Detection of clinically silent brain lesions in [18F]FDG PET/CT study in oncological patients: analysis of over 10,000 studies

Pietrzak, Agata; Marszałek, Andrzej; Kunikowska, Jolanta; Piotrowski, Tomasz; Medak, Adrianna; Pietrasz, Katarzyna; Wojtowicz, Julia; Cholewiński, Witold

doi:10.1038/s41598-021-98004-w

Cited by 8 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A review of the literature suggests that 2-deoxy-2-[18F]-floor-D-glucose ( 18 F-FDG) PET-CT is a valuable tool in identifying metabolically active brain tumors and monitoring treatment response [ 1 ]. Zhao et al (2014) reported that 18 F-FDG PET-CT had high sensitivity and specificity for detecting brain tumors and differentiating them from non-neoplastic lesions [ 2 ].…”

Section: Instructionmentioning

confidence: 99%

Improving the Classification of PCNSL and Brain Metastases by Developing a Machine Learning Model Based on 18F-FDG PET

Cui

Yao

et al. 2023

JPM

View full text Add to dashboard Cite

Background: The characteristic magnetic resonance imaging (MRI) and the positron emission tomography (PET) findings of PCNSL often overlap with other intracranial tumors, making definitive diagnosis challenging. PCNSL typically shows iso-hypointense to grey matter on T2-weighted imaging. However, a particular part of PCNSL can demonstrate T2-weighted hyperintensity as other intracranial tumors. Moreover, normal high uptake of FDG in the basal ganglia, thalamus, and grey matter can mask underlying PCNSL in 18F-FDG PET. In order to promote the efficiency of diagnosis, the MRI-based or PET/CT-based radiomics models combining histograms with texture features in diagnosing glioma and brain metastases have been widely established. However, the diagnosing model for PCNSL has not been widely reported. The study was designed to investigate a machine-learning (ML) model based on multiple parameters of 2-deoxy-2-[18F]-floor-D-glucose (18F-FDG) PET for differential diagnosis of PCNSL and metastases in the brain. Methods: Patients who underwent an 18F-FDG PET scan with untreated PCNSL or metastases in the brain were included between May 2016 and May 2022. A total of 126 lesions from 51 patients (43 patients with untreated brain metastases and eight patients with untreated PCNSL), including 14 lesions of PCNSL, and 112 metastatic lesions in the brain, met the inclusion criteria. PCNSL or brain metastasis was confirmed after pathology or clinical history. Principal component analysis (PCA) was used to decompose the datasets. Logistic regression (LR), support vector machine (SVM), and random forest classification (RFC) models were trained by two different groups of datasets, the group of multi-class features and the group of density features, respectively. The model with the highest mean precision score was selected. The testing sets and original data were used to examine the efficacy of models separately by using the weighted average F1 score and area under the curve (AUC) of the receiver operating characteristic curve (ROC). Results: The multi-class features-based RFC and SVM models reached identical weighted-average F1 scores in the testing set, and the score was 0.98. The AUCs of RFC and SVM models calculated from the testing set were 1.00 equally. Evaluated by the original dataset, the RFC model based on multi-class features performs better than the SVM model, whose weighted-average F1 scores of the RFC model calculated from the original data were 0.85 with an AUC of 0.93. Conclusions: The ML based on multi-class features of 18F-FDG PET exhibited the potential to distinguish PCNSL from brain metastases. The RFC models based on multi-class features provided comparatively high efficiency in our study.

show abstract

Section: Instructionmentioning

confidence: 99%

Improving the Classification of PCNSL and Brain Metastases by Developing a Machine Learning Model Based on 18F-FDG PET

Cui

Yao

et al. 2023

JPM

View full text Add to dashboard Cite

show abstract

“…Advanced MRI techniques, such as Diffusion MRI (dMRI) and Perfusion-Weighted Imaging (PWI), are increasingly included in both research and clinical MRI protocols for brain tumours, as they add important structural, physiological, and haemodynamic information [8]. Other imaging modalities, such as Positron Emission Tomography (PET), have shown very good diagnostic performance and sensitivity for the metabolic characterisation of brain tumours both at initial diagnosis and during follow-up [9][10][11]. However, the use of radioactive tracers makes PET less suitable than MRI in some patients, especially when multiple follow-up scans are needed.…”

Section: Introductionmentioning

confidence: 99%

Comprehensive Brain Tumour Characterisation with VERDICT-MRI: Evaluation of Cellular and Vascular Measures Validated by Histology

