From a01fe8a35c3908c044343fc54521e5f3cf9f3c1c Mon Sep 17 00:00:00 2001
From: john <jsolejr@gmail.com>
Date: Fri, 16 May 2025 13:52:44 +0000
Subject: [PATCH] Update analyize_discovery.py
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

✅ New Features

    Graphical file selectors for both:

        Choosing the discovery output file

        Choosing the name and location of the analysis output file

    Output saved to a text file formatted for easy copy/paste into Excel

    Tab-separated values in the summary for compatibility with Excel columns

    Modality breakdown + exam statistics in one concise report

📝 How to Use It

    Save the code below as dicom_analysis_tool.py.

    Run it (python dicom_analysis_tool.py or double-click if .py is registered).

    Click the button to:

        Select the discovery results .txt file.

        Specify the output .txt destination.

    It will create a text summary that can be easily opened in Excel (tab-delimited).
---
 analyize_discovery.py | 76 +++++++++++++++++++++++--------------------
 1 file changed, 40 insertions(+), 36 deletions(-)

diff --git a/analyize_discovery.py b/analyize_discovery.py
index 3c07be4..320483a 100644
--- a/analyize_discovery.py
+++ b/analyize_discovery.py
@@ -1,27 +1,35 @@
 import tkinter as tk
-from tkinter import filedialog, ttk
+from tkinter import filedialog, simpledialog
 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:
+def normalize_modalities(val):
+    if val.startswith("[") and val.endswith("]"):
+        try:
+            return ", ".join(eval(val))
+        except:
+            return val
+    return val
+
+def analyze_and_save():
+    input_path = filedialog.askopenfilename(
+        title="Select DICOM Discovery Output File",
+        filetypes=[("Text Files", "*.txt")]
+    )
+    if not input_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
+    output_path = filedialog.asksaveasfilename(
+        title="Save Analysis Output As",
+        defaultextension=".txt",
+        filetypes=[("Text Files", "*.txt")]
+    )
+    if not output_path:
+        return
 
+    df = pd.read_csv(input_path, delimiter='|', dtype=str).fillna('')
     df['ModalitiesInStudy'] = df['ModalitiesInStudy'].apply(normalize_modalities)
 
-    # Prepare metrics
     stats = {
         "Distinct StudyInstanceUIDs": df['StudyInstanceUID'].nunique(),
         "Distinct AccessionNumbers": df['AccessionNumber'].nunique(),
@@ -38,9 +46,9 @@ def load_and_analyze_file():
         "*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
+        "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']:
@@ -50,30 +58,26 @@ def load_and_analyze_file():
             else:
                 modality_counts["Other"] += 1
 
-    # Display results
-    output_window = tk.Toplevel(root)
-    output_window.title("DICOM Discovery Analysis")
+    with open(output_path, 'w') as f:
+        f.write("DICOM Discovery Analysis Summary\n")
+        f.write("="*40 + "\n\n")
+        for key, value in stats.items():
+            f.write(f"{key}\t{value}\n")
+        f.write("\nModality Breakdown\n")
+        f.write("-"*40 + "\n")
+        for modality, count in modality_counts.items():
+            f.write(f"{modality}\t{count}\n")
 
-    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.messagebox.showinfo("Analysis Complete", f"Analysis saved to:\n{output_path}")
 
-    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
+# GUI
 root = tk.Tk()
 root.title("DICOM Discovery Analyzer")
+root.geometry("400x150")
 
-frame = tk.Frame(root, padx=10, pady=10)
-frame.pack()
+frame = tk.Frame(root, padx=10, pady=20)
+frame.pack(expand=True)
 
-ttk.Button(frame, text="Select and Analyze Output File", command=load_and_analyze_file).pack()
+tk.Button(frame, text="Select Input File and Analyze", command=analyze_and_save, width=30).pack(pady=10)
 
 root.mainloop()