Deep-learning-based synthesis of post-contrast T1-weighted MRI for tumour response assessment in neuro-oncology: a multicentre, retrospective cohort study.

BACKGROUND: Gadolinium-based contrast agents (GBCAs) are widely used to enhance tissue contrast during MRI scans and play a crucial role in the management of patients with cancer. However, studies have shown gadolinium deposition in the brain after repeated GBCA administration with yet unknown clinical significance. We aimed to assess the feasibility and diagnostic value of synthetic post-contrast T1-weighted MRI generated from pre-contrast MRI sequences through deep convolutional neural networks (dCNN) for tumour response assessment in neuro-oncology. METHODS: In this multicentre, retrospective cohort study, we used MRI examinations to train and validate a dCNN for synthesising post-contrast T1-weighted sequences from pre-contrast T1-weighted, T2-weighted, and fluid-attenuated inversion recovery sequences. We used MRI scans with availability of these sequences from 775 patients with glioblastoma treated at Heidelberg University Hospital, Heidelberg, Germany (775 MRI examinations); 260 patients who participated in the phase 2 CORE trial (1083 MRI examinations, 59 institutions); and 505 patients who participated in the phase 3 CENTRIC trial (3147 MRI examinations, 149 institutions). Separate training runs to rank the importance of individual sequences and (for a subset) diffusion-weighted imaging were conducted. Independent testing was performed on MRI data from the phase 2 and phase 3 EORTC-26101 trial (521 patients, 1924 MRI examinations, 32 institutions). The similarity between synthetic and true contrast enhancement on post-contrast T1-weighted MRI was quantified using the structural similarity index measure (SSIM). Automated tumour segmentation and volumetric tumour response assessment based on synthetic versus true post-contrast T1-weighted sequences was performed in the EORTC-26101 trial and agreement was assessed with Kaplan-Meier plots. FINDINGS: The median SSIM score for predicting contrast enhancement on synthetic post-contrast T1-weighted sequences in the EORTC-26101 test set was 0·818 (95% CI 0·817-0·820). Segmentation of the contrast-enhancing tumour from synthetic post-contrast T1-weighted sequences yielded a median tumour volume of 6·31 cm3 (5·60 to 7·14), thereby underestimating the true tumour volume by a median of -0·48 cm3 (-0·37 to -0·76) with the concordance correlation coefficient suggesting a strong linear association between tumour volumes derived from synthetic versus true post-contrast T1-weighted sequences (0·782, 0·751-0·807, p<0·0001). Volumetric tumour response assessment in the EORTC-26101 trial showed a median time to progression of 4·2 months (95% CI 4·1-5·2) with synthetic post-contrast T1-weighted and 4·3 months (4·1-5·5) with true post-contrast T1-weighted sequences (p=0·33). The strength of the association between the time to progression as a surrogate endpoint for predicting the patients' overall survival in the EORTC-26101 cohort was similar when derived from synthetic post-contrast T1-weighted sequences (hazard ratio of 1·749, 95% CI 1·282-2·387, p=0·0004) and model C-index (0·667, 0·622-0·708) versus true post-contrast T1-weighted MRI (1·799, 95% CI 1·314-2·464, p=0·0003) and model C-index (0·673, 95% CI 0·626-0·711). INTERPRETATION: Generating synthetic post-contrast T1-weighted MRI from pre-contrast MRI using dCNN is feasible and quantification of the contrast-enhancing tumour burden from synthetic post-contrast T1-weighted MRI allows assessment of the patient's response to treatment with no significant difference by comparison with true post-contrast T1-weighted sequences with administration of GBCAs. This finding could guide the application of dCNN in radiology to potentially reduce the necessity of GBCA administration. FUNDING: Deutsche Forschungsgemeinschaft.

The added value of health-related quality of life as a prognostic indicator of overall survival and progression-free survival in glioma patients: a meta-analysis based on individual patient data from randomised controlled trials.

