{"id":23343,"date":"2026-05-07T05:31:01","date_gmt":"2026-05-07T03:31:01","guid":{"rendered":"https:\/\/yulcom-technologies.com\/?p=23343"},"modified":"2026-05-07T07:01:35","modified_gmt":"2026-05-07T05:01:35","slug":"artificial-intelligence-and-chest-x-rays-researchers-from-yulcom-concordia-university-and-mcgill-university-publish-new-research-on-lung-disease-classification","status":"publish","type":"post","link":"https:\/\/yulcom-technologies.com\/en\/artificial-intelligence-and-chest-x-rays-researchers-from-yulcom-concordia-university-and-mcgill-university-publish-new-research-on-lung-disease-classification\/","title":{"rendered":"Artificial Intelligence and Chest X-Rays: Researchers from YULCOM, Concordia University, and McGill University Publish New Research on Lung Disease Classification"},"content":{"rendered":"

Artificial Intelligence and Chest X-ray Analysis: A Study Conducted by Researchers from YULCOM Technologies, Concordia University, and the McGill University on Multi-Label Classification of Pulmonary Diseases<\/strong><\/h4>\n

The R&D team at YULCOM Technologies<\/strong> contributed to the research and authorship of the paper titled \u201cClinically-Inspired Hierarchical Multi-Label Classification of Chest X-rays with a Penalty-Based Loss Function.\u201d<\/em><\/p>\n

 <\/p>\n

This work, co-authored by YULCOM\u2019s R&D team in collaboration with Concordia University (Gina Cody School of Engineering and Computer Science) and the Division of Radiation Oncology at the McGill University Health Centre, was supported by a Canadian NSERC Discovery Grant (RGPIN-2017-06722).<\/p>\n

The paper is available on arXiv<\/a>.<\/p>\n

 <\/p>\n

Researchers Mehrdad Asadi, Komi Sodok\u00e9, PhD, Ian J. Gerard, and Marta Kersten-Oertel, PhD, propose an artificial intelligence (AI) approach for multi-label classification of chest X-rays (CXR), aiming to improve diagnostic accuracy while enhancing clinical interpretability.<\/p>\n

 <\/p>\n

In the medical field, AI is increasingly positioned as a decision-support tool to address key challenges such as radiologist workload, variability in interpretations, and the risk of diagnostic errors. However, conventional AI approaches face important limitations, particularly their inability to model clinical relationships between diseases and their lack of transparency.<\/p>\n

To overcome these challenges, the research team introduces a clinically inspired hierarchical approach that mirrors medical reasoning. Diseases are structured according to a hierarchy reflecting real-world pathological relationships. In addition, the authors propose a novel loss function\u2014Hierarchical Binary Cross-Entropy (HBCE)\u2014which penalizes inconsistencies in predictions (for example, predicting a specific condition without its broader category), thereby producing results that are more clinically coherent.<\/p>\n

The proposed model is based on a deep learning architecture trained on the CheXpert<\/strong> dataset. It also incorporates mechanisms to enhance interpretability, including:<\/p>\n