- Use cases
-
1. Preprocessing
- SageMaker Object Detection preprocessing
- Rekognition Object Detection preprocessing
- SageMaker Kmeans preprocessing
- Autopilot preprocessing
- DeepAR preprocessing
- Personalize preprocessing
- Select, drop or extract Columns
- Split dataset to Train and Test
- Upload to s3
- Forecast preprocessing
- Rekognition Classification preprocessing
- SageMaker Image Classification preprocessing
- Xgboost preprocessing
- Blazingtext preprocessing
- Comprehend custom preprocessing
-
2. Training
- SageMaker Object Detection training
- Rekognition Object Detection training
- Forecast training
- Personalize training
- BlazingText training
- DeepAR training
- SageMaker Kmeans training
- Comprehend custom training
- Autopilot Training
- Xgboost Training
- Autogluon training
- Rekognition Classification training
- SageMaker Image Classification training
-
3. Inference
- SageMaker Object Detection inference
- Forecast inference
- Rekognition Object Detection inference
- Comprehend custom inference
- Personalize inference
- Autopilot Inference
- BlazingText Inference
- Custom SageMaker model Inference
- DeepAR Inference
- Rekognition Classification inference
- SageMaker Image Classification inference
- SageMaker Kmeans inference
- Xgboost Inference
- Contribute a use case or contact us for help.
- Frequently Asked Questions
Pneumonia detection from Chest X-ray images using SageMaker
Introduction
Chest X-ray images (anterior-posterior) were selected from retrospective cohorts of pediatric patients of one to five years old from Guangzhou Women and Children’s Medical Center, Guangzhou. All chest X-ray imaging was performed as part of patients’ routine clinical care.
For the analysis of chest x-ray images, all chest radiographs were initially screened for quality control by removing all low quality or unreadable scans. The diagnoses for the images were then graded by two expert physicians before being cleared for training the AI system. In order to account for any grading errors, the evaluation set was also checked by a third expert.
Acknowledgements
-
License: CC BY 4.0
-
Citation: http://www.cell.com/cell/fulltext/S0092-8674(18)30154-5
This data was obtained from Kaggle here
For folks who want to repeat this use case, the data is stored as a direct download here
Here is what a normal chest X-ray looks like:
… and here is what a pneumonia patient's chest X-ray looks like:
Assumptions
For this PoC, we will simplify the dataset by using only a subset of images. We will take the training data available on Kaggle, and use about 1000 images in each class (Normal and Pneumonia). While this is is 1/5th of the images available in the actual dataset, it is sufficient for us to showcase art of the possible. We followed steps outlined in Rekognition custom classification preprocessing and training for this PoC.