[18F]FDG PET radiomics to predict disease-free survival in cervical cancer: a multi-scanner/center study with external validation

Ferreira, Marta S.; Lovinfosse, Pierre; Hermesse, Johanne; Decuypere, Marjolein; Rousseau, Caroline; Lucia, François; Schick, Ulrike; Reinhold, Caroline; Robin, Philippe; Hatt, Mathieu; Visvikis, Dimitris; Bernard, Claire; Leijenaar, Ralph T.H.; Kridelka, Frédéric; Lambin, Philippe; Meyer, Patrick; Hustinx, Roland

doi:10.1007/s00259-021-05303-5

Cited by 40 publications

(39 citation statements)

References 61 publications

(94 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We cannot confirm that all FDG-avid LNs are histopathological lymphadenopathies. Finally, recently there are many promising methods such as radiomics, machine learning, and especially deep learning ( 34 , 35 ). Combining these promising image analysis techniques may have more significant predictive values for the prognosis of cervical cancer.…”

Section: Discussionmentioning

confidence: 99%

The Role of the Metabolic Parameters of 18F-FDG PET/CT in Patients With Locally Advanced Cervical Cancer

et al. 2021

View full text Add to dashboard Cite

PurposeTo evaluate the role of the pre-treatment cervical and lymph node (LN) metabolic parameters of 18F-fluorodeoxyglucose positron emission tomography-computed tomography (18F-FDG PET/CT) for locally advanced cervical cancer (LACC) patients receiving concurrent chemoradiotherapy or radiotherapy.Methodswe reviewed 125 consecutive patients with LACC who underwent pre-treatment 18F-FDG PET/CT examination and concurrent chemoradiotherapy or radiotherapy from February 2010 to December 2015 at our institute. The mean standardized uptake value (SUVmean), maximum standardized uptake value (SUVmax), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) of cervical lesion and lymph node (LN) were recorded. Receiver operator characteristic curve, C-index, Kaplan-Meier method, and Cox proportional hazards models were performed.ResultsThe median follow-up was 62 months (range, 4-114 months). For 125 included patients with cervical cancer, the 5-year overall survival (OS), disease-free survival (DFS), local control (LC) and distant metastasis-free survival (DMFS) rates were 83.6%, 75.1%, 92.3% and 79.9%, respectively. Cervical MTV (c-index 0.59-0.61) and cervical TLG (c-index 0.60-0.62) values calculated with a threshold of 40% SUVmax presented stronger prediction capability than cervical SUVmean (c-index 0.51-0.58) and cervical SUVmax (c-index 0.53-0.57) for OS, DFS, LC, and DMFS. In univariate analysis, cervical TLG ≥ 113.4 had worse DFS and DMFS. Cervical MTV ≥ 18.3 cm3 had worse OS and DMFS. In multivariate analysis, cervical TLG ≥ 113.4 implied worse OS, DFS, and DMFS. In either univariate or multivariate analyses, cervical SUVmean and cervical SUVmax had no statistically significant correlation with OS, DFS, LC and DMFS. For 55 cervical cancer patients with positive LN, LN SUVmax presented strongest prediction capability for OS (c-index = 0.79), DFS (c-index = 0.72), LC (c-index = 0.62), and DMFS (c-index = 0.79). In multivariate analysis, LN SUVmax remained significant biomarker linked to OS, DFS, and DMFS.ConclusionPre-treatment cervical and LN metabolic parameters were associated with survival outcomes in patients with LACC. In our study, we found that pre-treatment cervical TLG and LN SUVmax may be important prognostic biomarkers for OS, DFS, and DMFS. However, further prospective studies with a large number of patients are required to evaluate the value of the metabolic parameters in survival outcomes prediction.

show abstract

Section: Discussionmentioning

confidence: 99%

The Role of the Metabolic Parameters of 18F-FDG PET/CT in Patients With Locally Advanced Cervical Cancer

et al. 2021

View full text Add to dashboard Cite

show abstract

“…As shown in Supplementary Table S9, ComBat improved the AUC and C-index in all intra_tumoral CT models compared to that without ComBat except for the AUC of OS prediction, while the improvement in intra_tumoral PET model is not obvious. As shown in Figure 5, first two principal component of principal component analysis (PCA) were plotted, before ComBat, three batches are totally separable in both PET and CT, after ComBat, three batches get closer and inseparable in CT, while still separable in PET, this probably limit the performance of ComBat in PET models [45][46]. Exploring other more effective harmonization methods should be investigated in the future, besides, proper batch division based on the factor that most contribute to batch effect should also be investigated.…”

Section: Figure 4 (A-c) Receiver Operating Characteristic Curves (Roc) Comparison Of Selected Models As Listed In Table 3 (D-f) Kaplan-mementioning

confidence: 99%

Complementary Value of Intra- and Peri-Tumoral PET/CT Radiomics for Outcome Prediction in Head and Neck Cancer

