Search

Partial dependence plots of the multivariate models for PP-prediction.

Summary of patient outcome of the individual groups (with landmark analysis) The landmark method was applied, that is all events before 5 months were excluded. 95% confidence intervals were provided in parentheses. PP-only patients were the best performing group, with a similar outcome compared to responding patients. TPD-only patients presented a significantly worse OS of 10 vs. 30 months in the PP-only group (p=0.002, FWER=0.010). Patients with mixed PP&TPD were in between both other groups.

Hyperparameter space in model tuning.

Distribution of pseudoprogression and true progression and association with OS, PFS and iPFS (no landmark).

Summary of patient outcome of the individual groups (without landmark analysis) 95% confidence intervals were provided in parentheses. PP-only patients were the best performing group, with a similar outcome compared to responding patients. TPD-only patients presented a significantly worse OS of 9 vs. 30 months in the PP-only group (p=0.001, FWER=0.007). Patients with mixed PP&TPD were in between both other groups.

Feature weights of the multivariate models for PP-prediction.

Purpose:We assessed the predictive potential of positron emission tomography (PET)/CT-based radiomics, lesion volume, and routine blood markers for early differentiation of pseudoprogression from true progression at 3 months.Experimental Design:112 patients with metastatic melanoma treated with immune checkpoint inhibition were included in our study. Median follow-up duration was 22 months. 716 metastases were segmented individually on CT and 2[18F]fluoro-2-deoxy-D-glucose (FDG)-PET imaging at three timepoints: baseline (TP0), 3 months (TP1), and 6 months (TP2). Response was defined on a lesion-individual level (RECIST 1.1) and retrospectively correlated with FDG-PET/CT radiomic features and the blood markers LDH/S100. Seven multivariate prediction model classes were generated.Results:Two-year (median) overall survival, progression-free survival, and immune progression–free survival were 69% (not reached), 24% (6 months), and 42% (16 months), respectively. At 3 months, 106 (16%) lesions had progressed, of which 30 (5%) were identified as pseudoprogression at 6 months. Patients with pseudoprogressive lesions and without true progressive lesions had a similar outcome to responding patients and a significantly better 2-year overall survival of 100% (30 months), compared with 15% (10 months) in patients with true progressions/without pseudoprogression (P = 0.002). Patients with mixed progressive/pseudoprogressive lesions were in between at 53% (25 months). The blood prediction model (LDH+S100) achieved an AUC = 0.71. Higher LDH/S100 values indicated a low chance of pseudoprogression. Volume-based models: AUC = 0.72 (TP1) and AUC = 0.80 (delta-volume between TP0/TP1). Radiomics models (including/excluding volume-related features): AUC = 0.79/0.78. Combined blood/volume model: AUC = 0.79. Combined blood/radiomics model (including volume-related features): AUC = 0.78. The combined blood/radiomics model (excluding volume-related features) performed best: AUC = 0.82.Conclusions:Noninvasive PET/CT-based radiomics, especially in combination with blood parameters, are promising biomarkers for early differentiation of pseudoprogression, potentially avoiding added toxicity or delayed treatment switch.

We explored imaging and blood bio-markers for survival prediction in a cohort of patients with metastatic melanoma treated with immune checkpoint inhibition.94 consecutive metastatic melanoma patients treated with immune checkpoint inhibition were included into this study. PET/CT imaging was available at baseline (Tp0), 3 months (Tp1) and 6 months (Tp2) after start of immunotherapy. Radiological response at Tp2 was evaluated using iRECIST. Total tumor burden (TB) at each time-point was measured and relative change of TB compared to baseline was calculated. LDH, CRP and S-100B were also analyzed. Cox proportional hazards model and logistic regression were used for survival analysis.iRECIST at Tp2 was significantly associated with overall survival (OS) with C-index=0.68. TB at baseline was not associated with OS, whereas TB at Tp1 and Tp2 provided similar predictive power with C-index of 0.67 and 0.71, respectively. Appearance of new metastatic lesions during follow-up was an independent prognostic factor (C-index=0.73). Elevated LDH and S-100B ratios at Tp2 were significantly associated with worse OS: C-index=0.73 for LDH and 0.73 for S-100B. Correlation of LDH with TB was weak (r=0.34). A multivariate model including TB change, S-100B, and appearance of new lesions showed the best predictive performance with C-index=0.83.Our analysis shows only a weak correlation between LDH and TB. Additionally, baseline TB was not a prognostic factor in our cohort. A multivariate model combining early blood and imaging biomarkers achieved the best predictive power with regard to survival, outperforming iRECIST.

