In this competition, we are classifying common thoracic lung diseases and localizing critical findings. This is an object detection and classification problem.

For each test image, you will be predicting a bounding box and class for all findings. If you predict that there are no findings, you should create a prediction of "14 1 0 0 1 1" (14 is the class ID for no finding, and this provides a one-pixel bounding box with a confidence of 1.0).

The images are in PNG format (already converted from DICOM for you) and resized to 1024x1024 pixels.

## Dataset information
The dataset comprises 15,000 postero-anterior (PA) CXR scans in PNG format.
All images were labeled by a panel of experienced radiologists for the presence of 14 critical radiographic findings as listed below:

```
0 - Aortic enlargement
1 - Atelectasis
2 - Calcification
3 - Cardiomegaly
4 - Consolidation
5 - ILD
6 - Infiltration
7 - Lung Opacity
8 - Nodule/Mass
9 - Other lesion
10 - Pleural effusion
11 - Pleural thickening
12 - Pneumothorax
13 - Pulmonary fibrosis
```
The "No finding" observation (14) was intended to capture the absence of all findings above.

Note that a key part of this competition is working with ground truth from multiple radiologists.

## Files
* **train.csv** - the train set metadata, with one row for each object, including a class and a bounding box. Some images in both test and train have multiple objects (several rows with respect the same image).

* **test.csv** - the test set metadata, only containing the filenames.
* **img_size.csv** - the original dimensions of the files: dim0 is the height and dim1 is the width.
* **sample_submission.csv** - sample submission (similar to test.csv) with dummy results. 

## Columns
```
image_id - unique image identifier
class_name - the name of the class of detected object (or "No finding")
class_id - the ID of the class of detected object
rad_id - the ID of the radiologist that made the observation
x_min - minimum X coordinate of the object's bounding box
y_min - minimum Y coordinate of the object's bounding box
x_max - maximum X coordinate of the object's bounding box
y_max - maximum Y coordinate of the object's bounding box
```