SPECT/CT Radiomics for Differentiating between Enchondroma and Grade I Chondrosarcoma

This study was performed to assess the value of SPECT/CT radiomics parameters in differentiating enchondroma and atypical cartilaginous tumors (ACTs) located in the long bones. Quantitative HDP SPECT/CT data of 49 patients with enchondromas or ACTs in the long bones were retrospectively reviewed. Pa...

Full description

Bibliographic Details
Main Authors: Hyukjin Yoon, Woo Hee Choi, Min Wook Joo, Seunggyun Ha, Yong-An Chung
Format: Article
Language:English
Published: MDPI AG 2023-10-01
Series:Tomography
Subjects:
Online Access:https://www.mdpi.com/2379-139X/9/5/148
_version_ 1827719813097586688
author Hyukjin Yoon
Woo Hee Choi
Min Wook Joo
Seunggyun Ha
Yong-An Chung
author_facet Hyukjin Yoon
Woo Hee Choi
Min Wook Joo
Seunggyun Ha
Yong-An Chung
author_sort Hyukjin Yoon
collection DOAJ
description This study was performed to assess the value of SPECT/CT radiomics parameters in differentiating enchondroma and atypical cartilaginous tumors (ACTs) located in the long bones. Quantitative HDP SPECT/CT data of 49 patients with enchondromas or ACTs in the long bones were retrospectively reviewed. Patients were randomly split into training (<i>n</i> = 32) and test (<i>n</i> = 17) data, and SPECT/CT radiomics parameters were extracted. In training data, LASSO was employed for feature reduction. Selected parameters were compared with classic quantitative parameters for the prediction of diagnosis. Significant parameters from training data were again tested in the test data. A total of 12 (37.5%) and 6 (35.2%) patients were diagnosed as ACTs in training and test data, respectively. LASSO regression selected two radiomics features, zone-length non-uniformity for zone (ZLNU<sub>GLZLM</sub>) and coarseness for neighborhood grey-level difference (Coarseness<sub>NGLDM</sub>). Multivariate analysis revealed higher ZLNU<sub>GLZLM</sub> as the only significant independent factor for the prediction of ACTs, with sensitivity and specificity of 85.0% and 58.3%, respectively, with a cut-off value of 191.26. In test data, higher ZLNU<sub>GLZLM</sub> was again associated with the diagnosis of ACTs, with sensitivity and specificity of 83.3% and 90.9%, respectively. HDP SPECT/CT radiomics may provide added value for differentiating between enchondromas and ACTs.
first_indexed 2024-03-10T20:51:14Z
format Article
id doaj.art-c57a2fa9f3c64bbd92bf672f10e655e7
institution Directory Open Access Journal
issn 2379-1381
2379-139X
language English
last_indexed 2024-03-10T20:51:14Z
publishDate 2023-10-01
publisher MDPI AG
record_format Article
series Tomography
spelling doaj.art-c57a2fa9f3c64bbd92bf672f10e655e72023-11-19T18:21:02ZengMDPI AGTomography2379-13812379-139X2023-10-01951868187510.3390/tomography9050148SPECT/CT Radiomics for Differentiating between Enchondroma and Grade I ChondrosarcomaHyukjin Yoon0Woo Hee Choi1Min Wook Joo2Seunggyun Ha3Yong-An Chung4Division of Nuclear Medicine, Department of Radiology, St. Vincent’s Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of KoreaDivision of Nuclear Medicine, Department of Radiology, St. Vincent’s Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of KoreaDepartment of Orthopedic Surgery, St. Vincent’s Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of KoreaDivision of Nuclear Medicine, Department of Radiology, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of KoreaDivision of Nuclear Medicine, Department of Radiology, Incheon St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of KoreaThis study was performed to assess the value of SPECT/CT radiomics parameters in differentiating enchondroma and atypical cartilaginous tumors (ACTs) located in the long bones. Quantitative HDP SPECT/CT data of 49 patients with enchondromas or ACTs in the long bones were retrospectively reviewed. Patients were randomly split into training (<i>n</i> = 32) and test (<i>n</i> = 17) data, and SPECT/CT radiomics parameters were extracted. In training data, LASSO was employed for feature reduction. Selected parameters were compared with classic quantitative parameters for the prediction of diagnosis. Significant parameters from training data were again tested in the test data. A total of 12 (37.5%) and 6 (35.2%) patients were diagnosed as ACTs in training and test data, respectively. LASSO regression selected two radiomics features, zone-length non-uniformity for zone (ZLNU<sub>GLZLM</sub>) and coarseness for neighborhood grey-level difference (Coarseness<sub>NGLDM</sub>). Multivariate analysis revealed higher ZLNU<sub>GLZLM</sub> as the only significant independent factor for the prediction of ACTs, with sensitivity and specificity of 85.0% and 58.3%, respectively, with a cut-off value of 191.26. In test data, higher ZLNU<sub>GLZLM</sub> was again associated with the diagnosis of ACTs, with sensitivity and specificity of 83.3% and 90.9%, respectively. HDP SPECT/CT radiomics may provide added value for differentiating between enchondromas and ACTs.https://www.mdpi.com/2379-139X/9/5/148HDP bone SPECT/CTradiomicsenchondromaschondrosarcoma
spellingShingle Hyukjin Yoon
Woo Hee Choi
Min Wook Joo
Seunggyun Ha
Yong-An Chung
SPECT/CT Radiomics for Differentiating between Enchondroma and Grade I Chondrosarcoma
Tomography
HDP bone SPECT/CT
radiomics
enchondromas
chondrosarcoma
title SPECT/CT Radiomics for Differentiating between Enchondroma and Grade I Chondrosarcoma
title_full SPECT/CT Radiomics for Differentiating between Enchondroma and Grade I Chondrosarcoma
title_fullStr SPECT/CT Radiomics for Differentiating between Enchondroma and Grade I Chondrosarcoma
title_full_unstemmed SPECT/CT Radiomics for Differentiating between Enchondroma and Grade I Chondrosarcoma
title_short SPECT/CT Radiomics for Differentiating between Enchondroma and Grade I Chondrosarcoma
title_sort spect ct radiomics for differentiating between enchondroma and grade i chondrosarcoma
topic HDP bone SPECT/CT
radiomics
enchondromas
chondrosarcoma
url https://www.mdpi.com/2379-139X/9/5/148
work_keys_str_mv AT hyukjinyoon spectctradiomicsfordifferentiatingbetweenenchondromaandgradeichondrosarcoma
AT wooheechoi spectctradiomicsfordifferentiatingbetweenenchondromaandgradeichondrosarcoma
AT minwookjoo spectctradiomicsfordifferentiatingbetweenenchondromaandgradeichondrosarcoma
AT seunggyunha spectctradiomicsfordifferentiatingbetweenenchondromaandgradeichondrosarcoma
AT yonganchung spectctradiomicsfordifferentiatingbetweenenchondromaandgradeichondrosarcoma