Purpose: We assessed the predictive potential of positron emission tomography (PET)/CT-based radiomics, lesion volume, and routine blood markers for early differentiation of pseudoprogression from true progression at 3 months. Experimental Design: 112 patients with metastatic melanoma treated with immune checkpoint inhibition were included in our study. Median follow-up duration was 22 months. 716 metastases were segmented individually on CT and 2[18F]fluoro-2-deoxy-D-glucose (FDG)-PET imaging at three timepoints: baseline (TP0), 3 months (TP1), and 6 months (TP2). Response was defined on a lesion-individual level (RECIST 1.1) and retrospectively correlated with FDG-PET/CT radiomic features and the blood markers LDH/S100. Seven multivariate prediction model classes were generated. Results: Two-year (median) overall survival, progression-free survival, and immune progression–free survival were 69% (not reached), 24% (6 months), and 42% (16 months), respectively. At 3 months, 106 (16%) lesions had progressed, of which 30 (5%) were identified as pseudoprogression at 6 months. Patients with pseudoprogressive lesions and without true progressive lesions had a similar outcome to responding patients and a significantly better 2-year overall survival of 100% (30 months), compared with 15% (10 months) in patients with true progressions/without pseudoprogression (P = 0.002). Patients with mixed progressive/pseudoprogressive lesions were in between at 53% (25 months). The blood prediction model (LDH+S100) achieved an AUC = 0.71. Higher LDH/S100 values indicated a low chance of pseudoprogression. Volume-based models: AUC = 0.72 (TP1) and AUC = 0.80 (delta-volume between TP0/TP1). Radiomics models (including/excluding volume-related features): AUC = 0.79/0.78. Combined blood/volume model: AUC = 0.79. Combined blood/radiomics model (including volume-related features): AUC = 0.78. The combined blood/radiomics model (excluding volume-related features) performed best: AUC = 0.82. Conclusions: Noninvasive PET/CT-based radiomics, especially in combination with blood parameters, are promising biomarkers for early differentiation of pseudoprogression, potentially avoiding added toxicity or delayed treatment switch.

BACKGROUND Radiomics is a promising tool for the identification of new prognostic biomarkers. Radiomic features can be affected by different scanning protocols, often present in retrospective and prospective clinical data. We compared a computed tomography (CT) radiomics model based on a large but highly heterogeneous multicentric image dataset with robust feature pre-selection to a model based on a smaller but standardized image dataset without pre-selection. MATERIALS AND METHODS Primary tumor radiomics was extracted from pre-treatment CTs of IIIA/N2/IIIB NSCLC patients from a prospective Swiss multicentric randomized trial (npatient = 124, ninstitution = 14, SAKK 16/00) and a validation dataset (npatient = 31, ninstitution = 1). Four robustness studies investigating inter-observer delineation variation, motion, convolution kernel, and contrast were conducted to identify robust features using an intraclass correlation coefficient threshold >0.9. Two 12-months overall survival (OS) logistic regression models were trained: (a) on the entire multicentric heterogeneous dataset but with robust feature pre-selection (MCR) and (b) on a smaller standardized subset using all features (STD). Both models were validated on the validation dataset acquired with similar reconstruction parameters as the STD dataset. The model performances were compared using the DeLong test. RESULTS In total, 113 stable features were identified (nshape = 8, nintensity = 0, ntexture = 7, nwavelet = 98). The convolution kernel had the strongest influence on the feature robustness (

Purpose: Due to the sharp gradients of intensity-modulated radiotherapy (IMRT) dose distributions, treatment uncertainties may induce substantial deviations from the planned dose during irradiation. Here, we investigate if the planned mean dose to parotid glands in combination with the dose gradient and information about anatomical changes during the treatment improves xerostomia prediction in head and neck cancer patients. Materials and methods: Eighty eight patients were retrospectively analyzed. Three features of the contralateral parotid gland were studied in terms of their association with the outcome, i.e., grade ≥ 2 (G2) xerostomia between 6 months and 2 years after radiotherapy (RT): planned mean dose (MD), average lateral dose gradient (GRADX), and parotid gland migration toward medial (PGM). PGM was estimated using daily megavoltage computed tomography (MVCT) images. Three logistic regression models where analyzed: based on (1) MD only, (2) MD and GRADX, and (3) MD, GRADX, and PGM. Additionally, the cohort was stratified based on the median value of GRADX, and a univariate analysis was performed to study the association of the MD with the outcome for patients in low- and high-GRADX domains. Results: The planned MD failed to recognize G2 xerostomia patients (AUC = 0.57). By adding the information of GRADX (second model), the model performance increased to AUC = 0.72. The addition of PGM (third model) led to further improvement in the recognition of the outcome (AUC = 0.79). Remarkably, xerostomia patients in the low-GRADX domain were successfully identified (AUC = 0.88) by the MD alone. Conclusions: Our results indicate that GRADX and PGM, which together serve as a proxy of dosimetric changes, provide valuable information for xerostomia prediction.

