File size: 8,370 Bytes
6f7f115
 
 
 
 
458f5af
6f7f115
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9ea4504
6f7f115
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9ea4504
6f7f115
 
 
 
 
 
 
 
 
 
 
 
 
 
9ea4504
6f7f115
 
 
 
 
 
 
 
 
 
 
 
 
 
458f5af
6f7f115
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9ea4504
 
6f7f115
 
9ea4504
6f7f115
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
import os

import pandas as pd
import torch
from torch.utils.data import Dataset
from torchvision.io import read_image

from tools.utils import mimic_cxr_image_path

# Ordered by oblique, lateral, AP, and then PA views so that PA views are closest in position to the generated tokens (and oblique is furtherest).
VIEW_ORDER = ['LPO', 'RAO', 'LAO', 'SWIMMERS', 'XTABLE LATERAL', 'LL', 'LATERAL',  'AP AXIAL', 'AP RLD', 'AP LLD', 'AP', 'PA RLD', 'PA LLD', 'PA']


class StudyIDEDStayIDSubset(Dataset):
    """
    Study ID & ED stay ID subset. Examples are indexed by the study identifier.
    Information from the ED module is added by finding the study_id that is within 
    the timespan of the stay_id for the subject_id. The history and indication 
    sections are also included.
    """
    def __init__(
        self, 
        split, 
        records,
        dataset_dir=None, 
        max_images_per_study=None,
        transforms=None, 
        images=True,
        columns='study_id, dicom_id, subject_id, findings, impression',
        and_condition='',
        study_id_inclusion_list=None,
        return_images=True,
        ed_module=True,
        extension='jpg',
    ):
        """
        Argument/s:
            split - 'train', 'validate', or 'test'.
            dataset_dir - Dataset directory.
            records - MIMIC-CXR & MIMIC-IV-ED records class instance.
            max_images_per_study - the maximum number of images per study.
            transforms - torchvision transformations.
            colour_space - PIL target colour space.
            images - flag to return processed images.
            columns - which columns to query on.
            and_condition - AND condition to add to the SQL query.
            study_id_inclusion_list - studies not in this list are excluded.
            return_images - return CXR images for the study as tensors.
            ed_module - use the ED module.
            extension - 'jpg' or 'dcm'.
        """
        super(StudyIDEDStayIDSubset, self).__init__()
        self.split = split
        self.dataset_dir = dataset_dir
        self.records = records
        self.max_images_per_study = max_images_per_study
        self.transforms = transforms
        self.images = images
        self.columns = columns
        self.and_condition = and_condition
        self.return_images = return_images
        self.ed_module = ed_module
        self.extension = extension
        
        # If max images per study is not set:
        self.max_images_per_study = float('inf') if self.max_images_per_study is None else self.max_images_per_study

        assert self.extension == 'jpg' or self.extension == 'dcm'

        if self.dataset_dir is not None:
            if self.extension == 'jpg':
                if 'physionet.org/files/mimic-cxr-jpg/2.0.0/files' not in self.dataset_dir:
                    self.dataset_dir = os.path.join(self.dataset_dir, 'physionet.org/files/mimic-cxr-jpg/2.0.0/files')
            elif self.extension == 'dcm':
                if 'physionet.org/files/mimic-cxr/2.0.0/files' not in self.dataset_dir:
                    self.dataset_dir = os.path.join(self.dataset_dir, 'physionet.org/files/mimic-cxr/2.0.0/files')

        query = f"""
        SELECT {columns}
        FROM mimic_cxr 
        WHERE split = '{split}' 
        {and_condition}
        ORDER BY study_id
        """

        # For multi-image, the study identifiers make up the training examples:
        df = self.records.connect.sql(query).df()

        # Drop studies that don't have a findings or impression section:
        df = df.dropna(subset=['findings', 'impression'], how='any')

        # This study has two rows in edstays (removed as it causes issues):
        if self.ed_module:
            df = df[df['study_id'] != 59128861]