Castellano

Bailo

Callea

et al. 2023

Cancers

View full text Add to dashboard Cite

The aim of this work was to extend the VERDICT-MRI framework for modelling brain tumours, enabling comprehensive characterisation of both intra- and peritumoural areas with a particular focus on cellular and vascular features. Diffusion MRI data were acquired with multiple b-values (ranging from 50 to 3500 s/mm2), diffusion times, and echo times in 21 patients with brain tumours of different types and with a wide range of cellular and vascular features. We fitted a selection of diffusion models that resulted from the combination of different types of intracellular, extracellular, and vascular compartments to the signal. We compared the models using criteria for parsimony while aiming at good characterisation of all of the key histological brain tumour components. Finally, we evaluated the parameters of the best-performing model in the differentiation of tumour histotypes, using ADC (Apparent Diffusion Coefficient) as a clinical standard reference, and compared them to histopathology and relevant perfusion MRI metrics. The best-performing model for VERDICT in brain tumours was a three-compartment model accounting for anisotropically hindered and isotropically restricted diffusion and isotropic pseudo-diffusion. VERDICT metrics were compatible with the histological appearance of low-grade gliomas and metastases and reflected differences found by histopathology between multiple biopsy samples within tumours. The comparison between histotypes showed that both the intracellular and vascular fractions tended to be higher in tumours with high cellularity (glioblastoma and metastasis), and quantitative analysis showed a trend toward higher values of the intracellular fraction (fic) within the tumour core with increasing glioma grade. We also observed a trend towards a higher free water fraction in vasogenic oedemas around metastases compared to infiltrative oedemas around glioblastomas and WHO 3 gliomas as well as the periphery of low-grade gliomas. In conclusion, we developed and evaluated a multi-compartment diffusion MRI model for brain tumours based on the VERDICT framework, which showed agreement between non-invasive microstructural estimates and histology and encouraging trends for the differentiation of tumour types and sub-regions.

show abstract

“…The PET studies of response assessment are conducted at various time points, including during and after the chemotherapy ( Adams and Kwee, 2016 ; Frood et al, 2021 ). In addition to its application in the field of brain tumor ( Boellaard et al, 2015 ; Treglia et al, 2019 ; Pietrzak et al, 2021 ), PET is a functional imaging modality with unique properties. It is conventionally used in brain science ( Hu et al, 2015 ; Tan et al, 2022 ).…”

Section: Introductionmentioning

confidence: 99%

Altered Regional Brain Glucose Metabolism in Diffuse Large B-Cell Lymphoma Patients Treated With Cyclophosphamide, Epirubicin, Vincristine, and Prednisone: An Fluorodeoxyglucose Positron Emission Tomography Study of 205 Cases

Zhang

Cui

et al. 2022

Front. Neurosci.

View full text Add to dashboard Cite

BackgroundA growing number of neuroimaging studies reported that chemotherapy might impair brain functions, leading to persistent cognitive alterations in a subset of cancer patients. The present study aimed to investigate the regional brain glucose metabolism differences between diffuse large B cell lymphoma (DLBCL) patients treated with cyclophosphamide, epirubicin, vincristine, and prednisone and controls using positron emission tomography with 18F-labeled fluoro-2-deoxyglucose integrated with computed tomography (18F-FDG PET/CT) scanning.MethodsWe analyzed 18F-FDG PET data from 205 right-handed subjects (for avoiding the influence of handedness factors on brain function), including 105 post-chemotherapy DLBCL patients and 100 controls. The two groups had similar average age, gender ratio, and years of education. First, we compared the regional brain glucose metabolism using a voxel-based two-sample t-test. Second, we compared the interregional correlation. Finally, we investigated the correlations between the regional brain glucose metabolism and the number of chemotherapy cycles.ResultsCompared with the controls, the post-chemotherapy group showed higher metabolism in the right hippocampus and parahippocampal gyrus (region of interest (ROI) 1) and the left hippocampus (ROI 2), and lower metabolism in the left medial orbitofrontal gyrus (ROI 3), the left medial superior frontal gyrus (ROI 4), and the left superior frontal gyrus (ROI 5). The two groups had different interregional correlations between ROI 3 and ROI 5. In some brain regions—mainly located in the bilateral frontal gyrus—the number of chemotherapy cycles was positively correlated with the regional brain glucose metabolism. Meanwhile, in some bilateral hippocampus regions, these two parameters were negatively correlated.ConclusionThe present study provides solid data on the regional brain glucose metabolism differences between post-chemotherapy DLBCL patients and controls. These results should improve our understanding of human brain functions alterations in post-chemotherapy DLBCL patients and suggest that 18F-FDG PET/CT scanning is a valuable neuroimaging technology for studying chemotherapy-induced brain function changes.

show abstract

Detection of clinically silent brain lesions in [18F]FDG PET/CT study in oncological patients: analysis of over 10,000 studies

Cited by 8 publications

References 16 publications

Improving the Classification of PCNSL and Brain Metastases by Developing a Machine Learning Model Based on 18F-FDG PET

Improving the Classification of PCNSL and Brain Metastases by Developing a Machine Learning Model Based on 18F-FDG PET

Comprehensive Brain Tumour Characterisation with VERDICT-MRI: Evaluation of Cellular and Vascular Measures Validated by Histology

Altered Regional Brain Glucose Metabolism in Diffuse Large B-Cell Lymphoma Patients Treated With Cyclophosphamide, Epirubicin, Vincristine, and Prednisone: An Fluorodeoxyglucose Positron Emission Tomography Study of 205 Cases

Contact Info

Product

Resources

About