Differential diagnostic value of &lt;sup&gt;18&lt;/sup&gt;F-FDG PET/CT for benign and malignant vertebral compression fractures: comparison with magnetic resonance imaging

He, Xu; Zhao, Long; Guo, Xiaoguang; Zhao, Liang; Wu, Jing; Huang, Jinxiong; Sun, Long; Xie, Chengrong; Chen, Haojun

doi:10.2147/cmar.s168374

Cited by 21 publications

(45 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In literature, other imaging modalities have been employed for the evaluation of spinal lesions. He et al investigated the differential diagnostic value of f-18 fluorodeoxyglucose PET/CT for the benign and malignant vertebral lesion [43]. They reported on the usefulness of both maximum standardized uptake value and uptake pattern for differentiation of benign and malignant lesions.…”

Section: Discussionmentioning

confidence: 99%

Radiomic Machine Learning Classifiers in Spine Bone Tumors: A Multi-Software, Multi-Scanner Study

Chianca

Cuocolo

Gitto

et al. 2021

European Journal of Radiology

View full text Add to dashboard Cite

Spinal lesion differential diagnosis remains challenging even in MRI. Radiomics and machine learning (ML) have proven useful even in absence of a standardized data mining pipeline. We aimed to assess ML diagnostic performance in spinal lesion differential diagnosis, employing radiomic data extracted by different software. Methods: Patients undergoing MRI for a vertebral lesion were retrospectively analyzed (n = 146, 67 males, 79 females; mean age 63 ± 16 years, range 8-89 years) and constituted the train (n = 100) and internal test cohorts (n = 46). Part of the latter had additional prior exams which constituted a multi-scanner, external test cohort (n = 35). Lesions were labeled as benign or malignant (2-label classification), and benign, primary malignant or metastases (3-label classification) for classification analyses. Features extracted via 3D Slicer heterogeneityCAD module (hCAD) and PyRadiomics were independently used to compare different combinations of feature selection methods and ML classifiers (n = 19). Results: In total, 90 and 1548 features were extracted by hCAD and PyRadiomics, respectively. The best feature selection method-ML algorithm combination was selected by 10 iterations of 10-fold cross-validation in the training data. For the 2-label classification ML obtained 94% accuracy in the internal test cohort, using hCAD data, and 86% in the external one. For the 3-label classification, PyRadiomics data allowed for 80% and 69% accuracy in the internal and external test sets, respectively. Conclusions: MRI radiomics combined with ML may be useful in spinal lesion assessment. More robust preprocessing led to better consistency despite scanner and protocol heterogeneity.

show abstract

Section: Discussionmentioning

confidence: 99%

Radiomic Machine Learning Classifiers in Spine Bone Tumors: A Multi-Software, Multi-Scanner Study

Chianca

Cuocolo

Gitto

et al. 2021

European Journal of Radiology

View full text Add to dashboard Cite

show abstract

“…Combined PET/CT has increased diagnostic value, but it is commonly associated with a general increase in the radiation dose received by the patient (12). To be competitive with the evolution of nonionizing imaging techniques, PET/CT needs to develop constantly, with dose reduction as one of the main goals (13)(14)(15).…”

Section: Hybrid Imaging Pet/ctmentioning

confidence: 99%

Technologist Approach to Global Dose Optimization

Costa

Testanera

Camoni

et al. 2018

J. Nucl. Med. Technol.

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

“…Recently, it has been reported that simultaneous 18 F-fluorodeoxyglucose positron emission tomography ( 18 F-FDG-PET) can be used to determine therapeutic response in spinal infections. 18 F-FDG-PET is less affected by other physical conditions and shows more objective results compared with blood inflammatory markers [9]. Several studies have shown a higher diagnostic accuracy in detecting residual infectious lesion by measuring the degree of 18 F-FDG uptake on 18 F-FDG-PET than by using CRP and MRI [9][10][11].…”

Section: Introductionmentioning

confidence: 99%

“…18 F-FDG-PET is less affected by other physical conditions and shows more objective results compared with blood inflammatory markers [9]. Several studies have shown a higher diagnostic accuracy in detecting residual infectious lesion by measuring the degree of 18 F-FDG uptake on 18 F-FDG-PET than by using CRP and MRI [9][10][11]. In addition, Jeon et al [5] reported differences between the degree of 18 F-FDG uptake and clinical symptoms in patients with cured PVO depending on the site of major structural damage.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Clinical and Radiological Features Predicting Intervertebral Autofusion after Successful Antibiotic Therapy in Pyogenic Vertebral Osteomyelitis

2021

View full text Add to dashboard Cite

Background: Pyogenic vertebral osteomyelitis (PVO) is a bacterial infection involving the intervertebral disc, vertebral body, and paravertebral soft tissues. Damaged intervertebral structure is a major cause of persistent back pain even after successful antibiotic therapy, which can be improved by achieving autofusion or via additional surgical fixation. In this study, we analyzed the clinical and radiological features predicting intervertebral autofusion after successful antibiotic therapy in lumbar PVO. Methods: This study was retrospectively conducted with 32 patients (20 men and 12 women) diagnosed with lumbar PVO that was completely cured with no recurrences after antibiotic therapy. They were divided into two groups with (group A, n = 18) and without (group B, n = 14) intervertebral autofusion at six-month follow-up. Differences in back pain, blood inflammatory markers, and radiological features of PVO on simultaneous 18F-fluorodeoxyglucose positron emission tomography/magnetic resonance imaging (18F-FDG-PET/MRI) of the intervertebral structure between the two groups were analyzed. Results: The mean duration of antibiotic therapy was 41.44 ± 14.21 (21–89) days. Group A showed a statistically higher erythrocyte sedimentation ratio (ESR; 59.28 ± 32.33 vs. 33.93 ± 18.76 mm/h, p = 0.014; normal range of ESR < 25), maximum standardized 18F-FDG uptake (SUVmax; 5.56 ± 1.86 vs. 3.98 ± 1.40, p = 0.013), and sustained extensive edematous changes on T2-weighted fat saturation (T2FS) MRI (p = 0.015) immediately after successful antibiotic therapy. However, no significant differences were observed in back pain, C-reactive protein, or the distribution of 18F-FDG uptake/contrast enhancement on 18F-FDG-PET/MRI (p > 0.05). Conclusions: Higher ESR and SUVmax of the intervertebral structure and sustained extensive edematous change on T2FS MRI immediately after successful antibiotic therapy are related with subsequent intervertebral autofusion, which should be carefully considered when assessing therapeutic response in PVO.

show abstract

Differential diagnostic value of <sup>18</sup>F-FDG PET/CT for benign and malignant vertebral compression fractures: comparison with magnetic resonance imaging

Cited by 21 publications

References 23 publications

Radiomic Machine Learning Classifiers in Spine Bone Tumors: A Multi-Software, Multi-Scanner Study

Radiomic Machine Learning Classifiers in Spine Bone Tumors: A Multi-Software, Multi-Scanner Study

Technologist Approach to Global Dose Optimization

Clinical and Radiological Features Predicting Intervertebral Autofusion after Successful Antibiotic Therapy in Pyogenic Vertebral Osteomyelitis

Contact Info

Product

Resources

About