table_of_cells_after_segmentation.py

import json
import pandas as pd
import os
import argparse
parser = argparse.ArgumentParser('table_of_cells')
parser.add_argument('--inputdir', '-i', required=True, help="Folder where json files generated by infer.py are stored")
parser.add_argument('--patient_id', '-s', required=True, help="Patient ID for which the segmentation table will be created")
parser.add_argument('--segmentation_dir',  default=   '/home/mathiane/LNENWork/CFlow_mathiane/CFlow/TumorSegmentation_Ki67_Baseline_2809_1004/segmentation_maps_3_thresholds' , required=False)

# Get parameters
args = parser.parse_args()
inputdir = args.inputdir
segmentation_dir = args.segmentation_dir
patient_id = args.patient_id
# Name of the output table
df_name =  patient_id + '_cells_detected_segmented.csv'
print('patient_id  ', patient_id)

print("Get tiles ID within the tumoral area")
# Get segmentation table
segmentation_correct = False
for tneid in os.listdir(segmentation_dir):
    if tneid.find(patient_id) != -1:  
        for ele in os.listdir(os.path.join(segmentation_dir, tneid)):
            if ele.find("csv") != -1:
                df_seg = pd.read_csv(os.path.join(segmentation_dir, tneid, ele))
                segmentation_correct = True
                                          
# Take into account only the tumoral tiles
df_seg_tumor = df_seg[df_seg['PredTumorNomal'] == 'Tumor'] 
print(df_seg_tumor.head())
if segmentation_correct:
    
    print("Get the infrence json filename of the tumoral tiles")
    tiles_to_include = []
    for i in range(df_seg_tumor.shape[0]):
        # Get name of json files generated by infer.py
        tile_id  =  df_seg_tumor.iloc[i,1].split('/')[-1][:-3] + 'json'
        tiles_to_include.append(tile_id)
    
    print("Create the coordianate table")
    x_list = []
    y_list = []
    label_list = []
    print(os.path.join(inputdir,args.patient_id, 'accept'))
    
    for file in os.listdir(os.path.join(inputdir,args.patient_id, 'accept')):
        # Read inference files if the tiles belongs to the tumor area
        if file.find('json') != -1 and file in tiles_to_include:
            # Get tile coords
            xul = int(file.split('_')[1])
            yul = int(file.split('_')[2].split('.')[0])
            with open(os.path.join(inputdir, args.patient_id ,'accept', file)) as json_file:
                cells = json.load(json_file)
            # Get all cells predicted in the tiles
            for cell in cells:
                    x_list.append(cell['x']+ xul )
                    y_list.append(cell['y'] + yul)
                    label_list.append(cell['label_id'])
        
    # Table summarizing the coordinated and the class of the cells detected by Pathonet in the tumor area
    df = pd.DataFrame()
    df['x'] = x_list
    df['y'] = y_list
    df['label'] = label_list
    print("Write the table")
    df.to_csv(os.path.join(inputdir,args.patient_id, df_name))
else:
    print("Segmentation table not found")