OBJECTIVE: Prognostic value of health-related quality of life (HRQoL) data may be important to inform patients in clinical practice and to guide clinical decision-making. Our study investigated the added prognostic value of HRQoL for overall survival (OS) and progression-free survival (PFS) in a large heterogeneous sample of glioma patients, besides known prognostic factors. METHODS: We included individual baseline data from previously published randomised controlled trials (RCTs) in glioma patients in which HRQoL was assessed through the European Organisation for Research and Treatment of Cancer QLQ-C30 and QLQ-BN20 questionnaires. Multivariable Cox regression models (stratified for newly diagnosed versus recurrent disease) were constructed, first with clinical variables (age, sex, tumour type, performance status, allocated treatment and extent of resection) only and subsequently with HRQoL variables added, separately for OS and PFS. The added prognostic value of HRQoL was calculated using C-indices. RESULTS: Baseline HRQoL and clinical data from 15 RCTs were included, comprising 5217 patients. In the model including both clinical and HRQoL variables, better cognitive and role functioning and less motor dysfunction were independently associated with longer OS, whereas better role and cognitive functioning, less nausea and vomiting and more appetite loss were independently associated with prolonged PFS. However, C-indices indicated only a small prognostic improvement of the models for OS and PFS when adding HRQoL to the clinical prognostic variables (+1.1% for OS and +.7% for PFS). CONCLUSION: Our findings demonstrate that several baseline HRQoL variables are independently prognostic for OS and PFS, yet the added value of HRQoL to the known clinical prognostic variables was small.

Automated quantitative tumour response assessment of MRI in neuro-oncology with artificial neural networks: a multicentre, retrospective study.

BACKGROUND: The Response Assessment in Neuro-Oncology (RANO) criteria and requirements for a uniform protocol have been introduced to standardise assessment of MRI scans in both clinical trials and clinical practice. However, these criteria mainly rely on manual two-dimensional measurements of contrast-enhancing (CE) target lesions and thus restrict both reliability and accurate assessment of tumour burden and treatment response. We aimed to develop a framework relying on artificial neural networks (ANNs) for fully automated quantitative analysis of MRI in neuro-oncology to overcome the inherent limitations of manual assessment of tumour burden. METHODS: In this retrospective study, we compiled a single-institution dataset of MRI data from patients with brain tumours being treated at Heidelberg University Hospital (Heidelberg, Germany; Heidelberg training dataset) to develop and train an ANN for automated identification and volumetric segmentation of CE tumours and non-enhancing T2-signal abnormalities (NEs) on MRI. Independent testing and large-scale application of the ANN for tumour segmentation was done in a single-institution longitudinal testing dataset from the Heidelberg University Hospital and in a multi-institutional longitudinal testing dataset from the prospective randomised phase 2 and 3 European Organisation for Research and Treatment of Cancer (EORTC)-26101 trial (NCT01290939), acquired at 38 institutions across Europe. In both longitudinal datasets, spatial and temporal tumour volume dynamics were automatically quantified to calculate time to progression, which was compared with time to progression determined by RANO, both in terms of reliability and as a surrogate endpoint for predicting overall survival. We integrated this approach for fully automated quantitative analysis of MRI in neuro-oncology within an application-ready software infrastructure and applied it in a simulated clinical environment of patients with brain tumours from the Heidelberg University Hospital (Heidelberg simulation dataset). FINDINGS: For training of the ANN, MRI data were collected from 455 patients with brain tumours (one MRI per patient) being treated at Heidelberg hospital between July 29, 2009, and March 17, 2017 (Heidelberg training dataset). For independent testing of the ANN, an independent longitudinal dataset of 40 patients, with data from 239 MRI scans, was collected at Heidelberg University Hospital in parallel with the training dataset (Heidelberg test dataset), and 2034 MRI scans from 532 patients at 34 institutions collected between Oct 26, 2011, and Dec 3, 2015, in the EORTC-26101 study were of sufficient quality to be included in the EORTC-26101 test dataset. The ANN yielded excellent performance for accurate detection and segmentation of CE tumours and NE volumes in both longitudinal test datasets (median DICE coefficient for CE tumours 0·89 [95% CI 0·86-0·90], and for NEs 0·93 [0·92-0·94] in the Heidelberg test dataset; CE tumours 0·91 [0·90-0·92], NEs 0·93 [0·93-0·94] in the EORTC-26101 test dataset). Time to progression from quantitative ANN-based assessment of tumour response was a significantly better surrogate endpoint than central RANO assessment for predicting overall survival in the EORTC-26101 test dataset (hazard ratios ANN 2·59 [95% CI 1·86-3·60] vs central RANO 2·07 [1·46-2·92]; p<0·0001) and also yielded a 36% margin over RANO (p<0·0001) when comparing reliability values (ie, agreement in the quantitative volumetrically defined time to progression [based on radiologist ground truth vs automated assessment with ANN] of 87% [266 of 306 with sufficient data] compared with 51% [155 of 306] with local vs independent central RANO assessment). In the Heidelberg simulation dataset, which comprised 466 patients with brain tumours, with 595 MRI scans obtained between April 27, and Sept 17, 2018, automated on-demand processing of MRI scans and quantitative tumour response assessment within the simulated clinical environment required 10 min of computation time (average per scan). INTERPRETATION: Overall, we found that ANN enabled objective and automated assessment of tumour response in neuro-oncology at high throughput and could ultimately serve as a blueprint for the application of ANN in radiology to improve clinical decision making. Future research should focus on prospective validation within clinical trials and application for automated high-throughput imaging biomarker discovery and extension to other diseases. FUNDING: Medical Faculty Heidelberg Postdoc-Program, Else Kröner-Fresenius Foundation.

