Improved detection of cholesterol gallstones using quasi-material decomposition images generated from single-energy computed tomography images via deep learning
Radiological Physics and Technology · 2024
DOI: 10.1007/s12194-024-00783-0 ↗Kurz gefasst
Fachartikel in der Zeitschrift Radiological Physics and Technology, 2024. Verfasst von Kojiro Nishijima und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Oita Prefectural Hospital, 8-1, Bunyo 2-Chome, Oita City, 870-8511, Japan. k-nishijima@oitapref-hosp.jp. Hauptthemen laut MEDLINE: Gallstones, Deep Learning, Tomography, X-Ray Computed, Cholesterol. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 17 Literaturangaben.
Abstract (Originalsprache)
In this study, we developed a method for generating quasi-material decomposition (quasi-MD) images from single-energy computed tomography (SECT) images using a deep convolutional neural network (DCNN). Our aim was to improve the detection of cholesterol gallstones and to determine the clinical utility of quasi-MD images. Four thousand pairs of virtual monochromatic images (70 keV) and MD images (fat/water) of the same section, obtained via dual-energy computed tomography (DECT), were used to train the DCNN. The trained DCNN can automatically generate quasi-MD images from the SECT images. Additional SECT images were obtained from 70 patients (40 with and 30 without cholesterol gallstones) to generate quasi-MD images for testing. The presence of gallstones in this dataset was confirmed by ultrasonography. We conducted a receiver operating characteristic (ROC) observer study with three radiologists to validate the clinical utility of the quasi-MD images for detecting cholesterol gallstones. The mean area under the ROC curve for the detection of cholesterol gallstones improved from 0.867 to 0.921 (p = 0.001) when quasi-MD images were added to SECT images. The clinical utility of quasi-MD imaging for detecting cholesterol gallstones was showed. This study demonstrated that the lesion detection capability of images obtained from SECT can be improved using a DCNN trained with DECT images obtained using high-end computed tomography systems.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Radiology, Oita Prefectural Hospital, 8-1, Bunyo 2-Chome, Oita City, 870-8511, Japan. k-nishijima@oitapref-hosp.jp.
- Faculty of Life Sciences, Kumamoto University, 4-24-1 Kuhonji, Chuo-Ku, Kumamoto, 862-0976, Japan.
Zitieren
APA
Nishijima, K., & Shiraishi, J. (2024). Improved detection of cholesterol gallstones using quasi-material decomposition images generated from single-energy computed tomography images via deep learning. Radiological Physics and Technology. https://doi.org/10.1007/s12194-024-00783-0
Vancouver
Nishijima K, Shiraishi J. Improved detection of cholesterol gallstones using quasi-material decomposition images generated from single-energy computed tomography images via deep learning. Radiological Physics and Technology. 2024. doi:10.1007/s12194-024-00783-0
BibTeX
@article{Nishijima2024,
author = {Nishijima, Kojiro and Shiraishi, Junji},
title = {Improved detection of cholesterol gallstones using quasi-material decomposition images generated from single-energy computed tomography images via deep learning},
journal = {Radiological Physics and Technology},
year = {2024},
doi = {10.1007/s12194-024-00783-0}
}
EUVIMED