def main(args):
mitosis_input_dir = '../../../deep-histopath/data/mitoses/mitoses_train_image_data/'
mitosis_reorganized_dir = '../../../deep-histopath/data/mitoses/mitoses_train_image_data_new/'
if args.reorganize_folder_structure:
print("1. Reorganize the data structure for Mask_RCNN")
reorganize_mitosis_images(mitosis_input_dir, mitosis_reorganized_dir)
inference_input_dir = 'datasets/stage1_test'
if args.split_big_images_to_small_ones:
print("2. Crop big images into small ones")
mitosis_files = [
str(f) for f in Path(mitosis_reorganized_dir).glob('**/**/*.tif')
]
crop_image(mitosis_files, inference_input_dir, size=128, overlap=16)
command = 'detect'
dataset = 'datasets/'
weights = 'models/mask_rcnn_nucleus_0380.h5'
subset = 'stage1_test'
if args.run_nucleus_detection:
print("3. Run the nucleus segmentation inference")
inference_result_dir = nucleus_mitosis.run(command, dataset, weights,
subset)
inference_result_dir = '../../results/nucleus/submit_20181016T152921'
inference_combine_result = 'datasets/stage1_combine_test/'
if args.combine_small_inference_results:
print("4. Combine small inference images and csvs to big ones")
combine_images(inference_result_dir, inference_combine_result)
combine_csvs(inference_result_dir,
inference_combine_result,
clean_output_dir=False)
ground_truth_dir = '../../../deep-histopath/data/mitoses/mitoses_train_ground_truth'
if args.visualize_the_ground_truth:
print("5. Visualize the ground truth masks")
add_groundtruth_mark(inference_combine_result,
ground_truth_dir,
hasHeader=False,
shape=Shape.CIRCLE)
# add_mark('/Users/fei/Documents/Github/Mask_RCNN/samples/nucleus/datasets/stage1_combine_test/01-01.png',
# '/Users/fei/Documents/Github/Mask_RCNN/samples/nucleus/datasets/stage1_combine_test/01-01.csv',
# hasHeader=True, shape=Shape.CIRCLE, mark_color=(255,0,0,50))
inference_dir = "datasets/stage1_combine_test/"
ground_truth_dir = "../../../deep-histopath/data/mitoses/mitoses_train_ground_truth"
if args.evaluate_nucleus_inference:
print("6. Evaluate the nucleus inference result")
check_nucleius_inference(inference_dir, ground_truth_dir)
img_dir = '../../../deep-histopath/data/mitoses/mitoses_train_image_data/'
location_csv_dir = 'datasets/stage1_combine_test/'
output_patch_basedir = 'datasets/sample_patches'
if args.extract_patch:
print("7. Extract patches according to the inference result")
extract_patches(img_dir, location_csv_dir, output_patch_basedir)
input_dir_basepath = 'datasets/sample_patches/'
output_dir_basepath = 'datasets/inference_results/'
model_file = '../../../deep-histopath/experiments/models/deep_histopath_model.hdf5'
if args.run_mitosis_classification:
print("8. Run mitosis classification inference")
batch_size = 128 * 10
num_parallel_calls = 1
prob_thres = 0.5,
eps = 64
min_samples = 1
isWeightedAvg = False
run_reference_in_batch(batch_size=batch_size,
input_dir_basepath=input_dir_basepath,
output_dir_basepath=output_dir_basepath,
model_file=model_file,
num_parallel_calls=num_parallel_calls,
prob_thres=prob_thres,
eps=eps,
min_samples=min_samples,
isWeightedAvg=isWeightedAvg)
output_dir_basepath = 'datasets/val_results/'
ground_truth_dir = "../../../deep-histopath/data/mitoses/val_ground_truth"
if args.compute_f1:
print("9. Compute F1 score")
f1, precision, recall, over_detected, non_detected, FP, TP, FN = \
evaluate_global_f1(output_dir_basepath, ground_truth_dir, threshold=30,
prob_threshold=None)
print("F1: {} \n"
"Precision: {} \n"
"Recall: {} \n"
"Over_detected: {} \n"
"Non_detected: {} \n"
"FP: {} \n"
"TP: {} \n"
"FN: {} \n".format(f1, precision, recall, over_detected,
non_detected, FP, TP, FN))
def main(args):
config = MitosisInferenceConfig()
if args.reorganize_folder_structure:
print("1. Reorganize the data structure for Mask_RCNN")
reorganize_mitosis_images(config.mitosis_input_dir,
config.mitosis_reorganized_dir)
if args.split_big_images_to_small_ones:
print("2. Crop big images into small ones")
mitosis_files = \
[str(f) for f in Path(config.mitosis_reorganized_dir)
.glob('**/**/*.tif')]
crop_image(mitosis_files,
config.inference_input_dir,
size=config.crop_image_size,
overlap=config.crop_image_overlap)
if args.run_nucleus_detection:
print("3. Run the nucleus segmentation inference")
nucleus_mitosis.inference(config.inference_input_dir, config.weights,
config.maskrcnn_inference_result_dir)
print("Inference result dir: ", config.maskrcnn_inference_result_dir)
if args.combine_small_inference_results:
print("4. Combine small inference images and csvs to big ones")
