Eprint first made available on ORBilu (E-prints, Working papers and Research blog)
Towards Generalizable Machine Learning for Chest X-ray Diagnosis with Multi-task learning
Ghamizi, Salah; Garcia Santa Cruz, Beatriz; Temple, Paul et al.
2022
 

Files


Full Text
Towards Generalizable Machine Learning for Chest X-ray Diagnosis with Multitask Learning.pdf
Publisher postprint (4.11 MB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Abstract :
[en] Clinicians use chest radiography (CXR) to diagnose common pathologies. Automated classification of these diseases can expedite analysis workflow, scale to growing numbers of patients and reduce healthcare costs. While research has produced classification models that perform well on a given dataset, the same models lack generalization on different datasets. This reduces confidence that these models can be reliably deployed across various clinical settings. We propose an approach based on multitask learning to improve model generalization. We demonstrate that learning a (main) pathology together with an auxiliary pathology can significantly impact generalization performance (between -10% and +15% AUC-ROC). A careful choice of auxiliary pathology even yields competitive performance with state-of-the-art models that rely on fine-tuning or ensemble learning, using between 6% and 34% of the training data that these models required. We, further, provide a method to determine what is the best auxiliary task to choose without access to the target dataset. Ultimately, our work makes a big step towards the creation of CXR diagnosis models applicable in the real world, through the evidence that multitask learning can drastically improve generalization.
Disciplines :
Computer science
Author, co-author :
Ghamizi, Salah ;  University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)
Garcia Santa Cruz, Beatriz ;  University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB)
Temple, Paul
Cordy, Maxime  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SerVal
Perrouin, Gilles
Papadakis, Mike ;  University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)
Le Traon, Yves ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SerVal
Language :
English
Title :
Towards Generalizable Machine Learning for Chest X-ray Diagnosis with Multi-task learning
Publication date :
February 2022
Number of pages :
18
Focus Area :
Security, Reliability and Trust
FnR Project :
FNR12669767 - Testing Self-learning Systems, 2018 (01/09/2019-31/08/2022) - Yves Le Traon
Available on ORBilu :
since 15 April 2022

Statistics


Number of views
246 (30 by Unilu)
Number of downloads
170 (11 by Unilu)

Bibliography


Similar publications



Contact ORBilu