# AMIA Public Challenge 2024 — Data

来源：https://www.kaggle.com/competitions/amia-public-challenge-2024/data

采集时间：2026-10-19T06:28:46Z

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
```