Merge pull request #6 from VemundFredriksen/tumor_insertion_improvement

Tumor insertion improvement

assets/readme.md

@@ -6,5 +6,5 @@
 2. Download the MSD Lung Tumor dataset from [here](https://drive.google.com/drive/folders/1HqEgzS8BV2c7xYNrZdEAnrHk7osJJ--2).
 3. Extract the zip file into `/assets/`.
 4. Run `synthlung format --dataset msd` to adjust dataset format
-5. Run `synthlung seed --dataset` to extract tumor seeds from the dataset
+5. Run `synthlung seed --dataset msd` to extract tumor seeds from the dataset
 6. Run `synthlung host --dataset msd` to extract lung masks from the images

synthlung/__main__.py

@@ -23,11 +23,11 @@ def format_msd():
 
 def generate_randomized_tumors():
     tumor_inserter = InsertTumorPipeline()
-    json_file_path = "./assets/source/msd/dataset.json"
+    json_file_path = "./assets/source/dataset.json"
     with open(json_file_path, 'r') as json_file:
         image_dict = json.load(json_file)
 
-    json_seed_path = "./assets/seeds/msd/dataset.json"
+    json_seed_path = "./assets/seeds/dataset.json"
     with open(json_seed_path, 'r') as json_file:
         seeds_dict = json.load(json_file)
 
@@ -36,12 +36,12 @@ def generate_randomized_tumors():
 def mask_hosts():
     lung_masker = LMInferer()
     host_masker = LungMaskPipeline(lung_masker)
-    json_file_path = "./assets/source/msd/dataset.json"
+    json_file_path = "./assets/source/dataset.json"
     with open(json_file_path, 'r') as json_file:
         image_dict = json.load(json_file)
 
-    #host_masker(image_dict)
-    json_generator = HostJsonGenerator('./assets/hosts/msd/')
+    host_masker(image_dict)
+    json_generator = HostJsonGenerator('./assets/hosts/')
     json_generator.generate_json()
 
 def main():

synthlung/utils/lung_segmentation_pipeline.py

@@ -43,7 +43,7 @@ def __init__(self, lungmask_inferer: LMInferer) -> None:
         self.compose = Compose([
             LoadImaged(keys=['image'], image_only = False),
             MaskLungs(lungmask_inferer=self.inferer),
-            SaveImaged(keys=['mask'], output_dir='./assets/hosts/msd/', output_postfix='', separate_folder=False)
+            SaveImaged(keys=['mask'], output_dir='./assets/hosts/', output_postfix='', separate_folder=False)
         ])
 
     def __call__(self, image_dict) -> Any:

synthlung/utils/tumor_insertion_pipeline.py

@@ -5,70 +5,61 @@
 import random
 import json
 import os
+import requests
+import secrets
+
+seed = 3
 
 class InsertTumor(object):
     def __call__(self, sample) -> None:
-        image, label, seed_image, seed_label = sample['image'], sample['label'], sample['seed_image'], sample['seed_label']
+        image, label, image_mask, seed_image, seed_label = sample['image'], sample['label'], sample["image_mask"], sample['seed_image'], sample['seed_label']
 
-        lungmask = self.__generate_random_lungmask__(image)
-        offset_randomizer = np.random.default_rng(3)
+        offset_randomizer = np.random.default_rng(seed)
 
-        while (True): #Temporary offset calculation
-            offset_location = (offset_randomizer.standard_normal() * (sample['image_meta_dict']['spatial_shape'] - seed_image.shape)).astype(int)
-            if (lungmask[offset_location[0], offset_location[1], offset_location[2]] == 1):
+        while (True):
+            offset_location = (offset_randomizer.random(size=3) * sample['image_meta_dict']['spatial_shape']).astype(int)
+            if (image_mask[offset_location[0], offset_location[1], offset_location[2]] > 0):
                 break
 