combine_images(config.maskrcnn_inference_result_dir,
config.maskrcnn_inference_combined_result,
size=config.crop_image_size)
combine_csvs(config.maskrcnn_inference_result_dir,
config.maskrcnn_inference_combined_result,
hasProb=config.hasProb,
clean_output_dir=False)
if args.cluster_nucleus_detection_results:
print("4.1 Cluster the nucleus detection results")
cluster_prediction_result(config.maskrcnn_inference_combined_result,
eps=32,
min_samples=1,
hasHeader=True,
isWeightedAvg=False,
prob_threshold=0.8)
for file_name in [
"11-01", "11-02", "11-03", "12-01", "12-02", "12-03"
]:
add_mark(os.path.join(config.maskrcnn_inference_combined_result,
"{}.png".format(file_name)),
os.path.join(
config.maskrcnn_inference_combined_clusterd_result,
"{}.csv".format(file_name)),
hasHeader=True,
shape=Shape.SQUARE,
mark_color=(255, 100, 100, 200))
if args.visualize_the_ground_truth:
print("5. Visualize the ground truth masks")
add_groundtruth_mark(config.maskrcnn_inference_combined_result,
config.ground_truth_dir,
hasHeader=False,
shape=Shape.CIRCLE)
# add_mark('/Users/fei/Documents/Github/Mask_RCNN/samples/nucleus/datasets/stage1_combine_test/01-01.png',
# '/Users/fei/Documents/Github/Mask_RCNN/samples/nucleus/datasets/stage1_combine_test/01-01.csv',
# hasHeader=True, shape=Shape.CIRCLE, mark_color=(255,0,0,50))
if args.evaluate_nucleus_inference:
print("6. Evaluate the nucleus inference result")
check_nucleus_inference(config.maskrcnn_inference_combined_result,
config.ground_truth_dir)
if args.extract_nucleus_patch:
print("7. Extract patches according to the inference result")
extract_patches(config.mitosis_input_dir,
config.maskrcnn_inference_combined_result,
config.extracted_nucleus_dir,
patch_size=config.mitosis_patch_size)
if args.run_mitosis_classification:
print("8. Run mitosis classification inference")
batch_size = 128
num_parallel_calls = 8
prob_thres = 0.5,
eps = 64
min_samples = 1
is_weighted_avg = False
run_mitosis_classification_in_batch(
batch_size=batch_size,
input_dir_basepath=config.extracted_nucleus_dir,
output_dir_basepath=config.mitosis_classification_result_dir,
model_file=config.mitosis_classification_model_file,
augmentation_number=config.augmentation_number,
mitosis_tile_size=config.mitosis_tile_size,
num_parallel_calls=config.
mitosis_classification_num_parallel_calls,
prefectch=config.mitosis_classification_prefetch,
prob_thres=prob_thres,
eps=eps,
min_samples=min_samples,
isWeightedAvg=is_weighted_avg)
if args.compute_f1:
print("9. Compute F1 score")
f1, precision, recall, over_detected, non_detected, FP, TP, FN = \
evaluate_global_f1(config.mitosis_classification_result_dir,
config.ground_truth_dir,
threshold=30,
prob_threshold=config.f1_prob_threshhold)
print("F1: {} \n"
"Precision: {} \n"
"Recall: {} \n"
"Over_detected: {} \n"
"Non_detected: {} \n"
"FP: {} \n"
"TP: {} \n"
"FN: {} \n".format(f1, precision, recall, len(over_detected),
len(non_detected), len(FP), len(TP), len(FN)))
from deephistopath.evaluation import evaluate_global_f1
import deephistopath.evaluation as ev
import deephistopath.detection as det
import shutil
img_dir = "data/mitoses/mitoses_train_image_data"
#pred_dir = "pred/result/2018/new_orig_v3_fp_v3_8_icpr/scratch/resnet_custom/resnet_custom_stride_32_nm_model_180307_175241"
#pred_dir = "pred/result/2018/new_orig_v3_fp_v3_8_icpr/scratch/resnet_custom/resnet_custom_stride_16_nm_model_180307_175241"
#pred_dir = "pred/result/2018/new_orig_v3_fp_v3_8_icpr/scratch/resnet_custom/resnet_custom_stride_1_nm_model_180307_175241"
#pred_dir = "pred/result/2018/new_orig_v3_fp_v3_8_icpr/scratch/resnet_custom/resnet_custom_stride_16_marg_model_180307_175241"
#ground_true_dir = "pred/data/val_ground_truth"
pred_dir = "/8tb/deep_histopath/result/mitoses/mitoses_test_image_result"
print("raw predictions:")
threshold = 30
prob_thresh = 0.5
f1, ppv, sens, over_detected, non_detected, fp_list, tp_list, fn_list = evaluate_global_f1(
pred_dir, ground_true_dir, threshold, prob_thresh)
print(f"F1: {f1}; Precision: {ppv}; Recall: {sens}; FP: {len(fp_list)}; TP: {len(tp_list)}; FN: "\
f"{len(fn_list)}")
# smooth prob maps
print("smoothing predictions:")
radius = 15
det.smooth_prediction_results(pred_dir, img_dir, radius, True)
# NOTE: this is probably not what we want to evaluate, because the smoothing algorithm needs the
# ensuing detection step to be useful
print("smoothed predictions:")
smooth_pred_dir = pred_dir + "_smoothed"
#threshold = 30 # 27
#prob_thresh = 0.35 #65
#f1, ppv, sens, over_detected, non_detected, fp_list, tp_list, fn_list = evaluate_global_f1(