|
1
|
|
|
import urllib.parse |
|
2
|
|
|
from .. import Subject, ScalarImage, LabelMap, DATA_REPO |
|
3
|
|
|
from ..data.io import read_matrix |
|
4
|
|
|
from ..download import download_url |
|
5
|
|
|
from ..utils import get_torchio_cache_dir |
|
6
|
|
|
|
|
7
|
|
|
|
|
8
|
|
|
class FPG(Subject): |
|
9
|
|
|
"""3T :math:`T_1`-weighted brain MRI and corresponding parcellation. |
|
10
|
|
|
|
|
11
|
|
|
Args: |
|
12
|
|
|
load_all: If ``True``, three more images will be loaded: a |
|
13
|
|
|
:math:`T_2`-weighted MRI, a diffusion MRI and a functional MRI. |
|
14
|
|
|
""" |
|
15
|
|
|
def __init__(self, load_all: bool = False): |
|
16
|
|
|
repo_dir = urllib.parse.urljoin(DATA_REPO, 'fernando/') |
|
17
|
|
|
|
|
18
|
|
|
self.filenames = { |
|
19
|
|
|
't1': 't1.nii.gz', |
|
20
|
|
|
'seg': 't1_seg_gif.nii.gz', |
|
21
|
|
|
'rigid': 't1_to_mni.tfm', |
|
22
|
|
|
'affine': 't1_to_mni_affine.h5', |
|
23
|
|
|
} |
|
24
|
|
|
if load_all: |
|
25
|
|
|
self.filenames['t2'] = 't2.nii.gz' |
|
26
|
|
|
self.filenames['fmri'] = 'fmri.nrrd' |
|
27
|
|
|
self.filenames['dmri'] = 'dmri.nrrd' |
|
28
|
|
|
|
|
29
|
|
|
download_root = get_torchio_cache_dir() / 'fpg' |
|
30
|
|
|
for filename in self.filenames.values(): |
|
31
|
|
|
download_url( |
|
32
|
|
|
urllib.parse.urljoin(repo_dir, filename), |
|
33
|
|
|
download_root, |
|
34
|
|
|
filename=filename, |
|
35
|
|
|
) |
|
36
|
|
|
|
|
37
|
|
|
rigid = read_matrix(download_root / self.filenames['rigid']) |
|
38
|
|
|
affine = read_matrix(download_root / self.filenames['affine']) |
|
39
|
|
|
subject_dict = { |
|
40
|
|
|
't1': ScalarImage( |
|
41
|
|
|
download_root / self.filenames['t1'], |
|
42
|
|
|
rigid_matrix=rigid, |
|
43
|
|
|
affine_matrix=affine, |
|
44
|
|
|
), |
|
45
|
|
|
'seg': LabelMap( |
|
46
|
|
|
download_root / self.filenames['seg'], |
|
47
|
|
|
rigid_matrix=rigid, |
|
48
|
|
|
affine_matrix=affine, |
|
49
|
|
|
), |
|
50
|
|
|
} |
|
51
|
|
|
if load_all: |
|
52
|
|
|
subject_dict['t2'] = ScalarImage( |
|
53
|
|
|
download_root / self.filenames['t2']) |
|
54
|
|
|
subject_dict['fmri'] = ScalarImage( |
|
55
|
|
|
download_root / self.filenames['fmri']) |
|
56
|
|
|
subject_dict['dmri'] = ScalarImage( |
|
57
|
|
|
download_root / self.filenames['dmri']) |
|
58
|
|
|
super().__init__(subject_dict) |
|
59
|
|
|
self.gif_colors = GIF_COLORS |
|
60
|
|
|
|
|
61
|
|
|
def plot(self, *args, **kwargs): |
|
62
|
|
|
super().plot(*args, **kwargs, cmap_dict={'seg': self.gif_colors}) |
|
63
|
|
|
|
|
64
|
|
|
|
|
65
|
|
|
GIF_COLORS = { |
|
66
|
|
|
0: (0, 0, 0), |
|
67
|
|
|
1: (0, 0, 0), |
|
68
|
|
|
5: (127, 255, 212), |
|
69
|
|
|
12: (240, 230, 140), |
|
70
|
|
|
16: (176, 48, 96), |
|
71
