1
|
Hong R, Li Q, Ma J, Lu C, Zhong Z. Computed tomography-based radiomics machine learning models for differentiating enchondroma and atypical cartilaginous tumor in long bones. ROFO-FORTSCHR RONTG 2024. [PMID: 39074797 DOI: 10.1055/a-2344-5398] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/31/2024]
Abstract
To explore the value of CT-based radiomics machine learning models for differentiating enchondroma from atypical cartilaginous tumor (ACT) in long bones and methods to improve model performance.59 enchondromas and 53 ACTs in long bones confirmed by pathology were collected retrospectively. The features were extracted from preoperative CT images of these patients, and least absolute shrinkage and selection operator (LASSO) regression was used for feature selection and dimensionality reduction. The selected features were used to construct classification models by thirteen machine learning algorithms. The data set was randomly divided into a training set and a test set at a proportion of 7:3 by ten-fold cross-validation to evaluate the performance of these models.A total of 1199 features were extracted, 9 features were selected, and 13 radiomics machine learning models were constructed. The area under the curve (AUC) of 11 models was more than 0.8, and that of 3 models was more than 0.9. The Extremely Randomized Trees model achieved the best performance (AUC = 0.9375 ± 0.0884), followed by the Adaptive Boosting model (AUC = 0.9188 ± 0.1010) and the Linear Discriminant Analysis model (AUC = 0.9062 ± 0.1459).CT-based radiomics machine learning models had great ability to distinguish enchondroma and ACT in long bones. By using filters to deeply mine high-order features in the original image and selecting appropriate machine learning algorithms, the performance of the model can be improved. · CT-based radiomics machine learning models can distinguish enchondroma and ACT in long bones.. · Using filters and selecting advanced machine learning algorithms can improve model performance.. · Clinical features have limited utility in distinguishing enchondroma and ACT in long bones.. · Hong R, Li Q, Ma J et al. Computed tomography-based radiomics machine learning models for differentiating enchondroma and atypical cartilaginous tumor in long bones. Fortschr Röntgenstr 2024; DOI 10.1055/a-2344-5398.
Collapse
Affiliation(s)
- Rui Hong
- Radiology, The Third Hospital of Hebei Medical University, Shijiazhuang, China
| | - Qian Li
- Radiology, The Third Hospital of Hebei Medical University, Shijiazhuang, China
| | - Jielin Ma
- Oncology, The Third Hospital of Hebei Medical University, Shijiazhuang, China
| | - Chunmiao Lu
- Radiology, The Third Hospital of Hebei Medical University, Shijiazhuang, China
| | - Zhiwei Zhong
- Radiology, The Third Hospital of Hebei Medical University, Shijiazhuang, China
| |
Collapse
|
2
|
Davies A, Patel A, Azzopardi C, James S, Botchu R, Jeys L. The influence of site on the incidence and diagnosis of solitary central cartilage tumours of the femur. A 21 st century perspective. J Clin Orthop Trauma 2022; 32:101953. [PMID: 35959501 PMCID: PMC9358228 DOI: 10.1016/j.jcot.2022.101953] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/30/2022] [Revised: 07/07/2022] [Accepted: 07/19/2022] [Indexed: 11/29/2022] Open
Abstract
OBJECTIVE To determine the incidence of central cartilage tumours (CCTs) in the femur and the impact of site (proximal, mid and distal thirds) on tumour grade. To compare study results with historically published data. MATERIALS AND METHODS Retrospective review of solitary CCTs arising in the femur over the past 13 years. Data collected included location (proximal, mid and distal thirds) and final diagnosis in terms of tumour grade based on imaging features ± histology. Case material collected from three bone tumour textbooks provided historical data. RESULTS 430 solitary CCTs were included in the femur. 73% cases arose in the distal, 3.7% in the mid and 23% in the proximal femur. The ratio of "benign" (combining enchondroma and atypical cartilaginous tumour (ACT)) to higher grade chondrosarcoma (CS) was 11:1 in the distal, 1:1 in the mid and 1:1.5 in the proximal femur, the distribution of benign to malignant tumours being significantly different between the regions (F test, p < 0.05). Comparison with historical data showed a reversal of the benign (enchondroma) to malignant (ACT and higher grade CS) of 30%:70%-84%:16% in the current series. CONCLUSIONS The site of origin of a CCT in the femur has an impact on final diagnosis with CS uncommon in the distal as compared with the mid and proximal femur. This is in contradistinction to historical data where the incidence of CS exceeded that of enchondroma at all sites.
