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

PURPOSE: To test the performances of native and tumour to liver ratio (TLR) radiomic features extracted from pre-treatment 2-[18F] fluoro-2-deoxy-D-glucose ([18F]FDG) PET/CT and combined with machine learning (ML) for predicting cancer recurrence in patients with locally advanced cervical cancer (LACC). METHODS: One hundred fifty-eight patients with LACC from multiple centers were retrospectively included in the study. Tumours were segmented using the Fuzzy Local Adaptive Bayesian (FLAB) algorithm. Radiomic features were extracted from the tumours and from regions drawn over the normal liver. Cox proportional hazard model was used to test statistical significance of clinical and radiomic features. Fivefold cross validation was used to tune the number of features. Seven different feature selection methods and four classifiers were tested. The models with the selected features were trained using bootstrapping and tested in data from each scanner independently. Reproducibility of radiomics features, clinical data added value and effect of ComBat-based harmonisation were evaluated across scanners. RESULTS: After a median follow-up of 23 months, 29% of the patients recurred. No individual radiomic or clinical features were significantly associated with cancer recurrence. The best model was obtained using 10 TLR features combined with clinical information. The area under the curve (AUC), F1-score, precision and recall were respectively 0.78 (0.67-0.88), 0.49 (0.25-0.67), 0.42 (0.25-0.60) and 0.63 (0.20-0.80). ComBat did not improve the predictive performance of the best models. Both the TLR and the native models performance varied across scanners used in the test set. CONCLUSION: [18F]FDG PET radiomic features combined with ML add relevant information to the standard clinical parameters in terms of LACC patient's outcome but remain subject to variability across PET/CT devices.

Convolutional neural networks for PET functional volume fully automatic segmentation: development and validation in a multi-center setting.

PURPOSE: In this work, we addressed fully automatic determination of tumor functional uptake from positron emission tomography (PET) images without relying on other image modalities or additional prior constraints, in the context of multicenter images with heterogeneous characteristics. METHODS: In cervical cancer, an additional challenge is the location of the tumor uptake near or even stuck to the bladder. PET datasets of 232 patients from five institutions were exploited. To avoid unreliable manual delineations, the ground truth was generated with a semi-automated approach: a volume containing the tumor and excluding the bladder was first manually determined, then a well-validated, semi-automated approach relying on the Fuzzy locally Adaptive Bayesian (FLAB) algorithm was applied to generate the ground truth. Our model built on the U-Net architecture incorporates residual blocks with concurrent spatial squeeze and excitation modules, as well as learnable non-linear downsampling and upsampling blocks. Experiments relied on cross-validation (four institutions for training and validation, and the fifth for testing). RESULTS: The model achieved good Dice similarity coefficient (DSC) with little variability across institutions (0.80 ± 0.03), with higher recall (0.90 ± 0.05) than precision (0.75 ± 0.05) and improved results over the standard U-Net (DSC 0.77 ± 0.05, recall 0.87 ± 0.02, precision 0.74 ± 0.08). Both vastly outperformed a fixed threshold at 40% of SUVmax (DSC 0.33 ± 0.15, recall 0.52 ± 0.17, precision 0.30 ± 0.16). In all cases, the model could determine the tumor uptake without including the bladder. Neither shape priors nor anatomical information was required to achieve efficient training. CONCLUSION: The proposed method could facilitate the deployment of a fully automated radiomics pipeline in such a challenging multicenter context.

Concordance between preoperative ESMO-ESGO-ESTRO risk classification and final histology in early-stage endometrial cancer.

OBJECTIVE: To evaluate the concordance between preoperative European Society for Medical Oncology (ESMO)-European Society of Gynaecological Oncology (ESGO)-European SocieTy for Radiotherapy and Oncology (ESTRO) risk classification in early-stage endometrial cancer (EC) assessed by biopsy and magnetic resonance imaging (MRI) with this classification based on histology of surgical specimen. METHODS: This bicentric retrospective study included women diagnosed with early-stage EC (≤stage II) who had a complete preoperative assessment and underwent a surgical management from January 2011 to December 2018. Patients were preoperatively classified into 3 degrees of risk of lymph node (LN) involvement based on biopsy and MRI. Based on final histological report, patients were re-classified using the preoperative classification. Concordance between the preoperative assessment and definitive histology was calculated with weighted Cohen's kappa coefficient. RESULTS: A total of 333 women were included and kappa coefficient of preoperative risk classification was 0.49. The risk was underestimated and overestimated in 37% and 10% of cases, respectively. Twenty-nine percent of patients had an incomplete LN staging according to the degree of risk of re-classification. The observed discordance in the risk classification was attributed to MRI in 75% of cases, to biopsy in 18% and in 7% to both (p<0.001). Kappa coefficient for concordance was 0.25 for MRI and 0.73 for biopsy. CONCLUSION: Concordance between preoperative ESMO-ESGO-ESTRO risk classification and final histology is weak. Given that the risk was underestimated in the majority of patients wrongly classified, sentinel LN procedure instead of no LN dissection could be an option offered to preoperative low-risk patients to decrease the indication of second surgery for re-staging and/or to avoid toxicity of adjuvant radiotherapy.