|
|
|
24: (48, 176, 96), |
|
72
|
|
|
31: (48, 176, 96), |
|
73
|
|
|
32: (103, 255, 255), |
|
74
|
|
|
33: (103, 255, 255), |
|
75
|
|
|
35: (238, 186, 243), |
|
76
|
|
|
36: (119, 159, 176), |
|
77
|
|
|
37: (122, 186, 220), |
|
78
|
|
|
38: (122, 186, 220), |
|
79
|
|
|
39: (96, 204, 96), |
|
80
|
|
|
40: (96, 204, 96), |
|
81
|
|
|
41: (220, 247, 164), |
|
82
|
|
|
42: (220, 247, 164), |
|
83
|
|
|
43: (205, 62, 78), |
|
84
|
|
|
44: (205, 62, 78), |
|
85
|
|
|
45: (225, 225, 225), |
|
86
|
|
|
46: (225, 225, 225), |
|
87
|
|
|
47: (60, 60, 60), |
|
88
|
|
|
48: (220, 216, 20), |
|
89
|
|
|
49: (220, 216, 20), |
|
90
|
|
|
50: (196, 58, 250), |
|
91
|
|
|
51: (196, 58, 250), |
|
92
|
|
|
52: (120, 18, 134), |
|
93
|
|
|
53: (120, 18, 134), |
|
94
|
|
|
54: (255, 165, 0), |
|
95
|
|
|
55: (255, 165, 0), |
|
96
|
|
|
56: (12, 48, 255), |
|
97
|
|
|
57: (12, 48, 225), |
|
98
|
|
|
58: (236, 13, 176), |
|
99
|
|
|
59: (236, 13, 176), |
|
100
|
|
|
60: (0, 118, 14), |
|
101
|
|
|
61: (0, 118, 14), |
|
102
|
|
|
62: (165, 42, 42), |
|
103
|
|
|
63: (165, 42, 42), |
|
104
|
|
|
64: (160, 32, 240), |
|
105
|
|
|
65: (160, 32, 240), |
|
106
|
|
|
66: (56, 192, 255), |
|
107
|
|
|
67: (56, 192, 255), |
|
108
|
|
|
70: (255, 225, 225), |
|
109
|
|
|
72: (184, 237, 194), |
|
110
|
|
|
73: (180, 231, 250), |
|
111
|
|
|
74: (225, 183, 231), |
|
112
|
|
|
76: (180, 180, 180), |
|
113
|
|
|
77: (180, 180, 180), |
|
114
|
|
|
81: (245, 255, 200), |
|
115
|
|
|
82: (255, 230, 255), |
|
116
|
|
|
83: (245, 245, 245), |
|
117
|
|
|
84: (220, 255, 220), |
|
118
|
|
|
85: (220, 220, 220), |
|
119
|
|
|
86: (200, 255, 255), |
|
120
|
|
|
87: (250, 220, 200), |
|
121
|
|
|
89: (245, 255, 200), |
|
122
|
|
|
90: (255, 230, 255), |
|
123
|
|
|
91: (245, 245, 245), |
|
124
|
|
|
92: (220, 255, 220), |
|
125
|
|
|
93: (220, 220, 220), |
|
126
|
|
|
94: (200, 255, 255), |
|
127
|
|
|
96: (140, 125, 255), |
|
128
|
|
|
97: (140, 125, 255), |
|
129
|
|
|
101: (255, 62, 150), |
|
130
|
|
|
102: (255, 62, 150), |
|
131
|
|
|
103: (160, 82, 45), |
|
132
|
|
|
104: (160, 82, 45), |
|
133
|
|
|
105: (165, 42, 42), |
|
134
|
|
|
106: (165, 42, 42), |
|
135
|
|
|
107: (205, 91, 69), |
|
136
|
|
|
108: (205, 91, 69), |
|
137
|
|
|
109: (100, 149, 237), |
|
138
|
|
|
110: (100, 149, 237), |
|
139
|
|
|
113: (135, 206, 235), |
|
140
|
|
|
114: (135, 206, 235), |
|
141
|
|
|
115: (250, 128, 114), |
|
142
|
|
|
116: (250, 128, 114), |
|
143
|
|
|
117: (255, 255, 0), |
|
144
|
|
|
118: (255, 255, 0), |
|
145
|
|
|
119: (221, 160, 221), |
|
146
|
|
|
120: (221, 160, 221), |
|
147
|
|
|
121: (0, 238, 0), |
|
148
|
|
|
122: (0, 238, 0), |
|
149
|
|
|
123: (205, 92, 92), |
|
150
|
|
|