+        offset_location = offset_location - np.array(seed_image.shape) // 2
+
         image[offset_location[0] : offset_location[0] + seed_image.shape[0], offset_location[1] : offset_location[1] + seed_image.shape[1], offset_location[2] : offset_location[2] + seed_image.shape[2]][seed_label == 1] = seed_image[seed_label == 1]
         label[offset_location[0] : offset_location[0] + seed_image.shape[0], offset_location[1] : offset_location[1] + seed_image.shape[1], offset_location[2] : offset_location[2] + seed_image.shape[2]][seed_label == 1] = 1
 
-        self.__remove_filename__(image)
-        self.__remove_filename__(label)
+        sample["image_meta_dict"]["filename_or_obj"] = sample["randomized_image"]
+        sample["label_meta_dict"]["filename_or_obj"] = sample["randomized_label"]
 
         return sample
-
-    def __generate_random_lungmask__(self, image): #Temporary method
-        shape_dim_0 = image.shape[0]
-        shape_dim_1 = image.shape[1]
-        shape_dim_2 = image.shape[2]
-        dim0min = shape_dim_0 // 4
-        dim0max = 3 * dim0min
-        dim1min = shape_dim_1 // 4
-        dim1max = 3 * dim1min
-        dim2min = shape_dim_2 // 4
-        dim2max = 3 * dim2min
-        arra = np.where(image > 0, 0, 0)
-        arra[dim0min : dim0max, dim1min : dim1max, dim2min : dim2max] = 1
-        return arra
-
-    def __remove_filename__(self, image):
-        image.meta['filename_or_obj'] = ""
 
 class InsertTumorPipeline(object):
     def __init__(self) -> None:
         self.randomized_dict = []
-        self.time = f"{datetime.datetime.now()}".replace(" ", "-").replace(":", ".")
+        #self.time = f"{datetime.datetime.now()}".replace(" ", "-").replace(":", ".")
+        self.time = "00-00"
         self.dir_name = f"./assets/artificial_tumors/{self.time}/"
         self.compose = Compose([
-            LoadImaged(keys=['image', 'label', 'seed_image', 'seed_label']),
+            LoadImaged(keys=['image', 'label', 'image_mask', 'seed_image', 'seed_label']),
             InsertTumor(),
-            SaveImaged(keys=['image'], output_dir=f"{self.dir_name}randomzied_images/", output_postfix="image"),
-            SaveImaged(keys=['label'], output_dir=f"{self.dir_name}randomzied_images/", output_postfix="label")
+            SaveImaged(keys=['image'], output_dir=f"{self.dir_name}randomzied_images/", output_postfix="", separate_folder=False),
+            SaveImaged(keys=['label'], output_dir=f"{self.dir_name}randomzied_images/", output_postfix="", separate_folder=False)
         ])
 
     def __call__(self, image_dict, seeds_dict) -> None:
         self.__generate_randomized_dict__(image_dict, seeds_dict)
         self.compose(self.randomized_dict)
 
     def __generate_randomized_dict__(self, image_dict, seeds_dict):
-        for n, i in enumerate(range(1)):
+        for n, i in enumerate(range(10)):
             image = random.choice(image_dict)
             seed = random.choice(seeds_dict)
 
+            image["image_mask"] = image["label"].replace("/source/", "/hosts/").replace("source_", "host_")
+
             output_name = {"randomized_image" : f"{self.dir_name}randomzied_images/image_{n}.nii.gz",
                            "randomized_label" : f"{self.dir_name}randomzied_images/label_{n}.nii.gz"}
 
             self.randomized_dict.append({**image, **seed, **output_name})
-        
+
         self.__log__()
 
     def __log__(self):
@@ -79,3 +70,17 @@ def __log__(self):
 
         with open(log_name + "dataset.json", 'w') as json_file:
             json.dump(self.randomized_dict, json_file, indent=4)
+
+        if (True):
+            return
+
+        for elem in self.randomized_dict:
+            jsonData = {"id" : str(secrets.token_hex(12))}
+            jsonData = {**jsonData, **elem}
+            jsonData = json.dumps(jsonData)
+            url = "http://localhost:5167/api/Log"
+            header = {"Content-Type" : "application/json"}
+
+            print(jsonData)
+
+            requests.post(url, data=jsonData, headers=header, verify=False)