Collapse
Affiliation(s)
- A.M. Davies
- Department of Musculoskeletal Imaging, Royal Orthopaedic Hospital, Birmingham, UK
| | - A. Patel
- Department of Musculoskeletal Imaging, Royal Orthopaedic Hospital, Birmingham, UK
| | - C. Azzopardi
- Department of Musculoskeletal Imaging, Royal Orthopaedic Hospital, Birmingham, UK
| | - S.L. James
- Department of Musculoskeletal Imaging, Royal Orthopaedic Hospital, Birmingham, UK
| | - R. Botchu
- Department of Musculoskeletal Imaging, Royal Orthopaedic Hospital, Birmingham, UK,Corresponding author. Department of Musculoskeletal Radiology, The Royal Orthopedic Hospital, Bristol Road South, Northfield, Birmingham, UK.
| | - L. Jeys
- Departments of Orthopaedic Oncology, Royal Orthopaedic Hospital, Birmingham, UK
| |
Collapse
|
3
|
Prevalence of enchondromas of the hand in adults as incidental findings on magnetic resonance imaging. JOURNAL OF CONTEMPORARY MEDICINE 2022. [DOI: 10.16899/jcm.1069082] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022] Open
|
4
|
Collier CD, Nelson GB, Conry KT, Kosmas C, Getty PJ, Liu RW. The Natural History of Benign Bone Tumors of the Extremities in Asymptomatic Children: A Longitudinal Radiographic Study. J Bone Joint Surg Am 2021; 103:575-580. [PMID: 33646982 DOI: 10.2106/jbjs.20.00999] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/01/2023]
Abstract
BACKGROUND Benign bone tumors are common incidental findings in the pediatric population during radiographic evaluation. Counseling these patients requires reassurance and raises questions about the natural history of these tumors over time. The purpose of this study was to estimate the prevalence and observe the behavior of benign childhood bone tumors in an asymptomatic population. METHODS A historical, longitudinal radiographic collection of healthy children was reviewed, which included comprehensive left-sided radiographs of the extremities at yearly intervals. In this study, 262 subjects with 25,555 radiographs were screened for benign bone tumors at a median age of 8 years (range, 0 to 18 years). All potential tumors were reviewed by a multidisciplinary panel, which confirmed the radiographic diagnosis of each lesion, the age at which the lesion first appeared, and the age at which it had resolved. Prevalence rates were calculated using the number of distinct subjects available for each radiographic location and age. RESULTS Thirty-five tumors were identified in 33 subjects, including 19 nonossifying fibromas, 8 enostoses, 6 osteochondromas, and 2 enchondromas. The prevalence rate for all tumors combined increased with age and was 18.9% overall. The overall prevalence rates for specific tumor types were 7.5% for nonossifying fibromas, 5.2% for enostoses, 4.5% for osteochondromas, and 1.8% for enchondromas. Nonossifying fibromas demonstrated a bimodal distribution of prevalence, with a peak at 5 years (10.8%) and another after skeletal maturity (13.3%). The median age at the first appearance for all tumors combined was 9 years (range, 2 to 15 years), but varied by tumor type. Nonossifying fibromas often resolved (7 [37%] of 19), with further resolution possible beyond the last available radiograph. Enostoses, osteochondromas, and enchondromas persisted until the last available radiographs in all subjects. CONCLUSIONS The prevalence of benign childhood bone tumors of the extremities was 18.9% in a historical asymptomatic population. Longitudinal radiographs allowed observation of the timing of the first appearance and the potential for resolution for each tumor type. These findings provide unique evidence to answer many commonly encountered questions when counseling patients and their families on benign bone tumors. LEVEL OF EVIDENCE Prognostic Level IV. See Instructions for Authors for a complete description of levels of evidence.
Collapse
Affiliation(s)
- Christopher D Collier
- Department of Orthopaedic Surgery, Indiana University School of Medicine, Indianapolis, Indiana
| | - Grant B Nelson
- Department of Orthopaedics, University Hospitals Rainbow Babies & Children's Hospital, Case Western Reserve University, Cleveland, Ohio
| | - Keegan T Conry
- Department of Orthopaedics, University Hospitals Rainbow Babies & Children's Hospital, Case Western Reserve University, Cleveland, Ohio
| | - Christos Kosmas
- Department of Radiology, University Hospitals Cleveland Medical Center, Case Western Reserve University, Cleveland, Ohio
| | - Patrick J Getty
- Department of Orthopaedics, University Hospitals Rainbow Babies & Children's Hospital, Case Western Reserve University, Cleveland, Ohio
| | - Raymond W Liu
- Department of Orthopaedics, University Hospitals Rainbow Babies & Children's Hospital, Case Western Reserve University, Cleveland, Ohio
| |
Collapse
|
5
|
Deckers C, de Leijer EM, Flucke U, de Rooy JWJ, Schreuder HWB, Dierselhuis EF, van der Geest ICM. Curettage and cryosurgery for enchondroma and atypical cartilaginous tumors of the long bones: Oncological results of a large series. J Surg Oncol 2021; 123:1821-1827. [PMID: 33713465 PMCID: PMC8251520 DOI: 10.1002/jso.26457] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2020] [Revised: 02/15/2021] [Accepted: 02/20/2021] [Indexed: 12/16/2022]
Abstract
BACKGROUND AND OBJECTIVES Intralesional surgical treatment is the preferred therapy for atypical cartilaginous tumors (ACTs) of the long bones in many institutions. However, the literature is still controversial regarding intralesional treatment versus wide resection. Due to the relative rarity of these tumors, studies reporting on the results of intralesional treatment are often small sample studies. METHODS We retrospectively analyzed the oncological results of 55 enchondromas, 119 ACTs, and 5 chondrosarcomas grade 2 (CS2) treated with curettage and cryosurgery between the years 2004 and 2017 at our institution. The median follow-up period was 53 months (range, 24-169 months). RESULTS In total, seven cases (three ACT, four CS2) recurred. Residual tumor was detected in 20 cases. Three cases underwent secondary curettage and cryosurgery due to local recurrence. Four cases underwent wide resection and reconstruction due to local recurrence with aggressive imaging characteristics. In total, 20 postoperative complications were seen. CONCLUSION Curettage and cryosurgery for enchondroma and ACT show very good oncological results with a low recurrence rate and acceptable complication rate. Curettage and cryosurgery is reliable as a surgical treatment for enchondroma and ACT. Further research should define the criteria for determining which specific cartilaginous tumors necessitate surgical treatment.
