Development of Clinical Radiomics-Based Models to Predict Survival Outcome in Pancreatic Ductal Adenocarcinoma: A Multicenter Retrospective Study.

PURPOSE: This multicenter retrospective study aims to identify reliable clinical and radiomic features to build machine learning models that predict progression-free survival (PFS) and overall survival (OS) in pancreatic ductal adenocarcinoma (PDAC) patients. METHODS: Between 2010 and 2020 pre-treatment contrast-enhanced CT scans of 287 pathology-confirmed PDAC patients from two sites of the Hopital Universitaire de Bruxelles (HUB) and from 47 hospitals within the HUB network were retrospectively analysed. Demographic, clinical, and survival data were also collected. Gross tumour volume (GTV) and non-tumoral pancreas (RPV) were semi-manually segmented and radiomics features were extracted. Patients from two HUB sites comprised the training dataset, while those from the remaining 47 hospitals of the HUB network constituted the testing dataset. A three-step method was used for feature selection. Based on the GradientBoostingSurvivalAnalysis classifier, different machine learning models were trained and tested to predict OS and PFS. Model performances were assessed using the C-index and Kaplan-Meier curves. SHAP analysis was applied to allow for post hoc interpretability. RESULTS: A total of 107 radiomics features were extracted from each of the GTV and RPV. Fourteen subgroups of features were selected: clinical, GTV, RPV, clinical & GTV, clinical & GTV & RPV, GTV-volume and RPV-volume both for OS and PFS. Subsequently, 14 Gradient Boosting Survival Analysis models were trained and tested. In the testing dataset, the clinical & GTV model demonstrated the highest performance for OS (C-index: 0.72) among all other models, while for PFS, the clinical model exhibited a superior performance (C-index: 0.70). CONCLUSIONS: An integrated approach, combining clinical and radiomics features, excels in predicting OS, whereas clinical features demonstrate strong performance in PFS prediction.

Treatment planning for MR-guided SBRT of pancreatic tumors on a 1.5 T MR-Linac: A global consensus protocol.

Background and purpose: Treatment planning for MR-guided stereotactic body radiotherapy (SBRT) for pancreatic tumors can be challenging, leading to a wide variation of protocols and practices. This study aimed to harmonize treatment planning by developing a consensus planning protocol for MR-guided pancreas SBRT on a 1.5 T MR-Linac. Materials and methods: A consortium was founded of thirteen centers that treat pancreatic tumors on a 1.5 T MR-Linac. A phased planning exercise was conducted in which centers iteratively created treatment plans for two cases of pancreatic cancer. Each phase was followed by a meeting where the instructions for the next phase were determined. After three phases, a consensus protocol was reached. Results: In the benchmarking phase (phase I), substantial variation between the SBRT protocols became apparent (for example, the gross tumor volume (GTV) D99% ranged between 36.8 - 53.7 Gy for case 1, 22.6 - 35.5 Gy for case 2). The next phase involved planning according to the same basic dosimetric objectives, constraints, and planning margins (phase II), which led to a large degree of harmonization (GTV D99% range: 47.9-53.6 Gy for case 1, 33.9-36.6 Gy for case 2). In phase III, the final consensus protocol was formulated in a treatment planning system template and again used for treatment planning. This not only resulted in further dosimetric harmonization (GTV D99% range: 48.2-50.9 Gy for case 1, 33.5-36.0 Gy for case 2) but also in less variation of estimated treatment delivery times. Conclusion: A global consensus protocol has been developed for treatment planning for MR-guided pancreatic SBRT on a 1.5 T MR-Linac. Aside from harmonizing the large variation in the current clinical practice, this protocol can provide a starting point for centers that are planning to treat pancreatic tumors on MR-Linac systems.

Radiomics software comparison using digital phantom and patient data: IBSI-compliance does not guarantee concordance of feature values.

INTRODUCTION: Radiomics is a promising imaging-based tool which could enhance clinical observation and identify representative features. To avoid different interpretations, the Image Biomarker Standardisation Initiative (IBSI) imposed conditions for harmonisation. This study evaluates IBSI-compliant radiomics applications against a known benchmark and clinical datasets for agreements. MATERIALS AND METHODS: The three radiomics platforms compared were RadiomiX Research Toolbox, LIFEx v7.0.0, and syngo.via Frontier Radiomics v1.2.5 (based on PyRadiomics v2.1). Basic assessment included comparing feature names and their formulas. The IBSI digital phantom was used for evaluation against reference values. For agreement evaluation (including same software but different versions), two clinical datasets were used: 27 contrast-enhanced computed tomography (CECT) of colorectal liver metastases and 39 magnetic resonance imaging (MRI) of breast cancer, including intravoxel incoherent motion (IVIM) and dynamic contrast-enhanced (DCE) MRI. The intraclass correlation coefficient (ICC, lower 95% confidence interval) was used, with 0.9 as the threshold for excellent agreement. RESULTS: The three radiomics applications share 41 (3 shape, 8 intensity, 30 texture) out of 172, 84 and 110 features for RadiomiX, LIFEx and syngo.via, respectively, as well as wavelet filtering. The naming convention is, however, different between them. Syngo.via had excellent agreement with the IBSI benchmark, while LIFEx and RadiomiX showed slightly worse agreement. Excellent reproducibility was achieved for shape features only, while intensity and texture features varied considerably with the imaging type. For intensity, excellent agreement ranged from 46% for the DCE maps to 100% for CECT, while this lowered to 44% and 73% for texture features, respectively. Wavelet features produced the greatest variation between applications, with an excellent agreement for only 3% to 11% features. CONCLUSION: Even with IBSI-compliance, the reproducibility of features between radiomics applications is not guaranteed. To evaluate variation, quality assurance of radiomics applications should be performed and repeated when updating to a new version or adding a new modality.

Pre-trial quality assurance of diffusion-weighted MRI for radiomic analysis and the role of harmonisation.

PURPOSE: The aim of this study was to perform a quantitative quality assurance of diffusion-weighted MRI to assess the variability of the mean apparent diffusion coefficient (ADC) and other radiomic features across the scanners involved in the REGINA trial. MATERIALS AND METHODS: The NIST/QIBA diffusion phantom was acquired on six 3 T scanners from five centres with a rectum-specific diffusion protocol. All sequences were repeated in each scan session without moving the phantom from the table. Linear interpolation to two isotropic voxel spacing (0.9 and 4 mm) was performed as well as the ComBat feature harmonisation method between scanners. The absolute accuracy error was evaluated for the mean ADC. Repeatability and reproducibility within-subject coefficients of variation (wCV) were computed for 142 radiomic features. RESULTS: For the mean ADC, accuracy error ranged between 0.1 % and 8.5 %, repeatability was <1 % and reproducibility was <3 % for diffusivity range between 0.4 and 1.1x10-3mm2/s. For the other radiomic features, wCV was below 10 % for 24 % and 15 % features for repeatability with resampling 0.9 mm and 4 mm, respectively, and 13 % and 11 % feature for reproducibility. ComBat method could improve significantly the wCV compared to reproducibility without ComBat (p-value < 0.001) but variation was still high for most of the features. CONCLUSION: Our study provided the first investigation of feature selection for development of robust predictive models in the REGINA trial, demonstrating the added value of such a quality assurance process to select conventional and radiomic features in prospective multicentre trials.