浅析细胞图像数据的主动学习

import os, sys, randomimport xml.etree.ElementTree as ETfrom glob import globimport pandas as pdfrom shutil import copyfileannotations = glob('BCCD_Dataset/BCCD/Annotations/*.xml')df = []for file in annotations:#filename = file.split('/')[-1].split('.')[0] + '.jpg'#filename = str(cnt) + '.jpg'filename = file.split('\\')[-1]filename =filename.split('.')[0] + '.jpg'row = []parsedXML = ET.parse(file)cell_id = 0for node in parsedXML.getroot().iter('object'):blood_cells = node.find('name').textxmin = int(node.find('bndbox/xmin').text)xmax = int(node.find('bndbox/xmax').text)ymin = int(node.find('bndbox/ymin').text)ymax = int(node.find('bndbox/ymax').text)row = [filename, cell_id, blood_cells, xmin, xmax, ymin, ymax]df.append(row)cell_id += 1data = pd.DataFrame(df, columns=['filename', 'cell_id', 'cell_type', 'xmin', 'xmax', 'ymin', 'ymax'])data['image_id'] = data['filename'].apply(lambda x: int(x[-7:-4]))data[['filename', 'image_id', 'cell_id', 'cell_type', 'xmin', 'xmax', 'ymin', 'ymax']].to_csv('bccd.csv', index=False)

import osimport pandas as pdfrom PIL import Imagedef crop_cell(row):"""crop_cell(row)given a pd.Series row of the dataframe, load row['filename'] with PIL,crop it to the box row['xmin'], row['xmax'], row['ymin'], row['ymax']save the cropped image,return cropped filename"""input_dir = 'BCCD\JPEGImages'output_dir = 'BCCD\cropped'# open imageim = Image.open(f"{input_dir}\{row['filename']}")# size of the image in pixelswidth, height = im.size# setting the points for cropped imageleft = row['xmin']bottom = row['ymax']right = row['xmax']top = row['ymin']# cropped imageim1 = im.crop((left, top, right, bottom))cropped_fname = f"BloodImage_{row['image_id']:03d}_{row['cell_id']:02d}.jpg"# shows the image in image viewer# im1.show()# save imagetry:im1.save(f"{output_dir}\{cropped_fname}")except:return 'error while saving image'return cropped_fnameif __name__ == "__main__":# load labels csv into Pandas DataFramefilepath = "BCCD\dataset2-master\labels.csv"df = pd.read_csv(filepath)# iterate through cells, crop each cell, and save cropped cell to filedataset_df['cell_filename'] = dataset_df.apply(crop_cell, axis=1)

# imports for the whole experimentimport numpy as npfrom matplotlib import pyplot as pltfrom modAL import ActiveLearnerimport pandas as pdfrom modAL.uncertainty import uncertainty_samplingfrom sklearn import preprocessingfrom sklearn.metrics import , average_precision_scorefrom sklearn.linear_model import LogisticRegression# upload the cell profiler features for each celldata = pd.read_csv('Zaretski_Image_All.csv')# filter plateletsdata = data[data['cell_type'] != 'Platelets']# define the labeltarget = 'cell_type'label_encoder = preprocessing.LabelEncoder()y = label_encoder.fit_transform(data[target])# take the learning features onlyX = data.iloc[:, 5:]# create training and testing setsX_train, X_test, y_train, y_test = train_test_split(X.to_numpy(), y, test_size=0.33, random_state=42)

dummy_learner = LogisticRegression()
active_learner = ActiveLearner(
estimator=LogisticRegression(),
query_strategy=uncertainty_sampling()
)

# the training size that we will start withbase_size = 5# the 'base' data that will be the training set for our modelX_train_base_dummy = X_train[:base_size]X_train_base_active = X_train[:base_size]y_train_base_dummy = y_train[:base_size]y_train_base_active = y_train[:base_size]# the 'new' data that will simulate unlabeled data that we pick a sample from and label itX_train_new_dummy = X_train[base_size:]X_train_new_active = X_train[base_size:]y_train_new_dummy = y_train[base_size:]y_train_new_active = y_train[base_size:]

# arrays to accumulate the scores of each simulation along the epochsdummy_scores = []active_scores = []# number of desired epochsrange_epoch = 298# running the experimentfor i in range(range_epoch):# train the models on the 'base' datasetactive_learner.fit(X_train_base_active, y_train_base_active)dummy_learner.fit(X_train_base_dummy, y_train_base_dummy)# evaluate the modelsdummy_pred = dummy_learner.predict(X_test)active_pred = active_learner.predict(X_test)# accumulate the scoresdummy_scores.append(average_precision_score(dummy_pred, y_test))active_scores.append(average_precision_score(active_pred, y_test))# pick the next sample in the random strategy and randomly# add it to the 'base' dataset of the dummy learner and remove it from the 'new' datasetX_train_base_dummy = np.append(X_train_base_dummy, [X_train_new_dummy[0, :]], axis=0)y_train_base_dummy = np.concatenate([y_train_base_dummy, np.array([y_train_new_dummy[0]])], axis=0)X_train_new_dummy = X_train_new_dummy[1:]y_train_new_dummy = y_train_new_dummy[1:]# pick next sample in the active strategyquery_idx, query_sample = active_learner.query(X_train_new_active)# add the index to the 'base' dataset of the active learner and remove it from the 'new' datasetX_train_base_active = np.append(X_train_base_active, X_train_new_active[query_idx], axis=0)y_train_base_active = np.concatenate([y_train_base_active, y_train_new_active[query_idx]], axis=0)X_train_new_active = np.concatenate([X_train_new_active[:query_idx[0]], X_train_new_active[query_idx[0] + 1:]], axis=0)y_train_new_active = np.concatenate([y_train_new_active[:query_idx[0]], y_train_new_active[query_idx[0] + 1:]], axis=0)

plt.plot(list(range(range_epoch)), active_scores, label='Active Learning')plt.plot(list(range(range_epoch)), dummy_scores, label='Dummy')plt.xlabel('number of added samples')plt.ylabel('average precision score')plt.legend(loc='lower right')plt.savefig("models robustness vs dummy.png", bbox_inches='tight')plt.show()