Estimation of Missing DICOM Windowing Parameters in High-Dynamic-Range Radiographs Using Deep Learning

Mateja Napravnik, Natali Bakotić, Franko Hržić, Damir Miletić and Ivan Štajduhar ()
Additional contact information
Mateja Napravnik: Faculty of Engineering, University of Rijeka, Vukovarska 58, 51000 Rijeka, Croatia
Natali Bakotić: Faculty of Engineering, University of Rijeka, Vukovarska 58, 51000 Rijeka, Croatia
Franko Hržić: Faculty of Engineering, University of Rijeka, Vukovarska 58, 51000 Rijeka, Croatia
Damir Miletić: Clinical Hospital Centre Rijeka, University of Rijeka, Krešimirova 42, 51000 Rijeka, Croatia
Ivan Štajduhar: Faculty of Engineering, University of Rijeka, Vukovarska 58, 51000 Rijeka, Croatia

Mathematics, 2025, vol. 13, issue 10, 1-16

Abstract: Digital Imaging and Communication in Medicine (DICOM) is a standard format for storing medical images, which are typically represented in higher bit depths (10–16 bits), enabling detailed representation but exceeding the display capabilities of standard displays and human visual perception. To address this, DICOM images are often accompanied by windowing parameters, analogous to tone mapping in High-Dynamic-Range image processing, which compress the intensity range to enhance diagnostically relevant regions. This study evaluates traditional histogram-based methods and explores the potential of deep learning for predicting window parameters in radiographs where such information is missing. A range of architectures, including MobileNetV3Small, VGG16, ResNet50, and ViT-B/16, were trained on high-bit-depth computed radiography images using various combinations of loss functions, including structural similarity (SSIM), perceptual loss (LPIPS), and an edge preservation loss. Models were evaluated based on multiple criteria, including pixel entropy preservation, Hellinger distance of pixel value distributions, and peak-signal-to-noise ratio after 8-bit conversion. The tested approaches were further validated on the publicly available GRAZPEDWRI-DX dataset. Although histogram-based methods showed satisfactory performance, especially scaling through identifying the peaks in the pixel value histogram, deep learning-based methods were better at selectively preserving clinically relevant image areas while removing background noise.

Keywords: DICOM 8-bit export; X-ray imaging; image entropy; bit depth reduction; high-dynamic-range compression (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/10/1596/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/10/1596/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:10:p:1596-:d:1654908

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().