Explainable Image Quality Assessment for Medical Imaging
Medical image quality assessment is an important aspect of image acquisition, as poor-quality images may lead to misdiagnosis. Manual labelling of image quality is a tedious task for population studies and can lead to misleading results. While much research has been done on automated analysis of ima...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Medical image quality assessment is an important aspect of image acquisition,
as poor-quality images may lead to misdiagnosis. Manual labelling of image
quality is a tedious task for population studies and can lead to misleading
results. While much research has been done on automated analysis of image
quality to address this issue, relatively little work has been done to explain
the methodologies. In this work, we propose an explainable image quality
assessment system and validate our idea on two different objectives which are
foreign object detection on Chest X-Rays (Object-CXR) and Left Ventricular
Outflow Tract (LVOT) detection on Cardiac Magnetic Resonance (CMR) volumes. We
apply a variety of techniques to measure the faithfulness of the saliency
detectors, and our explainable pipeline relies on NormGrad, an algorithm which
can efficiently localise image quality issues with saliency maps of the
classifier. We compare NormGrad with a range of saliency detection methods and
illustrate its superior performance as a result of applying these methodologies
for measuring the faithfulness of the saliency detectors. We see that NormGrad
has significant gains over other saliency detectors by reaching a repeated
Pointing Game score of 0.853 for Object-CXR and 0.611 for LVOT datasets. |
---|---|
DOI: | 10.48550/arxiv.2303.14479 |