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.

results/classification_results.json

@@ -0,0 +1,52 @@
+[
+  {
+    "model": "VGG16",
+    "image_cv": 0.992,
+    "image_test": 1.0,
+    "image_nfeat": 5000,
+    "patient_cv": 0.9122,
+    "patient_test": 0.8933,
+    "patient_nfeat": 200,
+    "drop": 0.1067
+  },
+  {
+    "model": "DenseNet121",
+    "image_cv": 0.9875,
+    "image_test": 0.9955,
+    "image_nfeat": 5000,
+    "patient_cv": 0.9367,
+    "patient_test": 0.8711,
+    "patient_nfeat": 1000,
+    "drop": 0.1243
+  },
+  {
+    "model": "EfficientNetB1",
+    "image_cv": 0.9829,
+    "image_test": 0.9955,
+    "image_nfeat": 5000,
+    "patient_cv": 0.9158,
+    "patient_test": 0.8844,
+    "patient_nfeat": 1000,
+    "drop": 0.111
+  },
+  {
+    "model": "MobileNetV2",
+    "image_cv": 0.9875,
+    "image_test": 0.9955,
+    "image_nfeat": 2000,
+    "patient_cv": 0.913,
+    "patient_test": 0.8889,
+    "patient_nfeat": 750,
+    "drop": 0.1066
+  },
+  {
+    "model": "ResNet50",
+    "image_cv": 0.967,
+    "image_test": 0.9773,
+    "image_nfeat": 750,
+    "patient_cv": 0.8742,
+    "patient_test": 0.8622,
+    "patient_nfeat": 400,
+    "drop": 0.1151
+  }
+]