Add analyize_discovery.py

analyize_discovery.py

@@ -0,0 +1,79 @@
+import tkinter as tk
+from tkinter import filedialog, ttk
+import pandas as pd
+import os
+
+def load_and_analyze_file():
+    file_path = filedialog.askopenfilename(title="Select DICOM Discovery Output File", filetypes=[("Text Files", "*.txt")])
+    if not file_path:
+        return
+
+    df = pd.read_csv(file_path, delimiter='|', dtype=str).fillna('')
+
+    # Normalize modalities to upper case and flatten list-like strings
+    def normalize_modalities(val):
+        if val.startswith("[") and val.endswith("]"):
+            try:
+                return ", ".join(eval(val))
+            except:
+                return val
+        return val
+
+    df['ModalitiesInStudy'] = df['ModalitiesInStudy'].apply(normalize_modalities)
+
+    # Prepare metrics
+    stats = {
+        "Distinct StudyInstanceUIDs": df['StudyInstanceUID'].nunique(),
+        "Distinct AccessionNumbers": df['AccessionNumber'].nunique(),
+        "AccessionNumbers with 2 StudyInstanceUIDs": (df.groupby('AccessionNumber')['StudyInstanceUID'].nunique() == 2).sum(),
+        "AccessionNumbers with 3 StudyInstanceUIDs": (df.groupby('AccessionNumber')['StudyInstanceUID'].nunique() == 3).sum(),
+        "AccessionNumbers with >3 StudyInstanceUIDs": (df.groupby('AccessionNumber')['StudyInstanceUID'].nunique() > 3).sum(),
+        "Missing AccessionNumbers": (df['AccessionNumber'] == '').sum(),
+        "Missing StudyDescriptions": (df['StudyDescription'] == '').sum(),
+        "*QA* in PatientID": df['PatientID'].str.contains('QA', case=False, na=False).sum(),
+        "*QA* in StudyDescription": df['StudyDescription'].str.contains('QA', case=False, na=False).sum(),
+        "*QA* in PatientName": df['PatientName'].str.contains('QA', case=False, na=False).sum(),
+        "*TEST* in PatientID": df['PatientID'].str.contains('TEST', case=False, na=False).sum(),
+        "*TEST* in StudyDescription": df['StudyDescription'].str.contains('TEST', case=False, na=False).sum(),
+        "*TEST* in PatientName": df['PatientName'].str.contains('TEST', case=False, na=False).sum()
+    }
+
+    # Modality breakdown
+    modality_counts = {
+        "CR": 0, "DX": 0, "CT": 0, "MR": 0, "NM": 0, "US": 0, "XA": 0, "PR": 0, "SC": 0, "OT": 0, "Other": 0
+    }
+
+    for val in df['ModalitiesInStudy']:
+        for modality in [m.strip().upper() for m in val.split(',') if m.strip()]:
+            if modality in modality_counts:
+                modality_counts[modality] += 1
+            else:
+                modality_counts["Other"] += 1
+
+    # Display results
+    output_window = tk.Toplevel(root)
+    output_window.title("DICOM Discovery Analysis")
+
+    row = 0
+    for key, val in stats.items():
+        tk.Label(output_window, text=f"{key}:").grid(row=row, column=0, sticky='w', padx=5, pady=2)
+        tk.Label(output_window, text=f"{val}").grid(row=row, column=1, sticky='w', padx=5, pady=2)
+        row += 1
+
+    tk.Label(output_window, text="Modality Breakdown:").grid(row=row, column=0, sticky='w', padx=5, pady=10)
+    row += 1
+    for modality, count in modality_counts.items():
+        tk.Label(output_window, text=f"{modality}:").grid(row=row, column=0, sticky='w', padx=20, pady=2)
+        tk.Label(output_window, text=f"{count}").grid(row=row, column=1, sticky='w', padx=5, pady=2)
+        row += 1
+
+# GUI setup
+root = tk.Tk()
+root.title("DICOM Discovery Analyzer")
+
+frame = tk.Frame(root, padx=10, pady=10)
+frame.pack()
+
+ttk.Button(frame, text="Select and Analyze Output File", command=load_and_analyze_file).pack()
+
+root.mainloop()