Robin Wijsman

Three-dimensional conformal hypofractionated simultaneous integrated boost in breast conserving therapy: Results on local control and survival

PURPOSE To report on local control and survival after breast conserving therapy (BCT) including three-dimensional conformal simultaneous integrated boost irradiation (3D-CRT-SIB) and on the influence of age on outcome. PATIENT AND METHODS For this study, 752 consecutive female breast cancer patients (stages I-III), treated with 3D-CRT-SIB at the University Medical Center Groningen from 2005 to 2008, were retrospectively identified. Median age was 58.4 (range 26-84) years. The SIB fractionation used was: 28×1.8Gy (whole breast) and 28×2.3Gy or 2.4Gy (tumour bed). Next to outcome, we estimated the effect of age on the recurrence-free period (RFP) by multivariate Cox regression survival analysis. RESULTS Median follow-up was 41 (range 3-65) months. Local control was 99.6% at 3 years (6 ipsilateral recurrences). The 3-year locoregional control, RFP and overall survival (OS) rates were 99.2%, 95.5%, and 97.1%, respectively. In multivariate analysis, tumours >2cm (hazard ratio (HR) 3.11; 95% confidence interval (CI) 1.57-6.17) and triple negativity (HR 3.03; 95% CI 1.37-6.67) and not age were associated with impaired RFP. CONCLUSIONS At 3 years, the 3D-CRT-SIB technique in BCT results in excellent local control and OS. Age was not a risk factor for any recurrence.

Multivariable normal-tissue complication modeling of acute esophageal toxicity in advanced stage non-small cell lung cancer patients treated with intensity-modulated (chemo-)radiotherapy

BACKGROUND AND PURPOSE The majority of normal-tissue complication probability (NTCP) models for acute esophageal toxicity (AET) in advanced stage non-small cell lung cancer (AS-NSCLC) patients treated with (chemo-)radiotherapy are based on three-dimensional conformal radiotherapy (3D-CRT). Due to distinct dosimetric characteristics of intensity-modulated radiation therapy (IMRT), 3D-CRT based models need revision. We established a multivariable NTCP model for AET in 149 AS-NSCLC patients undergoing IMRT. MATERIALS AND METHODS An established model selection procedure was used to develop an NTCP model for Grade ⩾2 AET (53 patients) including clinical and esophageal dose-volume histogram parameters. RESULTS The NTCP model predicted an increased risk of Grade ⩾2 AET in case of: concurrent chemoradiotherapy (CCR) [adjusted odds ratio (OR) 14.08, 95% confidence interval (CI) 4.70-42.19; p<0.001], increasing mean esophageal dose [Dmean; OR 1.12 per Gy increase, 95% CI 1.06-1.19; p<0.001], female patients (OR 3.33, 95% CI 1.36-8.17; p=0.008), and ⩾cT3 (OR 2.7, 95% CI 1.12-6.50; p=0.026). The AUC was 0.82 and the model showed good calibration. CONCLUSIONS A multivariable NTCP model including CCR, Dmean, clinical tumor stage and gender predicts Grade ⩾2 AET after IMRT for AS-NSCLC. Prior to clinical introduction, the model needs validation in an independent patient cohort.

Evaluating the use of optimally respiratory gated 18F-FDG-PET in target volume delineation and its influence on radiation doses to the organs at risk in non-small-cell lung cancer patients

ObjectiveThis radiotherapy planning study evaluated tumour delineation using both optimally respiratory gated and nongated fluorine-18 fluorodeoxyglucose-PET (18F-FDG-PET). MethodsFor 22 non-small-cell lung tumours, both scans were used to create the nongated and gated (g) gross tumour volumes (GTVg) together with the accompanying clinical target volumes (CTV) and planning target volumes (PTV). The size of the target volumes (TV) was evaluated and the accompanying radiotherapy plans were created to study the radiation doses to the organs at risk (OAR). ResultsThe median volumes of GTVg, CTVg and PTVg were statistically significantly smaller compared with the corresponding nongated volumes, resulting in a median TV reduction of 0.5 cm3 (interquartile range 0.1–1.2), 1.5 cm3 (−0.2 to 7.0) and 2.3 cm3 (−0.5 to 11.3) for the GTVg, CTVg and PTVg, respectively. For the OAR, only the percentage of lung (GTV included) receiving at least 35 Gy was significantly smaller after gating, with a median difference in lung volume receiving at least 35 Gy of 5.7 cm3 (interquartile range −0.8 to 30.50). ConclusionCompared with nongated 18F-FDG-PET, the TVs obtained with optimally respiratory gated 18F-FDG-PET were significantly smaller, however, without a clinically relevant difference in radiation dose to the OAR.

Comparison of toxicity and outcome in advanced stage non-small cell lung cancer patients treated with intensity-modulated (chemo-)radiotherapy using IMRT or VMAT

Retrospective evaluation of 188 advanced stage non-small cell lung cancer patients treated with IMRT or VMAT revealed a limited increase of moderate to severe acute esophageal toxicity after VMAT. Acute pulmonary toxicity and severe late toxicity were low. Overall survival did not differ between the IMRT and VMAT groups.

