NIHR Global Health Research Unit on Respiratory Health (RESPIRE)

Computational framework to interpret chest X-rays and diagnose pneumonia

This project is based at Child Health Research Foundation in Bangladesh


  • Project title: Construction of a computational framework to automatically interpret chest X-rays and diagnose pneumonia
  • Acute or chronic:  Acute
  • Based at:  Child Health Research Foundation (CHRF)
  • Start date:  July 2018
  • End date:  August 2021
  • Principal investigator:  Professor Samir K Saha
  • Project team:  Professor Samir K Saha, Dr Senjuti Saha, Dr Mark Sun


It is estimated that 95% of the two million deaths due to pneumonia occur in developing countries. In Bangladesh alone, six million cases of pneumonia are diagnosed every year. Unfortunately, diagnostic methods to date lack sensitivity or are difficult to fully standardized. The lack of a reliable diagnostic hampers the execution of evidence based interventions, impacting the monitoring of interventions, like vaccines.

The “gold standard” for defining pneumonia are chest X-rays. However, the interpretations are subjective, sometimes requiring multiple radiologists/clinicians to reach a conclusive diagnosis. As there are few well-trained radiologists/clinicians in resource-poor settings, having a tool to aid in the diagnosis of pneumonia would be invaluable in the impact monitoring of interventions.

Aim and impact

The aim of the project is to construct a computational framework to automatically and systematically interpret paediatric chest X-rays to diagnose pneumonia. 

The automated diagnostic system will enable members of the broader community, such as health care workers in areas without experts, to efficiently diagnose pneumonia. If successful, it will eventually incentivise the use of chest x-ray as the go-to diagnostic for evidence-based interventions.

Additionally, this project will aid in clinical studies aiming to monitor the impact of interventions like vaccines, support patient management by providing real-time interpretations, and to facilitate antibiotic stewardship.

Key developments

  • Readers have begun assessing a bank of paediatric x-ray images to create a training set. 
  • Performance assessment of the computational prediction model is underway. The model is being evaluated using two additional data sites - Kumudini Women’s Medical College and Hospital study site (KMWCH, rural Bangladesh) and 47 images from the Institute of Child and Mother Health (ICMH, urban Dhaka).
  • Organised a workshop in September 2019 to discuss their study with pulmonologists, chest physicians, radiologists, paediatricians, GPs, microbiologists and computer scientists.
  • Organised a seminar in November 2019 on respiratory disease burden and RESPIRE research for 200 participants, including chest physicians, pulmonologists, paediatricians, GPs, researchers, and journalists.
  • Held a public rally on World Pneumonia Day 2019 with 300 participants.
  • Established a patient advisory group to provide feedback and input into research studies.
  • A protocol paper titled “A study protocol and design for the assessment of paediatric pneumonia from X-Ray images using deep learning” has been published in BMJ Open Protocols.

Project data

Download the project data management plan 

View the project metadata on the Health Data Research Innovation Gateway