Description

A pre-trained densenet121 model for disease pattern detection in chest x-rays.

Model Overview

The model is trained using a densenet121 model [1] for disease pattern detection in chest x-rays [2].

Data

This model is trained using PLCO training data and evaluated on the PLCO validation data.

You can apply for access to the dataset at: https://biometry.nci.nih.gov/cdas/learn/plco/images/

Training configuration

The provided training configuration required 12GB-memory GPUs. The training was performed with command train.sh, which required 12GB-memory GPUs.

Training Graph Input Shape: 256 x 256

Input and output formats

Input: 16-bit CXR png

Output: 15 binary labels, each bit is corresponding to the prediction of 'Nodule', 'Mass', 'Distortion of Pulmonary Architecture', 'Pleural Based Mass', 'Granuloma', 'Fluid in Pleural Space', 'Right Hilar Abnormality', 'Left Hilar Abnormality', 'Major Atelectasis', 'Infiltrate', 'Scarring', 'Pleural Fibrosis', 'Bone/Soft Tissue Lesion', 'Cardiac Abnormality', 'COPD'

Scores

This model achieves the following Dice score on the validation data

1. Averaged AUC over all disease categories: 0.8587

Availability

Sign in is required to access. This model is usable only as part of Transfer Learning & Annotation Tools in Clara Train SDK container. You can download the model from NGC registry as described in Getting Started Guide.

Disclaimer

This is an example, not to be used for diagnostic purposes

References

[1] Huang, Gao, et al. "Densely connected convolutional networks." Proceedings of the IEEE conference on computer vision and pattern recognition. 2017. https://arxiv.org/abs/1608.06993.

[2] Wang, Xiaosong, et al. "Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases." Proceedings of the IEEE conference on computer vision and pattern recognition. 2017. https://arxiv.org/abs/1705.02315.