Machine learning algorithms for outcome prediction in (chemo)radiotherapy: An empirical comparison of classifiers

Purpose Machine learning classification algorithms (classifiers) for prediction of treatment response are becoming more popular in radiotherapy literature. General Machine learning literature provides evidence in favor of some classifier families (random forest, support vector machine, gradient boosting) in terms of classification performance. The purpose of this study is to compare such classifiers specifically for (chemo)radiotherapy datasets and to estimate their average discriminative performance for radiation treatment outcome prediction. Methods We collected 12 datasets (3496 patients) from prior studies on post‐(chemo)radiotherapy toxicity, survival, or tumor control with clinical, dosimetric, or blood biomarker features from multiple institutions and for different tumor sites, that is, (non‐)small‐cell lung cancer, head and neck cancer, and meningioma. Six common classification algorithms with built‐in feature selection (decision tree, random forest, neural network, support vector machine, elastic net logistic regression, LogitBoost) were applied on each dataset using the popular open‐source R package caret. The R code and documentation for the analysis are available online (https://github.com/timodeist/classifier_selection_code). All classifiers were run on each dataset in a 100‐repeated nested fivefold cross‐validation with hyperparameter tuning. Performance metrics (AUC, calibration slope and intercept, accuracy, Cohens kappa, and Brier score) were computed. We ranked classifiers by AUC to determine which classifier is likely to also perform well in future studies. We simulated the benefit for potential investigators to select a certain classifier for a new dataset based on our study (pre‐selection based on other datasets) or estimating the best classifier for a dataset (set‐specific selection based on information from the new dataset) compared with uninformed classifier selection (random selection). Results Random forest (best in 6/12 datasets) and elastic net logistic regression (best in 4/12 datasets) showed the overall best discrimination, but there was no single best classifier across datasets. Both classifiers had a median AUC rank of 2. Preselection and set‐specific selection yielded a significant average AUC improvement of 0.02 and 0.02 over random selection with an average AUC rank improvement of 0.42 and 0.66, respectively. Conclusion Random forest and elastic net logistic regression yield higher discriminative performance in (chemo)radiotherapy outcome and toxicity prediction than other studied classifiers. Thus, one of these two classifiers should be the first choice for investigators when building classification models or to benchmark ones own modeling results against. Our results also show that an informed preselection of classifiers based on existing datasets can improve discrimination over random selection.

Esophageal wall dose-surface maps do not improve the predictive performance of a multivariable NTCP model for acute esophageal toxicity in advanced stage NSCLC patients treated with intensity-modulated (chemo-)radiotherapy

In our previous work, a multivariable normal-tissue complication probability (NTCP) model for acute esophageal toxicity (AET) Grade  ⩾2 after highly conformal (chemo-)radiotherapy for non-small cell lung cancer (NSCLC) was developed using multivariable logistic regression analysis incorporating clinical parameters and mean esophageal dose (MED). Since the esophagus is a tubular organ, spatial information of the esophageal wall dose distribution may be important in predicting AET. We investigated whether the incorporation of esophageal wall dose-surface data with spatial information improves the predictive power of our established NTCP model. For 149 NSCLC patients treated with highly conformal radiation therapy esophageal wall dose-surface histograms (DSHs) and polar dose-surface maps (DSMs) were generated. DSMs were used to generate new DSHs and dose-length-histograms that incorporate spatial information of the dose-surface distribution. From these histograms dose parameters were derived and univariate logistic regression analysis showed that they correlated significantly with AET. Following our previous work, new multivariable NTCP models were developed using the most significant dose histogram parameters based on univariate analysis (19 in total). However, the 19 new models incorporating esophageal wall dose-surface data with spatial information did not show improved predictive performance (area under the curve, AUC range 0.79-0.84) over the established multivariable NTCP model based on conventional dose-volume data (AUC  =  0.84). For prediction of AET, based on the proposed multivariable statistical approach, spatial information of the esophageal wall dose distribution is of no added value and it is sufficient to only consider MED as a predictive dosimetric parameter.

External validation of an NTCP model for acute esophageal toxicity in locally advanced NSCLC patients treated with intensity-modulated (chemo-)radiotherapy

BACKGROUND AND PURPOSE We externally validated a previously established multivariable normal-tissue complication probability (NTCP) model for Grade ≥2 acute esophageal toxicity (AET) after intensity-modulated (chemo-)radiotherapy or volumetric-modulated arc therapy for locally advanced non-small cell lung cancer. MATERIALS AND METHODS A total of 603 patients from five cohorts (A-E) within four different Dutch institutes were included. Using the NTCP model, containing predictors concurrent chemoradiotherapy, mean esophageal dose, gender and clinical tumor stage, the risk of Grade ≥2 AET was estimated per patient and model discrimination and (re)calibration performance were evaluated. RESULTS Four validation cohorts (A, B, D, E) experienced higher incidence of Grade ≥2 AET compared to the training cohort (49.3-70.2% vs 35.6%; borderline significant for one cohort, highly significant for three cohorts). Cohort C experienced lower Grade ≥2 AET incidence (21.7%, p < 0.001). For three cohorts (A-C), discriminative performance was similar to the training cohort (area under the curve (AUC) 0.81-0.89 vs 0.84). In the two remaining cohorts (D-E) the model showed poor discriminative power (AUC 0.64 and 0.63). Reasonable calibration performance was observed in two cohorts (A-B), and recalibration further improved performance in all three cohorts with good discrimination (A-C). Recalibration for the two poorly discriminating cohorts (D-E) did not improve performance. CONCLUSIONS The NTCP model for AET prediction was successfully validated in three out of five patient cohorts (AUC ≥0.80). The model did not perform well in two cohorts, which included patients receiving substantially different treatment. Before applying the model in clinical practice, validation of discrimination and (re)calibration performance in a local cohort is recommended.

