results : list of dict
+        Each dict has keys "nfeatures" and "best_cv_accuracy".
+    split_type : str
+        Label for the plot title, e.g. "Image-level split".
+    output_path : str, optional
+        Output file path.
+    figsize : tuple
+    dpi : int
+
+    Returns
+    -------
+    fig : matplotlib Figure
+    """
+    fig, ax = plt.subplots(figsize=figsize)
+
+    nfeats = [r["nfeatures"] for r in cv_results]
+    accs = [r["best_cv_accuracy"] for r in cv_results]
+
+    ax.plot(nfeats, accs, marker="o")
+    ax.set_xscale("log")
+    ax.set_xlabel("Number of selected features")
+    ax.set_ylabel("Mean 5-fold validation accuracy")
+    if split_type:
+        ax.set_title(split_type)
+    plt.tight_layout()
+
+    if output_path is None:
+        output_path = f"{split_type.replace(' ', '_').replace('-', '_')}_cv.png"
+    plt.savefig(output_path, dpi=dpi)
+    plt.close()
+    print(f"  Saved CV accuracy plot to {output_path}")
+
+    return fig