Radiology· 2017Q1

Deep Learning at Chest Radiography: Automated Classification of Pulmonary Tuberculosis by Using Convolutional Neural Networks

Paras Lakhani, Baskaran Sundaram

1,808citations
Q1SCImago
2017year

Short summary

A deep learning model achieved 92.5% accuracy in classifying pulmonary tuberculosis from chest radiographs, outperforming radiologists in a reader study.

AI-generated from the title and abstract; the full text is not read.

Key points

A deep learning model achieved 92.5% accuracy (AUC) in classifying pulmonary tuberculosis from chest radiographs.
The model was trained on a dataset of over 1,000 chest X-rays.
In a reader study, the deep learning model outperformed three radiologists.
The findings suggest deep learning can serve as a valuable tool for TB diagnosis.

AI-generated from the title and abstract; the full text is not read.