Cost-effectiveness of temozolomide for the treatment of newly diagnosed glioblastoma multiforme: a report from the EORTC 26981/22981 NCI-C CE3 Intergroup Study.

BACKGROUND: The study aimed to compare the cost-effectiveness of concomitant and adjuvant temozolomide (TMZ) for the treatment of newly diagnosed glioblastoma multiforme versus initial radiotherapy alone from a public health care perspective. METHODS: The economic evaluation was performed alongside a randomized, multicenter, phase 3 trial. The primary endpoint of the trial was overall survival. Costs included all direct medical costs. Economic data were collected prospectively for a subgroup of 219 patients (38%). Unit costs for drugs, procedures, laboratory and imaging, radiotherapy, and hospital costs per day were collected from the official national reimbursement lists based on 2004. For the cost-effectiveness analysis, survival was expressed as 2.5 years restricted mean estimates. The incremental cost-effectiveness ratio (ICER) was constructed. Confidence intervals for the ICER were calculated using the Fieller method and bootstrapping. RESULTS: The difference in 2.5 years restricted mean survival between the treatment arms was 0.25 life-years and the ICER was euro37,361 per life-year gained with a 95% confidence interval (CI) ranging from euro19,544 to euro123,616. The area between the survival curves of the treatment arms suggests an increase of the overall survival gain for a longer follow-up. An extrapolation of the overall survival per treatment arm and imputation of costs for the extrapolated survival showed a substantial reduction in ICER. CONCLUSIONS: The ICER of euro37,361 per life-year gained is a conservative estimate. We concluded that despite the high TMZ acquisition costs, the costs per life-year gained are comparable to accepted first-line treatment with chemotherapy in patients with cancer.

Panel review of anaplastic oligodendroglioma from European Organization For Research and Treatment of Cancer Trial 26951: assessment of consensus in diagnosis, influence of 1p/19q loss, and correlations with outcome.

The diagnosis of anaplastic oligodendroglioma (AOD) or anaplastic oligoastrocytoma (AOA) is subject to interobserver variation. The aim of this study was to estimate consensus in typing and grading of these tumors using tumor material collected in a large prospective randomized phase III study and to correlate the consensus diagnosis with the 1p/19q status of the tumors and the clinical outcome. The available pathology material of the first 150 patients, randomized into the European Organization for Research and Treatment of Cancer Trial 26951, was reviewed by an independent panel of 9 neuropathologists. The presence of deletions of 1p and 19q was assessed by fluorescence in situ hybridization with locus-specific probes. The panel reached consensus on the diagnosis of AOD in 52% of the tumors that had been diagnosed as AOD by the local pathologists, whereas only 8% of the local diagnosis of AOA was confirmed with consensus. The concordance on the panel diagnosis of AOD was high (intraclass correlation = 86%). The survival curves for AOD with 1p/19q loss, AOD without these losses, and AOA without 1p/19q loss ran separately in this order. The absence of necrosis and the presence of endothelial abnormalities were correlated with better outcomes. In multivariate analysis, patients' age, 1p/19q loss, and necrosis were identified as independent prognostic factors.

