Parameter choices in HaarPSI for IQA with medical images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Karner, Clemens, Gröhl, Janek, Selby, Ian, Babar, Judith, Beckford, Jake, Else, Thomas R, Sadler, Timothy J, Shahipasand, Shahab, Thavakumar, Arthikkaa, Roberts, Michael, Rudd, James H. F., Schönlieb, Carola-Bibiane, Weir-McCall, Jonathan R, Breger, Anna
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908492402524160
author Karner, Clemens
Gröhl, Janek
Selby, Ian
Babar, Judith
Beckford, Jake
Else, Thomas R
Sadler, Timothy J
Shahipasand, Shahab
Thavakumar, Arthikkaa
Roberts, Michael
Rudd, James H. F.
Schönlieb, Carola-Bibiane
Weir-McCall, Jonathan R
Breger, Anna
author_facet Karner, Clemens
Gröhl, Janek
Selby, Ian
Babar, Judith
Beckford, Jake
Else, Thomas R
Sadler, Timothy J
Shahipasand, Shahab
Thavakumar, Arthikkaa
Roberts, Michael
Rudd, James H. F.
Schönlieb, Carola-Bibiane
Weir-McCall, Jonathan R
Breger, Anna
contents When developing machine learning models, image quality assessment (IQA) measures are a crucial component for the evaluation of obtained output images. However, commonly used full-reference IQA (FR-IQA) measures have been primarily developed and optimized for natural images. In many specialized settings, such as medical images, this poses an often overlooked problem regarding suitability. In previous studies, the FR-IQA measure HaarPSI showed promising behavior regarding generalizability. The measure is based on Haar wavelet representations and the framework allows optimization of two parameters. So far, these parameters have been aligned for natural images. Here, we optimize these parameters for two medical image data sets, a photoacoustic and a chest X-ray data set, with IQA expert ratings. We observe that they lead to similar parameter values, different to the natural image data, and are more sensitive to parameter changes. We denote the novel optimized setting as HaarPSI$_{MED}$, which improves the performance of the employed medical images significantly (p<0.05). Additionally, we include an independent CT test data set that illustrates the generalizability of HaarPSI$_{MED}$, as well as visual examples that qualitatively demonstrate the improvement. The results suggest that adapting common IQA measures within their frameworks for medical images can provide a valuable, generalizable addition to employment of more specific task-based measures.
format Preprint
id arxiv_https___arxiv_org_abs_2410_24098
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Parameter choices in HaarPSI for IQA with medical images
Karner, Clemens
Gröhl, Janek
Selby, Ian
Babar, Judith
Beckford, Jake
Else, Thomas R
Sadler, Timothy J
Shahipasand, Shahab
Thavakumar, Arthikkaa
Roberts, Michael
Rudd, James H. F.
Schönlieb, Carola-Bibiane
Weir-McCall, Jonathan R
Breger, Anna
Image and Video Processing
Computer Vision and Pattern Recognition
When developing machine learning models, image quality assessment (IQA) measures are a crucial component for the evaluation of obtained output images. However, commonly used full-reference IQA (FR-IQA) measures have been primarily developed and optimized for natural images. In many specialized settings, such as medical images, this poses an often overlooked problem regarding suitability. In previous studies, the FR-IQA measure HaarPSI showed promising behavior regarding generalizability. The measure is based on Haar wavelet representations and the framework allows optimization of two parameters. So far, these parameters have been aligned for natural images. Here, we optimize these parameters for two medical image data sets, a photoacoustic and a chest X-ray data set, with IQA expert ratings. We observe that they lead to similar parameter values, different to the natural image data, and are more sensitive to parameter changes. We denote the novel optimized setting as HaarPSI$_{MED}$, which improves the performance of the employed medical images significantly (p<0.05). Additionally, we include an independent CT test data set that illustrates the generalizability of HaarPSI$_{MED}$, as well as visual examples that qualitatively demonstrate the improvement. The results suggest that adapting common IQA measures within their frameworks for medical images can provide a valuable, generalizable addition to employment of more specific task-based measures.
title Parameter choices in HaarPSI for IQA with medical images
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.24098