Stereotactic radiotherapy boost after definite chemoradiation for non-responding locally advanced NSCLC based on early response monitoring 18F-FDG-PET/CT

Background and purpose Prognosis of locally advanced non-small cell lung cancer remains poor despite chemoradiation. This planning study evaluated a stereotactic boost after concurrent chemoradiotherapy (30 × 2 Gy) to improve local control. The maximum achievable boost directed to radioresistant primary tumor subvolumes based on pre-treatment fluorine-18 fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG-PET/CT) (pre-treatment-PET) and on early response monitoring 18F-FDG-PET/CT (ERM-PET) was compared. Materials and methods For ten patients, a stereotactic boost (VMAT) was planned on ERM-PET (PTVboost;ERM) and on pre-treatment-PET (PTVboost;pre-treatment), using a 70% SUVmax threshold with 7 mm margin to segmentate radioresistant subvolumes. Dose was escalated till organ at risk (OAR) constraints were met, aiming to plan at least 18 Gy in 3 fractions (EQD2 84 Gy/BED 100.8 Gy). Results In five patients, PTVboost;ERM was 9–40% smaller relative to PTVboost;pre-treatment. Overlap of PTVboost;ERM with OARs decreased also compared to overlap of PTVboost;pre-treatment with OARs. However, any overlap with OAR remained in 4/5 patients resulting in minimal differences between planned dose before and during treatment. Median dose (EQD2) covering 99% and 95% of PTVboost;ERM were 15 Gy and 18 Gy respectively. Median boost volume receiving a physical dose of  ≥ 18 Gy (V18) was 88%. V18 was ≥ 80% for PTVboost in six patients. Conclusions A significant stereotactic boost to volumes with high initial or persistent 18F-FDG-uptake could be planned above 60 Gy chemoradiation. Differences between planned dose before and during treatment were minimal. However, as an ERM-PET also monitors changes in tumor position, we recommend to plan the boost on the ERM-PET.

Development of symptomatic brain metastases after chemoradiotherapy for stage III non-small cell lung cancer: Does the type of chemotherapy regimen matter?

OBJECTIVES Symptomatic brain metastases (BM) occur frequently after chemoradiotherapy (CRT) for stage III NSCLC. Aim of the current study was to determine whether the specific chemotherapy used in a CRT regimen influences BM development. MATERIALS AND METHODS Retrospective multicenter study including all consecutive stage III NSCLC who completed CRT. Primary endpoints: symptomatic BM development, whether this was the only site of first relapse. Differences between regimens were assessed with a logistic regression model including known BM risk factors and the specific chemotherapy: concurrent versus sequential (cCRT/sCRT), within cCRT: daily low dose cisplatin (LDC)-cyclic dose polychemotherapy; LDC-(non-)taxane cyclic dose; LDC-polychemotherapy subgroups of ≥50 patients. RESULTS Between January 2006 and June 2014, 838 patients were eligible (737 cCRT, 101 sCRT). 18.2% developed symptomatic BM, 8.0% had BM as only site of first relapse. BM patients were significantly younger, female, had more advanced N-stage and had adenocarcinoma histology. In both cCRT and sCRT BM were found in 18% (p=0.904). In cyclic dose cCRT (N=346) and LDC (N=391) BM were found in 18.8% and 17.9%, respectively (p=0.757). In 7.2% and 8.7%, respectively, BM were the only site of first relapse (p=0.463). The chemotherapy used (cCRT versus sCRT) had no influence on BM development, not for all brain relapses nor as only site of first relapse (OR 0.88 (p=0.669), OR 0.93 (p=0.855), respectively). LDC versus cyclic dose cCRT was not significantly different: neither for all brain relapses nor as only site of first relapse (OR 0.96 (p=0.819), OR 1.21 (p=0.498), respectively). Comparable results were found for LDC versus cyclic dose non-taxane (N=277) and cyclic dose taxane regimens (N=69) and for cCRT regimens with ≥50 patients (LDC versus cisplatin/etoposide (N=188), cisplatin/vinorelbin (N=65), weekly cisplatin/docetaxel (N=60)). CONCLUSION approximately 18% developed symptomatic BM after stage III diagnosis, not dependent on type of chemotherapy regimen used within a CRT treatment.