Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Machine learning-based prediction of conversion coefficients for I-123 metaiodobenzylguanidine heart-to-mediastinum ratio

Okuda, Koichi ; Nakajima, Kenichi ; Kitamura, Chiemi ; Ljungberg, Michael LU ; Hosoya, Tetsuo ; Kirihara, Yumiko and Hashimoto, Mitsumasa (2023) In Journal of Nuclear Cardiology 30(4). p.1630-1641
Abstract

Purpose: We developed a method of standardizing the heart-to-mediastinal ratio in 123I-labeled meta-iodobenzylguanidine (MIBG) images using a conversion coefficient derived from a dedicated phantom. This study aimed to create a machine-learning (ML) model to estimate conversion coefficients without using a phantom. Methods: 210 Monte Carlo (MC) simulations of 123I-MIBG images to obtain conversion coefficients using collimators that differed in terms of hole diameter, septal thickness, and length. Simulated conversion coefficients and collimator parameters were prepared as training datasets, then a gradient-boosting ML was trained to estimate conversion coefficients from collimator parameters. Conversion... (More)

Purpose: We developed a method of standardizing the heart-to-mediastinal ratio in 123I-labeled meta-iodobenzylguanidine (MIBG) images using a conversion coefficient derived from a dedicated phantom. This study aimed to create a machine-learning (ML) model to estimate conversion coefficients without using a phantom. Methods: 210 Monte Carlo (MC) simulations of 123I-MIBG images to obtain conversion coefficients using collimators that differed in terms of hole diameter, septal thickness, and length. Simulated conversion coefficients and collimator parameters were prepared as training datasets, then a gradient-boosting ML was trained to estimate conversion coefficients from collimator parameters. Conversion coefficients derived by ML were compared with those that were MC simulated and experimentally derived from 613 phantom images. Results: Conversion coefficients were superior when estimated by ML compared with the classical multiple linear regression model (root mean square deviations: 0.021 and 0.059, respectively). The experimental, MC simulated, and ML-estimated conversion coefficients agreed, being, respectively, 0.54, 0.55, and 0.55 for the low-; 0.74, 0.70, and 0.72 for the low-middle; and 0.88, 0.88, and 0.88 for the medium-energy collimators. Conclusions: The ML model estimated conversion coefficients without the need for phantom experiments. This means that conversion coefficients were comparable when estimated based on collimator parameters and on experiments.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
I-MIBG, collimator, heart-to-mediastinum ratio, Monte Carlo simulation
in
Journal of Nuclear Cardiology
volume
30
issue
4
pages
1630 - 1641
publisher
Springer
external identifiers
  • pmid:36740650
  • scopus:85147383148
ISSN
1071-3581
DOI
10.1007/s12350-023-03198-3
language
English
LU publication?
yes
id
2df89033-c6c7-4c7b-a046-bceee764dd62
date added to LUP
2023-02-24 12:43:48
date last changed
2024-04-18 19:07:28
@article{2df89033-c6c7-4c7b-a046-bceee764dd62,
  abstract     = {{<p>Purpose: We developed a method of standardizing the heart-to-mediastinal ratio in <sup>123</sup>I-labeled meta-iodobenzylguanidine (MIBG) images using a conversion coefficient derived from a dedicated phantom. This study aimed to create a machine-learning (ML) model to estimate conversion coefficients without using a phantom. Methods: 210 Monte Carlo (MC) simulations of <sup>123</sup>I-MIBG images to obtain conversion coefficients using collimators that differed in terms of hole diameter, septal thickness, and length. Simulated conversion coefficients and collimator parameters were prepared as training datasets, then a gradient-boosting ML was trained to estimate conversion coefficients from collimator parameters. Conversion coefficients derived by ML were compared with those that were MC simulated and experimentally derived from 613 phantom images. Results: Conversion coefficients were superior when estimated by ML compared with the classical multiple linear regression model (root mean square deviations: 0.021 and 0.059, respectively). The experimental, MC simulated, and ML-estimated conversion coefficients agreed, being, respectively, 0.54, 0.55, and 0.55 for the low-; 0.74, 0.70, and 0.72 for the low-middle; and 0.88, 0.88, and 0.88 for the medium-energy collimators. Conclusions: The ML model estimated conversion coefficients without the need for phantom experiments. This means that conversion coefficients were comparable when estimated based on collimator parameters and on experiments.</p>}},
  author       = {{Okuda, Koichi and Nakajima, Kenichi and Kitamura, Chiemi and Ljungberg, Michael and Hosoya, Tetsuo and Kirihara, Yumiko and Hashimoto, Mitsumasa}},
  issn         = {{1071-3581}},
  keywords     = {{I-MIBG; collimator; heart-to-mediastinum ratio; Monte Carlo simulation}},
  language     = {{eng}},
  number       = {{4}},
  pages        = {{1630--1641}},
  publisher    = {{Springer}},
  series       = {{Journal of Nuclear Cardiology}},
  title        = {{Machine learning-based prediction of conversion coefficients for I-123 metaiodobenzylguanidine heart-to-mediastinum ratio}},
  url          = {{http://dx.doi.org/10.1007/s12350-023-03198-3}},
  doi          = {{10.1007/s12350-023-03198-3}},
  volume       = {{30}},
  year         = {{2023}},
}