Feng

et al. 2021

IEEE Access

View full text Add to dashboard Cite

To investigate the prognostic value of peri-tumoral radiomics features of pre-treatment PET/CT images in patients with head and neck cancer. 166 patients from 4 centers (111 for training and 55 for external independent testing) were retrospectively analyzed. 11 regions were used for feature extraction, (1) Intra-tumoral region (Intra) was first dilated radially along the edge by 3, 6, 9, 12 and 15 mm to obtain (2) 5 solid combined regions (noted as Comb_3, 6, 9, 12, and 15, respectively), and (3) 5 hollow annular regions with equal ring width of 3 mm were then generated as peri-tumoral regions (noted as Peri_3, 6, 9, 12 and 15, respectively). 92 individual/integrated models were constructed by using features from Clinical alone, CT or PET alone, Clinical+PET, Clinical+CT, PET+CT, Clinical+PET+CT, Intra+Peri, Clinical+Intra+Peri and Clinical+PET+CT (Intra+Peri). In individual models, only 4 models showed p<0.05 (PET_Peri_3 and PET_Comb_6 for distant metastasis (DM) prediction, Clinical and PET_Peri_6 for death prediction). In integrated models, Clinical+CT (Intra+Peri_6), PET (Intra+Peri_3) and Clinical+PET_Peri_6 achieved the best performance for the prediction of local recurrence (LR), DM and death with AUC of 0.75, 0.80 and 0.87, C-index of 0.71, 0.80 and 0.83, p-value of 0.003, 0.008 and 0.001, respectively. Peri-tumoral regions that located closer to the intra-tumoral region (Peri_3 and Peri_6) showed better performance compared to those located further. The integration of intra-tumoral and peritumoral radiomics features achieved better performance than either of them alone, PET and CT radiomics features also provided complementary information to clinical features.

show abstract

“…We extracted two hundred and fteen features from the segmented volumes, which included rst order grey level statistics, geometry, fractals, texture matrix based features and others. Features were extracted using the Oncoradiomics research toolbox and their detailed description can be found in supplementary data of our previous study [23]. All features were calculated according to the Imaging biomarkers standardization initiative (IBSI) [25].…”

Section: Images Radiomic Featuresmentioning

confidence: 99%

“…PET/CT studies were performed in the CHU of Liège, where 89 studies were acquired using a Philips Gemini TF or BB (scanner A), in the CHU of Brest and ICO St Herblain, where 17 and 34, respectively, were acquired using a Siemens Biograph mCT (scanner B) and at the McGill University Health Center, where 18 studies were performed with a General Electric Discovery ST (scanner C). The patient's clinical characteristics, treatment, acquisition and reconstruction protocols are described in our previous study [23].…”

Section: Datamentioning

confidence: 99%

“…In this study, we compared the effect of 6 [ 18 F]FDG PET intensity discretization methods on the prediction of disease free survival (DFS) in locally advanced cervical cancer (LACC) patients from 3 different scanners/centers. Moreover, we evaluated the effect of combining these different discretization approaches with 7 distinct feature selection (FS) methods as well as with the effect of feature transformation using tumour to liver ratio (TLR) features as done in our previous work [23]. In contrast to what was done in our previous work, we trained 84 distinct models using the data of one of the scanners and evaluated these models on the remaining two.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comparison of radiomic pre-processing steps in the reproducible prediction of disease free survival across multi-scanners/centers

Ferreira

Lovinfosse

Hermesse

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Background Features reproducibility and the generalizability of the models are currently among the most important limitations when integrating radiomics into the clinics. Radiomic features are sensitive to imaging acquisition protocols, reconstruction algorithms and parameters, as well as by the different steps of the usual radiomics workflow. We propose a framework for comparing the reproducibility of different pre-processing steps in PET/CT radiomic analysis in the prediction of disease free survival (DFS) across multi-scanners/centers. Results We evaluated and compared the prediction performance of several models that differ in i) the type of intensity discretization, ii) feature selection method, iii) features type i.e, original or tumour to liver ratio radiomic features (OR or TLR). We trained our models using data from one scanner/center and tested on two external scanner/centers. Our results show that there is a low reproducibility in predictions across scanners and discretization methods. Despite of this, TLR based models were generally more robust than OR. Maximum relevance minimum redundancy (MRMR) forward feature selection with Pearson correlation was the feature selection method that had the best mean area under the precision recall curve when using it combining the features from all discretization’s bin’s number (D_All_FBN) with TLR features for two of the four classifiers. Conclusion We evaluated and compared the prediction performance of several models in a data set containing hundred fifty-eight patients with locally advanced cervical cancer (LACC) from three distinct scanners. In our cohort of LAAC patients pre-processing of radiomic features in [18F]FDG PET affects DFS predictions performances across scanners and combining the D_All_FBN TLR approach with the MRMR forward Pearson feature selection method might help increasing robustness of radiomic studies.

show abstract

[18F]FDG PET radiomics to predict disease-free survival in cervical cancer: a multi-scanner/center study with external validation

Cited by 40 publications

References 61 publications

The Role of the Metabolic Parameters of 18F-FDG PET/CT in Patients With Locally Advanced Cervical Cancer

The Role of the Metabolic Parameters of 18F-FDG PET/CT in Patients With Locally Advanced Cervical Cancer

Complementary Value of Intra- and Peri-Tumoral PET/CT Radiomics for Outcome Prediction in Head and Neck Cancer

Comparison of radiomic pre-processing steps in the reproducible prediction of disease free survival across multi-scanners/centers

Contact Info

Product

Resources

About