Deep learning-based material decomposition of iodine and calcium in mobile photon counting detector CT
Authors:
Open Access
- 26 July 2024
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 19 (7) , e0306627
Abstract
Photon-counting detector (PCD)-based computed tomography (CT) offers several advantages over conventional energy-integrating detector-based CT. Among them, the ability to discriminate energy exhibits significant potential for clinical applications because it provides material-specific information. That is, material decomposition (MD) can be achieved through energy discrimination. In this study, deep learning-based material decomposition was performed using live animal data. We propose MD-Unet, which is a deep learning strategy for material decomposition based on an Unet architecture trained with data from three energy bins. To mitigate the data insufficiency, we developed a pretrained model incorporating various simulation data forms and augmentation strategies. Incorporating these approaches into model training results in enhanced precision in material decomposition, thereby enabling the identification of distinct materials at individual pixel locations. The trained network was applied to the acquired animal data to evaluate material decomposition results. Compared with conventional methods, the newly generated MD-Unet demonstrated more accurate material decomposition imaging. Moreover, the network demonstrated an improved material decomposition ability and significantly reduced noise. In addition, they can potentially offer an enhancement level similar to that of a typical contrast agent. This implies that it can acquire images of the same quality with fewer contrast agents administered to patients, thereby demonstrating its significant clinical value.Keywords
Funding Information
- Ministry of Health & Welfare, Republic of Korea (HT18C0005)
- Ministry of Science and ICT (2020M3H2A1076786)
- Ministry of Trade, Industry and Energy MOTIE, South Korea (1415187686)
- Korea government (No.2019-0-00421)
- Korea Institute for Advancement of Technology (P0023704)
This publication has 31 references indexed in Scilit:
- Edge loss functions for deep-learning depth-mapMachine Learning with Applications, 2022
- Feasibility study of portable multi-energy computed tomography with photon-counting detector for preclinical and clinical applicationsScientific Reports, 2021
- Single image super-resolution based on a modified U-net with mixed gradient lossSignal, Image and Video Processing, 2021
- COVID TV-Unet: Segmenting COVID-19 chest CT images using connectivity imposed UnetComputer Methods and Programs in Biomedicine Update, 2021
- Deep‐learning‐based direct inversion for material decompositionMedical Physics, 2020
- Image domain dual material decomposition for dual‐energy CT using butterfly networkMedical Physics, 2019
- Measurement of Glomerular Filtration Rate using Quantitative SPECT/CT and Deep-learning-based Kidney SegmentationScientific Reports, 2019
- Dual-Energy Computed Tomographic Applications for Differentiation of Intracranial Hemorrhage, Calcium, and IodineNeuroimaging Clinics Of North America, 2017
- Deep learningNature, 2015
- Abdominal rapid-kVp-switching dual-energy MDCT with reduced IV contrast compared to conventional MDCT with standard weight-based IV contrast: an intra-patient comparisonAbdominal Radiology, 2014