import torch
import torch.cuda
import torch.nn.functional as F
from torch.utils.data import Dataset
from util.disk import getCache
from util.util import XyzTuple, xyz2irc
from util.logconf import logging
log = logging.getLogger(__name__)
# log.setLevel(logging.WARN)
# log.setLevel(logging.INFO)
log.setLevel(logging.DEBUG)
raw_cache = getCache('part2ch14_raw')
CandidateInfoTuple = namedtuple(
'CandidateInfoTuple',
'isNodule_bool, hasAnnotation_bool, isMal_bool, diameter_mm, series_uid, center_xyz'
)
MaskTuple = namedtuple(
'MaskTuple',
'raw_dense_mask, dense_mask, body_mask, air_mask, raw_candidate_mask, candidate_mask, lung_mask, neg_mask, pos_mask'
)
@functools.lru_cache(1)
def getCandidateInfoList(requireDataOnDisk_bool=True):
# We construct a set with all series_uids that are present on disk.
# This will let us use the data, even if we haven't downloaded all of
import numpy as np
import torch
import torch.cuda
from torch.utils.data import Dataset
from util.disk import getCache
from util.util import XyzTuple, xyz2irc
from util.logconf import logging
log = logging.getLogger(__name__)
# log.setLevel(logging.WARN)
log.setLevel(logging.INFO)
log.setLevel(logging.DEBUG)
raw_cache = getCache('part2ch08_raw')
@functools.lru_cache(1)
def getNoduleInfoList(requireDataOnDisk_bool=True):
# We construct a set with all series_uids that are present on disk.
# This will let us use the data, even if we haven't downloaded all of
# the subsets yet.
mhd_list = glob.glob('data/luna/subset*/*.mhd')
dataPresentOnDisk_set = {os.path.split(p)[-1][:-4] for p in mhd_list}
diameter_dict = {}
with open('data/luna/annotations.csv', "r") as f:
for row in list(csv.reader(f))[1:]:
series_uid = row[0]
annotationCenter_xyz = tuple([float(x) for x in row[1:4]])
import torch
import torch.cuda
import torch.nn.functional as F
from torch.utils.data import Dataset
from util.disk import getCache
from util.util import XyzTuple, xyz2irc
from util.logconf import logging
log = logging.getLogger(__name__)
# log.setLevel(logging.WARN)
# log.setLevel(logging.INFO)
log.setLevel(logging.DEBUG)
raw_cache = getCache("part2ch13_raw")
MaskTuple = namedtuple(
"MaskTuple",
"raw_dense_mask, dense_mask, body_mask, air_mask, raw_candidate_mask, candidate_mask, lung_mask, neg_mask, pos_mask",
)
CandidateInfoTuple = namedtuple(
"CandidateInfoTuple",
"isNodule_bool, hasAnnotation_bool, isMal_bool, diameter_mm, series_uid, center_xyz",
)
@functools.lru_cache(1)
def getCandidateInfoList(requireOnDisk_bool=True):
# We construct a set with all series_uids that are present on disk.
import torch
import torch.cuda
from torch.utils.data import Dataset, DataLoader
from torch.utils.data.sampler import Sampler
from util.disk import getCache
from util.util import XyzTuple, xyz2irc, IrcTuple
from util.logconf import logging
from util.affine import affine_grid_generator
log = logging.getLogger(__name__)
# log.setLevel(logging.WARN)
log.setLevel(logging.INFO)
log.setLevel(logging.DEBUG)
raw_cache = getCache('part2ch11_raw')
cubic_cache = getCache('part2ch11_cubic')
NoduleInfoTuple = namedtuple('NoduleInfoTuple', 'isMalignant_bool, diameter_mm, series_uid, center_xyz')
@functools.lru_cache(1)
def getNoduleInfoList(requireDataOnDisk_bool=True):
# We construct a set with all series_uids that are present on disk.
# This will let us use the data, even if we haven't downloaded all of
# the subsets yet.
mhd_list = glob.glob('data-unversioned/part2/luna/subset*/*.mhd')
dataPresentOnDisk_set = {os.path.split(p)[-1][:-4] for p in mhd_list}
diameter_dict = {}
with open('data/part2/luna/annotations.csv', "r") as f:
for row in list(csv.reader(f))[1:]:
import numpy as np
import torch
import torch.cuda
from torch.utils.data import Dataset
from util.disk import getCache
from util.util import XyzTuple, xyz2irc
from util.logconf import logging
log = logging.getLogger(__name__)
# log.setLevel(logging.WARN)
log.setLevel(logging.INFO)
log.setLevel(logging.DEBUG)
cache = getCache('part2')
class Ct(object):
def __init__(self, series_uid):
mhd_path = glob.glob('data/luna/subset*/{}.mhd'.format(series_uid))[0]
ct_mhd = sitk.ReadImage(mhd_path)
ct_ary = np.array(sitk.GetArrayFromImage(ct_mhd), dtype=np.float32)