        # Exclude studies not in list:
        if study_id_inclusion_list is not None:
            df = df[df['study_id'].isin(study_id_inclusion_list)]

        # Example study identifiers for the subset:
        self.examples = df['study_id'].unique().tolist()

        # Record statistics:
        self.num_study_ids = len(self.examples)
        self.num_dicom_ids = len(df['dicom_id'].unique().tolist())
        self.num_subject_ids = len(df['subject_id'].unique().tolist())

    def __len__(self):
        return self.num_study_ids

    def __getitem__(self, index):

        study_id = self.examples[index]

        # Get the study:
        study = self.records.connect.sql(
            f"""
            SELECT dicom_id, study_id, subject_id, study_datetime, ViewPosition
            FROM mimic_cxr 
            WHERE (study_id = {study_id});
            """
        ).df()
        subject_id = study.iloc[0, study.columns.get_loc('subject_id')]
        study_id = study.iloc[0, study.columns.get_loc('study_id')]
        study_datetime = study['study_datetime'].max()

        example_dict = {
            'study_ids': study_id,
            'subject_id': subject_id,
            'index': index,
        }

        example_dict.update(self.records.return_mimic_cxr_features(study_id))

        if self.ed_module:
            edstays = self.records.connect.sql(
                f"""
                SELECT stay_id, intime, outtime
                FROM edstays 
                WHERE (subject_id = {subject_id})
                AND intime < '{study_datetime}'
                AND outtime > '{study_datetime}';
                """
            ).df()

            assert len(edstays) <= 1
            stay_id = edstays.iloc[0, edstays.columns.get_loc('stay_id')] if not edstays.empty else None
            self.records.clear_start_end_times()
            example_dict.update(self.records.return_ed_module_features(stay_id, study_datetime))

            example_dict['stay_ids'] = stay_id

        if self.return_images:
            example_dict['images'], example_dict['image_time_deltas'] = self.get_images(study, study_datetime)

        return example_dict

    def get_images(self, example, reference_time):
        """
        Get the image/s for a given example. 

        Argument/s:
            example - dataframe for the example.
            reference_time - reference_time for time delta.

        Returns:
            The image/s for the example
        """

        # Sample if over max_images_per_study. Only allowed during training:
        if len(example) > self.max_images_per_study:
            assert self.split == 'train'
            example = example.sample(n=self.max_images_per_study, axis=0)

        # Order by ViewPostion:
        example['ViewPosition'] = example['ViewPosition'].astype(pd.CategoricalDtype(categories=VIEW_ORDER, ordered=True))
        
        # Sort the DataFrame based on the categorical column
        example = example.sort_values(by=['study_datetime', 'ViewPosition'])

        # Load and pre-process each CXR:
        images, time_deltas = [], []
        for _, row in example.iterrows():
            images.append(
                self.load_and_preprocess_image(
                    row['subject_id'], 
                    row['study_id'], 
                    row['dicom_id'], 
                ),
            )
            time_deltas.append(self.records.compute_time_delta(row['study_datetime'], reference_time, to_tensor=False))
                
        if self.transforms is not None:
            images = torch.stack(images, 0)
        return images, time_deltas

    def load_and_preprocess_image(self, subject_id, study_id, dicom_id):
        """
        Load and preprocess an image using torchvision.transforms.v2:
            https://pytorch.org/vision/stable/auto_examples/transforms/plot_transforms_getting_started.html#sphx-glr-auto-examples-transforms-plot-transforms-getting-started-py

        Argument/s:
            subject_id - subject identifier.
            study_id - study identifier.
            dicom_id - DICOM identifier.

        Returns:
            image - Tensor of the CXR.
        """

        if self.extension == 'jpg':

            image_file_path = mimic_cxr_image_path(self.dataset_dir, subject_id, study_id, dicom_id, self.extension)
            image = read_image(image_file_path)

        elif self.extension == 'dcm':
            raise NotImplementedError

        if self.transforms is not None:
            image = self.transforms(image)

        return image