Collapse
Affiliation(s)
- Claudia Deckers
- Department of Orthopedics, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Esther M de Leijer
- Department of Orthopedics, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Uta Flucke
- Department of Pathology, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Jacky W J de Rooy
- Department of Radiology, Nuclear Medicine and Anatomy, Radboud University Medical Center, Nijmegen, The Netherlands
| | - H W Bart Schreuder
- Department of Orthopedics, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Edwin F Dierselhuis
- Department of Orthopedics, Radboud University Medical Center, Nijmegen, The Netherlands
| | | |
Collapse
|
6
|
Engel H, Herget GW, Füllgraf H, Sutter R, Benndorf M, Bamberg F, Jungmann PM. Chondrogenic Bone Tumors: The Importance of Imaging Characteristics. ROFO-FORTSCHR RONTG 2020; 193:262-275. [PMID: 33152784 DOI: 10.1055/a-1288-1209] [Citation(s) in RCA: 17] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022]
Abstract
BACKGROUND Chondrogenic tumors are the most frequent primary bone tumors. Malignant chondrogenic tumors represent about one quarter of malignant bone tumors. Benign chondrogenic bone tumors are frequent incidental findings at imaging. Radiological parameters may be helpful for identification, characterization, and differential diagnosis. METHODS Systematic PubMed literature research. Identification and review of studies analyzing and describing imaging characteristics of chondrogenic bone tumors. RESULTS AND CONCLUSIONS The 2020 World Health Organization (WHO) classification system differentiates between benign, intermediate (locally aggressive or rarely metastasizing), and malignant chondrogenic tumors. On imaging, typical findings of differentiated chondrogenic tumors are lobulated patterns with a high signal on T2-weighted magnetic resonance imaging (MRI) and ring- and arc-like calcifications on conventional radiography and computed tomography (CT). Depending on the entity, the prevalence of this chondrogenic pattern differs. While high grade tumors may be identified due to aggressive imaging patterns, the differentiation between benign and intermediate grade chondrogenic tumors is challenging, even in an interdisciplinary approach. KEY POINTS · The WHO defines benign, intermediate, and malignant chondrogenic bone tumors. · Frequent benign tumors: osteochondroma and enchondroma; Frequent malignant tumor: conventional chondrosarcoma. · Differentiation between enchondroma versus low-grade chondrosarcoma is challenging for radiologists and pathologists. · Pain, deep scalloping, cortical destruction, bone expansion, soft tissue component: favor chondrosarcoma. · Potential malignant transformation of osteochondroma: progression after skeletal maturity, cartilage cap thickness (> 2 cm adult; > 3 cm child). · Potentially helpful advanced imaging methods: Dynamic MRI, texture analysis, FDG-PET/CT. CITATION FORMAT · Engel H, Herget GW, Füllgraf H et al. Chondrogenic Bone Tumors: The Importance of Imaging Characteristics. Fortschr Röntgenstr 2021; 193: 262 - 274.
Collapse
Affiliation(s)
- Hannes Engel
- Department of Radiology, Medical Center - University of Freiburg, Faculty of Medicine, University of Freiburg, Germany
| | - Georg W Herget
- Department of Orthopaedics and Traumatology, Medical Center - University of Freiburg, Faculty of Medicine, University of Freiburg, Germany
| | - Hannah Füllgraf
- Institute for Surgical Pathology, Medical Center - University of Freiburg, Faculty of Medicine, University of Freiburg, Germany
| | - Reto Sutter
- Department of Radiology, Balgrist University Hospital, Zurich, Switzerland; Faculty of Medicine, University of Zurich, Switzerland
| | - Matthias Benndorf
- Department of Radiology, Medical Center - University of Freiburg, Faculty of Medicine, University of Freiburg, Germany
| | - Fabian Bamberg
- Department of Radiology, Medical Center - University of Freiburg, Faculty of Medicine, University of Freiburg, Germany
| | - Pia M Jungmann
- Department of Radiology, Medical Center - University of Freiburg, Faculty of Medicine, University of Freiburg, Germany
| |
Collapse
|