# CTs are natively expressed in https://en.wikipedia.org/wiki/Hounsfield_scale
# HU are scaled oddly, with 0 g/cc (air, approximately) being -1000 and 1 g/cc (water) being 0.
# This converts HU to g/cc.
ct_ary += 1000
ct_ary /= 1000
# This gets rid of negative density stuff used to indicate out-of-FOV
import numpy as np
import torch
import torch.cuda
from torch.utils.data import Dataset
from util.disk import getCache
from util.util import XyzTuple, xyz2irc
from util.logconf import logging
log = logging.getLogger(__name__)
# log.setLevel(logging.WARN)
# log.setLevel(logging.INFO)
log.setLevel(logging.DEBUG)
raw_cache = getCache('raw')
CandidateInfoTuple = namedtuple(
'CandidateInfoTuple',
'isNodule_bool, diameter_mm, series_uid, center_xyz',
)
@functools.lru_cache(1)
def getCandidateInfoList(requireOnDisk_bool=True):
# We construct a set with all series_uids that are present on disk.
# This will let us use the data, even if we haven't downloaded all of
# the subsets yet.
mhd_list = glob.glob('data/subset*/*.mhd')
presentOnDisk_set = {os.path.split(p)[-1][:-4] for p in mhd_list}
import imageio
import glob
import torch
import copy
import functools
import random
import torch
import matplotlib.pyplot as plt
from torch.utils.data import Dataset
from torch.nn.functional import affine_grid, grid_sample
from util.disk import getCache
import math
device = (torch.device('cuda')
if torch.cuda.is_available() else torch.device('cpu'))
raw_cache = getCache('gloms_raw')
class Gloms:
def __init__(self, file_path):
self.file_path = file_path
self.file_list = glob.glob(self.file_path)
self.num = len(self.file_list)
ims = torch.tensor(
[imageio.volread(file_name) for file_name in self.file_list],
dtype=torch.float32,
device=device)
self.images = ims
def show_glom(self, glom_id, cmap="gray", step=1):
# print(glom_id)im3d = util.img_as_float(im[:, :, :])
import SimpleITK as sitk
import numpy as np
import torch
import torch.cuda
from torch.utils.data import Dataset
from util.disk import getCache
from util.util import XyzTuple, xyz2irc
from util.logconf import logging
log = logging.getLogger(__name__)
log.setLevel(logging.INFO)
raw_cache = getCache('part2ch9_raw')
NoduleInfoTuple = namedtuple('NoduleInfoTuple', 'isMalignant_bool',
'diameter_mm', 'series_uid', 'center_xyz')
@functools.lru_cache(1)
def getNoduleInfoList(requireDataOnDisk_bool=True):
# We construct a set with all series_uids that are present on disk.
# This will let us use the data, even if we haven't downloaded all
# of the subsets yet.
mhd_list = glob.glob("data-unversioned/part2/luna/subset*/*.mhd")
dataPresentOnDisk_set = {os.path.split(p)[-1][:-4] for p in mhd_list}
diameter_dict = {}
with open("data/part2/luna/annotations.csv", 'r') as f:
import csv, copy
import functools
import glob
import os
from collections import namedtuple
import SimpleITK as sitk
import numpy as np
import torch as torch
from torch.utils.data import Dataset
from util.utils import xyz2irc, irc2xyz, XyzTuple, IrcTuple
from util.disk import getCache
import log
raw_cache = getCache('luna_raw')
logger = log.setup_custom_logger(__name__)
CandidateInfoTuple = namedtuple(
'CandidateInfoTuple',
'isNodule_bool, diameter_mm, series_uid, center_xyz',
)
@functools.lru_cache(1)
def get_candidate_info_list(requireOnDisk_bool=True):
mhd_list = glob.glob('data/subset*/*.mhd')
presentOnDisk_set = {os.path.split(p)[-1][:-4] for p in mhd_list}
diameter_dict = {}
with open('data/annotations.csv') as f:
import numpy as np
import torch
import torch.cuda
from torch.utils.data import Dataset
from util.disk import getCache
from util.util import XyzTuple, xyz2irc
from util.logconf import logging
log = logging.getLogger(__name__)
# log.setLevel(logging.WARN)
log.setLevel(logging.INFO)
log.setLevel(logging.DEBUG)
cache = getCache('p2ch1')
class Ct(object):
def __init__(self, series_uid):
mhd_path = glob.glob('data/luna/subset*/{}.mhd'.format(series_uid))[0]
ct_mhd = sitk.ReadImage(mhd_path)
ct_ary = np.array(sitk.GetArrayFromImage(ct_mhd), dtype=np.float32)
# CTs are natively expressed in https://en.wikipedia.org/wiki/Hounsfield_scale
# HU are scaled oddly, with 0 g/cc (air, approximately) being -1000 and 1 g/cc (water) being 0.
# This converts HU to g/cc.
ct_ary += 1000
ct_ary /= 1000
