---
title: "Data-Centric AI for Chest X-Ray Analysis in Resource-Constrained Settings"
authors:
  - "Yasmeena Akhter"
doi: "10.24963/ijcai.2025/1237"
url: "https://ijcai.org/proceedings/2025/1237"
pdf: "https://ijcai.org/proceedings/2025/1237.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "10965-10966"
track: "Doctoral Consortium"
keywords:
  - "Computer Vision: CV: Transfer, low-shot, semi- and un- supervised learning"
  - "Multidisciplinary Topics and Applications: MDA: Computational sustainability"
  - "Computer Vision: CV: Machine learning for vision"
  - "Multidisciplinary Topics and Applications: MDA: Health and medicine"
  - "Machine Learning: ML: Applications"
  - "Machine Learning: ML: Attention models"
  - "Computer Vision: CV: Biomedical image analysis"
  - "Machine Learning: ML: Cost-sensitive learning"
  - "Machine Learning: ML: Classification"
  - "Machine Learning: ML: Ensemble methods"
  - "Computer Vision: CV: Applications"
  - "Machine Learning: ML: Multi-label"
  - "Machine Learning: ML: Convolutional networks"
  - "Computer Vision: CV: Representation learning"
  - "Machine Learning: ML: Representation learning"
  - "Machine Learning: ML: Multi-task and transfer learning"
---

# Data-Centric AI for Chest X-Ray Analysis in Resource-Constrained Settings

Yasmeena Akhter

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 10965-10966. DOI: [10.24963/ijcai.2025/1237](https://doi.org/10.24963/ijcai.2025/1237)

## Abstract

With approximately 2 billion chest X-ray examinations conducted globally each year, the demand for radiological interpretation far surpasses the available expertise, particularly in resource-constrained regions. Recent advancements in artificial intelligence and computer vision present promising solutions for automated chest X-ray analysis. Nevertheless, integrating AI-driven diagnostics into clinical practice encounters several challenges, including data-centric issues, implementation barriers, deployment complexities, and the need for trustworthy AI. This dissertation focuses on the data-centric aspect, making significant contributions through enhanced data collection, the creation of novel datasets, algorithm development, privacy-preserving collaborative learning, and modelling for low-resolution data. It offers practical methodologies for embedding AI into chest radiology workflows, with a particular emphasis on addressing underserved conditions and healthcare settings with limited data availability. Furthermore, this work illustrates how tailored AI solutions can democratize access to high-quality radiological care while balancing privacy considerations and operational constraints across diverse environments.