This competition is a binary classification of normal vs pneumonia. You will have to predict the patients are normal or has pneumonia from their chest X-rays.
Video description of the challenge
Among the medical imaging examinations, chest X-rays are the most common. Each year, there are 3.6 billion medical procedures involving ionizing radiation, of which over 2 billion are chest X-rays . Pneumonia is one among the many diseases that chest X-ray can help to detect. Every year in the US, pneumonia causes hospitalization of more than 1 million adults, and kills around 50 000. Detecting pneumonia is a difficult task which requires expertise of radiologists. However, there is always a shortage of radiologists to interpret the X-ray results. Moreover, fatigue due to heavy workload may also deteriorate the diagnostic accuracy of radiologists.
Automatic interpretation of chest X-ray would bring numerous substantial benefits, but it is also a challenging task. Lung opacity may be vague and very similar to minor benign anomalies. Variation in radiation settings may also make an image look more hazy in general.
The challenge was inspired by 2018 RSNA Pneumonia Detection Challenge. Excluding the No lung opacity / Not normal category, we propose a binary classification task of normal vs pneumonia for our participants. Participants should build a model able to learn from the training data and make predictions on unseen data.
Data:
https://www.kaggle.com/kmader/lung-opacity-overview
https://www.kaggle.com/uzairshahmdn/rsna-pneumonia-detection-stage-2-jpeg-images
https://www.kaggle.com/sovitrath/rsna-pneumonia-detection-2018
Icon:
https://www.iconfinder.com/iconsets/health-and-medical-35
Instructors: Isabelle Guyon, Kim Gerdes.
The competition was designed by Hygieia, whose group members: Phan Anh Vu, Alejandro de la Cruz López, Paavo Camps, Xinwen Xu, Nour Jemli.
This is a binary classification problem. The dataset contain input and labels for training. You have to build a model to label every row of the validation set and the test set with 0(normal) or 1(lung opacity). You need to upload your predictions for validation and test set
The submissions are evaluated by accuracy. We also encourage you to compute other metrics such as precision and recall.
Submissions must be made before the end of phase 1. You may submit 5 submissions every day and 100 in total.
This challenge is for educational purposes only and no prizes are granted. It is governed by the general ChaLearn contest rules.
Start: Nov. 15, 2018, midnight
Description: Development phase: tune your models and submit prediction results, trained model, or untrained model.
Start: April 30, 2050, midnight
Description: Final phase (no submission, your last submission from the previous phase is automatically forwarded).
Never
You must be logged in to participate in competitions.
Sign In# | Username | Score |
---|---|---|
1 | mevrard | 0.8910 |
2 | Thibaut | 0.8835 |
3 | saulo_msantos | 0.8835 |