Objectives: In this study, we aimed to assess the impact of different CT reconstruction kernels on the stability of radiomic features and the transferability between different diseases and tissue types. Three lung diseases were evaluated, i.e. non-small cell lung cancer (NSCLC), malignant pleural mesothelioma (MPM) and interstitial lung disease related to systemic sclerosis (SSc-ILD) as well as four different tissue types, i.e. primary tumor, largest involved lymph node ipsilateral and contralateral lung. Methods: Pre-treatment non-contrast enhanced CT scans from 23 NSCLC, 10 MPM and 12 SSc-ILD patients were collected retrospectively. For each patient, CT scans were reconstructed using smooth and sharp kernel in filtered back projection. The regions of interest (ROIs) were contoured on the smooth kernel-based CT and transferred to the sharp kernel-based CT. The voxels were resized to the largest voxel dimension of each cohort. In total, 1386 features were analyzed. Feature stability was assessed using the intraclass correlation coefficient. Features above the stability threshold >0.9 were considered stable. Results: We observed a strong impact of the reconstruction method on stability of the features (at maximum 26% of the 1386 features were stable). Intensity features were the most stable followed by texture and wavelet features. The wavelet features showed a positive correlation between percentage of stable features and size of the ROI (R2 = 0.79, p = 0.005). Lymph node radiomics showed poorest stability (Conclusion: The robustness of radiomic features is strongly affected by different reconstruction kernels. The effect is largely influenced by the tissue type and less by the disease type. Advances in knowledge: The study presents to our knowledge the most complete analysis on the impact of convolution kernel on the robustness of CT-based radiomics for four relevant tissue types in three different lung diseases.

Purpose: The purpose of this study is to investigate whether machine learning with dosiomic, radiomic, and demographic features allows for xerostomia risk assessment more precise than normal tissue complication probability (NTCP) models based on the mean radiation dose to parotid glands. Material and methods: A cohort of 153 head-and-neck cancer patients was used to model xerostomia at 0-6 months (early), 6-15 months (late), 15-24 months (long-term), and at any time (a longitudinal model) after radiotherapy. Predictive power of the features was evaluated by the area under the receiver operating characteristic curve (AUC) of univariate logistic regression models. The multivariate NTCP models were tuned and tested with single and nested cross-validation, respectively. We compared predictive performance of seven classification algorithms, six feature selection methods, and ten data cleaning/class balancing techniques using the Friedman test and the Nemenyi post hoc analysis. Results: NTCP models based on the parotid mean dose failed to predict xerostomia (AUCs < 0.60). The most informative predictors were found for late and long-term xerostomia. Late xerostomia correlated with the contralateral dose gradient in the anterior posterior (AUC = 0.72) and the right left (AUC = 0.68) direction, whereas long-term xerostomia was associated with parotid volumes (AUCs > 0.85), dose gradients in the right left (AUCs > 0.78), and the anterior posterior (AUCs > 0.72) direction. Multivariate models of long-term xerostomia were typically based on the parotid volume, the parotid eccentricity, and the dose volume histogram (DVH) spread with the generalization AUCs ranging from 0.74 to 0.88. On average, support vector machines and extra-trees were the top performing classifiers, whereas the algorithms based on logistic regression were the best choice for feature selection. We found no advantage in using data cleaning or class balancing methods. Conclusion: We demonstrated that incorporation of organ- and dose-shape descriptors is beneficial for xerostomia prediction in highly conformal radiotherapy treatments. Due to strong reliance on patient-specific, dose-independent factors, our results underscore the need for development of personalized data-driven risk profiles for NTCP models of xerostomia. The facilitated machine learning pipeline is described in detail and can serve as a valuable reference for future work in radiomic and dosiomic NTCP modeling.