Detailed Information

Cited 0 time in webofscience Cited 4 time in scopus
Metadata Downloads

Detecting Multiple Myeloma Infiltration of the Bone Marrow on CT Scans in Patients with Osteopenia: Feasibility of Radiomics Analysisopen access

Authors
Park, HyerimLee, So-YeonLee, JooyeonPak, JuyoungLee, KoeunLee, Seung-EunJung, Joon-Yong
Issue Date
Apr-2022
Publisher
MDPI AG
Keywords
multiple myeloma; computed tomography; radiomics; texture analysis; machine learning
Citation
Diagnostics, v.12, no.4
Journal Title
Diagnostics
Volume
12
Number
4
URI
https://scholarworks.bwise.kr/sch/handle/2021.sw.sch/21709
DOI
10.3390/diagnostics12040923
ISSN
2075-4418
Abstract
It is difficult to detect multiple myeloma (MM) infiltration of the bone marrow on computed tomography (CT) scans of patients with osteopenia. Our aim is to determine the feasibility of using radiomics analysis to detect MM infiltration of the bone marrow on CT scans of patients with osteopenia. The contrast-enhanced thoracic CT scans of 104 patients with MM and 104 age- and sex-matched controls were retrospectively evaluated. All individuals had decreased bone density on radiography. The study group was divided into development (n = 160) and temporal validation sets (n = 48). The radiomics model was developed using 805 texture features extracted from the bone marrow for a development set, using a Random Forest algorithm. The developed models were applied to evaluate a temporal validation set. For comparison, three radiologists evaluated the CTs for the possibility of MM infiltration in the bone marrow. The diagnostic performances were assessed and compared using an area under the receiver operating characteristic curve (AUC) analysis. The AUC of the radiomics model was not significantly different from those of the radiologists (p = 0.056-0.821). The radiomics analysis results showed potential for detecting MM infiltration in the bone marrow on CT scans of patients with osteopenia.
Files in This Item
There are no files associated with this item.
Appears in
Collections
College of Medicine > Department of Radiology > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Altmetrics

Total Views & Downloads

BROWSE