Histopathologic assessment of hot-spot microvessel density and vascular patterns in glioblastoma: Poor observer agreement limits clinical utility as prognostic factors: a translational research project of the European Organization for Research and Treatment of Cancer Brain Tumor Group.

BACKGROUND: Hot-spot microvessel density (MVD) and vascular patterns have been reported as histopathologic factors that influence prognosis in retrospective series of malignant gliomas. To investigate clinical utility, the authors systematically studied observer agreement on MVD and vascular patterns and the influence of repeatedly assessed data on patient outcomes in 2 independent glioblastoma series. METHODS: MVD and vascular patterns were assessed retrospectively by 5 observers in 1) a retrospectively compiled glioblastoma series that included 110 patients and 2) a glioblastoma series that included 233 patients who were treated within a randomized trial. MVD was determined in the field of greatest density ("hot-spot"). Predominantly classic or bizarre vascular patterns were determined by using a previously defined algorithm. RESULTS: Observer agreement on MVD was highly variable (range of kappa values, 0.464-0.901). The worst observer agreement was achieved when both the selection of hot-spots and MVD counts were performed independently. Survival analysis did not show a consistent association between repeatedly assessed MVD and patient outcome. Observer agreement on vascular patterns was poor (kappa = 0.297). Survival analysis did not show a consistent association between repeatedly assessed vascular patterns and patient outcome. CONCLUSIONS: Observer agreement on hot-spot MVD and vascular patterns in patients with glioblastoma was poor in independent assessments. MVD and vascular patterns were not associated consistently with patient outcome. Based on these findings, the authors concluded that poor observer agreement limits the clinical utility of histopathologically assessed hot-spot MVD and vascular patterns as prognostic factors in patients with glioblastoma. Improved methodologies for morphologic assessment of glioblastoma vascularization need to be identified.

Cost effectiveness of paclitaxel/cisplatin compared with cyclophosphamide/cisplatin in the treatment of advanced ovarian cancer in Belgium.

OBJECTIVE: To assess the economic impact of two polychemotherapy regimens for patients with advanced ovarian cancer from the perspective of the Belgian health insurance and financing system. DESIGN: An economic evaluation was integrated in an intergroup randomised controlled trial (EORTC 55931) in which patients were randomised to receive the new treatment of paclitaxel and cisplatin or the standard therapy of cyclophosphamide and cisplatin. Data on the use of medical resources were collected prospectively for the 231 European Organization for Research and Treatment of Cancer (EORTC) patients in the trial and costs were valued by using unit prices. The outcome for the economic evaluation was mean survival time as determined by the so-called restricted means method, with the time point of restriction fixed by statistical criteria. A correction of censoring of the cost data collected in the trial was also performed. MAIN OUTCOME MEASURES AND RESULTS: The paclitaxel and cisplatin group experienced a statistically significant improvement in mean survival time of 4 months, which was associated with an increase in the average total cost per patient of 6795 euros (EUR; 1998 values), when costs were assessed over the same period as the gain in mean survival time. This corresponds to a point estimate of the incremental cost-effectiveness ratio of EUR20 385 per life-year gained. The impact of uncertainty was assessed by using a bias-corrected and accelerated bootstrap method with 5000 resamples, and the final results of the analysis are expressed in terms of a cost-effectiveness acceptability curve. CONCLUSIONS: The present economic evaluation has shown that the substitution of paclitaxel for cyclophosphamide in the chemotherapy regimen for women with advanced ovarian cancer leads to a significant improvement in patient survival, which is associated with an increase in costs for the Belgian health insurance system.