124: (205, 92, 92), |
|
151
|
|
|
125: (176, 48, 96), |
|
152
|
|
|
126: (176, 48, 96), |
|
153
|
|
|
129: (152, 251, 152), |
|
154
|
|
|
130: (152, 251, 152), |
|
155
|
|
|
133: (50, 205, 50), |
|
156
|
|
|
134: (50, 205, 50), |
|
157
|
|
|
135: (0, 100, 0), |
|
158
|
|
|
136: (0, 100, 0), |
|
159
|
|
|
137: (173, 216, 230), |
|
160
|
|
|
138: (173, 216, 230), |
|
161
|
|
|
139: (153, 50, 204), |
|
162
|
|
|
140: (153, 50, 204), |
|
163
|
|
|
141: (160, 32, 240), |
|
164
|
|
|
142: (160, 32, 240), |
|
165
|
|
|
143: (0, 206, 208), |
|
166
|
|
|
144: (0, 206, 208), |
|
167
|
|
|
145: (51, 50, 135), |
|
168
|
|
|
146: (51, 50, 135), |
|
169
|
|
|
147: (135, 50, 74), |
|
170
|
|
|
148: (135, 50, 74), |
|
171
|
|
|
149: (218, 112, 214), |
|
172
|
|
|
150: (218, 112, 214), |
|
173
|
|
|
151: (240, 230, 140), |
|
174
|
|
|
152: (240, 230, 140), |
|
175
|
|
|
153: (255, 255, 0), |
|
176
|
|
|
154: (255, 255, 0), |
|
177
|
|
|
155: (255, 110, 180), |
|
178
|
|
|
156: (255, 110, 180), |
|
179
|
|
|
157: (0, 255, 255), |
|
180
|
|
|
158: (0, 255, 255), |
|
181
|
|
|
161: (100, 50, 100), |
|
182
|
|
|
162: (100, 50, 100), |
|
183
|
|
|
163: (178, 34, 34), |
|
184
|
|
|
164: (178, 34, 34), |
|
185
|
|
|
165: (255, 0, 255), |
|
186
|
|
|
166: (255, 0, 255), |
|
187
|
|
|
167: (39, 64, 139), |
|
188
|
|
|
168: (39, 64, 139), |
|
189
|
|
|
169: (255, 99, 71), |
|
190
|
|
|
170: (255, 99, 71), |
|
191
|
|
|
171: (255, 69, 0), |
|
192
|
|
|
172: (255, 69, 0), |
|
193
|
|
|
173: (210, 180, 140), |
|
194
|
|
|
174: (210, 180, 140), |
|
195
|
|
|
175: (0, 255, 127), |
|
196
|
|
|
176: (0, 255, 127), |
|
197
|
|
|
177: (74, 155, 60), |
|
198
|
|
|
178: (74, 155, 60), |
|
199
|
|
|
179: (255, 215, 0), |
|
200
|
|
|
180: (255, 215, 0), |
|
201
|
|
|
181: (238, 0, 0), |
|
202
|
|
|
182: (238, 0, 0), |
|
203
|
|
|
183: (46, 139, 87), |
|
204
|
|
|
184: (46, 139, 87), |
|
205
|
|
|
185: (238, 201, 0), |
|
206
|
|
|
186: (238, 201, 0), |
|
207
|
|
|
187: (102, 205, 170), |
|
208
|
|
|
188: (102, 205, 170), |
|
209
|
|
|
191: (255, 218, 185), |
|
210
|
|
|
192: (255, 218, 185), |
|
211
|
|
|
193: (238, 130, 238), |
|
212
|
|
|
194: (238, 130, 238), |
|
213
|
|
|
195: (255, 165, 0), |
|
214
|
|
|
196: (255, 165, 0), |
|
215
|
|
|
197: (255, 192, 203), |
|
216
|
|
|
198: (255, 192, 203), |
|
217
|
|
|
199: (244, 222, 179), |
|
218
|
|
|
200: (244, 222, 179), |
|
219
|
|
|
201: (208, 32, 144), |
|
220
|
|
|
202: (208, 32, 144), |
|
221
|
|
|
203: (34, 139, 34), |
|
222
|
|
|
204: (34, 139, 34), |
|
223
|
|
|
205: (125, 255, 212), |
|
224
|
|
|
206: (127, 255, 212), |
|
225
|
|
|
207: (0, 0, 128), |
|
226
|
|
|
208: (0, 0, 128), |
|
227
|
|
|
} |
|
228
|
|
|
|
fepegar /
torchio
