The Image Biomarker Standardization Initiative: Standardized Convolutional Filters for Reproducible Radiomics and Enhanced Clinical Insights.

Filters are commonly used to enhance specific structures and patterns in images, such as vessels or peritumoral regions, to enable clinical insights beyond the visible image using radiomics. However, their lack of standardization restricts reproducibility and clinical translation of radiomics decision support tools. In this special report, teams of researchers who developed radiomics software participated in a three-phase study (September 2020 to December 2022) to establish a standardized set of filters. The first two phases focused on finding reference filtered images and reference feature values for commonly used convolutional filters: mean, Laplacian of Gaussian, Laws and Gabor kernels, separable and nonseparable wavelets (including decomposed forms), and Riesz transformations. In the first phase, 15 teams used digital phantoms to establish 33 reference filtered images of 36 filter configurations. In phase 2, 11 teams used a chest CT image to derive reference values for 323 of 396 features computed from filtered images using 22 filter and image processing configurations. Reference filtered images and feature values for Riesz transformations were not established. Reproducibility of standardized convolutional filters was validated on a public data set of multimodal imaging (CT, fluorodeoxyglucose PET, and T1-weighted MRI) in 51 patients with soft-tissue sarcoma. At validation, reproducibility of 486 features computed from filtered images using nine configurations × three imaging modalities was assessed using the lower bounds of 95% CIs of intraclass correlation coefficients. Out of 486 features, 458 were found to be reproducible across nine teams with lower bounds of 95% CIs of intraclass correlation coefficients greater than 0.75. In conclusion, eight filter types were standardized with reference filtered images and reference feature values for verifying and calibrating radiomics software packages. A web-based tool is available for compliance checking.

A common [18F]-FDG PET radiomic signature to predict survival in patients with HPV-induced cancers.

Locally advanced cervical cancer (LACC) and anal and oropharyngeal squamous cell carcinoma (ASCC and OPSCC) are mostly caused by oncogenic human papillomaviruses (HPV). In this paper, we developed machine learning (ML) models based on clinical, biological, and radiomic features extracted from pre-treatment fluorine-18-fluorodeoxyglucose positron emission tomography ([18F]-FDG PET) images to predict the survival of patients with HPV-induced cancers. For this purpose, cohorts from five institutions were used: two cohorts of patients treated for LACC including 104 patients from Gustave Roussy Campus Cancer (Center 1) and 90 patients from Leeds Teaching Hospitals NHS Trust (Center 2), two datasets of patients treated for ASCC composed of 66 patients from Institut du Cancer de Montpellier (Center 3) and 67 patients from Oslo University Hospital (Center 4), and one dataset of 45 OPSCC patients from the University Hospital of Zurich (Center 5). Radiomic features were extracted from baseline [18F]-FDG PET images. The ComBat technique was applied to mitigate intra-scanner variability. A modified consensus nested cross-validation for feature selection and hyperparameter tuning was applied on four ML models to predict progression-free survival (PFS) and overall survival (OS) using harmonized imaging features and/or clinical and biological variables as inputs. Each model was trained and optimized on Center 1 and Center 3 cohorts and tested on Center 2, Center 4, and Center 5 cohorts. The radiomic-based CoxNet model achieved C-index values of 0.75 and 0.78 for PFS and 0.76, 0.74, and 0.75 for OS on the test sets. Radiomic feature-based models had superior performance compared to the bioclinical ones, and combining radiomic and bioclinical variables did not improve the performances. Metabolic tumor volume (MTV)-based models obtained lower C-index values for a majority of the tested configurations but quite equivalent performance in terms of time-dependent AUCs (td-AUC). The results demonstrate the possibility of identifying common PET-based image signatures for predicting the response of patients with induced HPV pathology, validated on multi-center multiconstructor data.

European Society for Radiotherapy and Oncology and European Organisation for Research and Treatment of Cancer consensus on re-irradiation: definition, reporting, and clinical decision making.

Re-irradiation can be considered for local recurrence or new tumours adjacent to a previously irradiated site to achieve durable local control for patients with cancer who have otherwise few therapeutic options. With the use of new radiotherapy techniques, which allow for conformal treatment plans, image guidance, and short fractionation schemes, the use of re-irradiation for different sites is increasing in clinical settings. Yet, prospective evidence on re-irradiation is scarce and our understanding of the underlying radiobiology is poor. Our consensus on re-irradiation aims to assist in re-irradiation decision making, and to standardise the classification of different forms of re-irradiation and reporting. The consensus has been endorsed by the European Society for Radiotherapy and Oncology and the European Organisation for Research and Treatment of Cancer. The use of this classification in daily clinical practice and research will facilitate accurate understanding of the clinical implications of re-irradiation and allow for cross-study comparisons. Data gathered in a uniform manner could be used in the future to make recommendations for re-irradiation on the basis of clinical evidence. The consensus document is based on an adapted Delphi process and a systematic review of the literature was done according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA).

Computed tomography-based radiomics decodes prognostic and molecular differences in interstitial lung disease related to systemic sclerosis.

BACKGROUND: Radiomic features calculated from routine medical images show great potential for personalised medicine in cancer. Patients with systemic sclerosis (SSc), a rare, multiorgan autoimmune disorder, have a similarly poor prognosis due to interstitial lung disease (ILD). Here, our objectives were to explore computed tomography (CT)-based high-dimensional image analysis ("radiomics") for disease characterisation, risk stratification and relaying information on lung pathophysiology in SSc-ILD. METHODS: We investigated two independent, prospectively followed SSc-ILD cohorts (Zurich, derivation cohort, n=90; Oslo, validation cohort, n=66). For every subject, we defined 1355 robust radiomic features from standard-of-care CT images. We performed unsupervised clustering to identify and characterise imaging-based patient clusters. A clinically applicable prognostic quantitative radiomic risk score (qRISSc) for progression-free survival (PFS) was derived from radiomic profiles using supervised analysis. The biological basis of qRISSc was assessed in a cross-species approach by correlation with lung proteomic, histological and gene expression data derived from mice with bleomycin-induced lung fibrosis. RESULTS: Radiomic profiling identified two clinically and prognostically distinct SSc-ILD patient clusters. To evaluate the clinical applicability, we derived and externally validated a binary, quantitative radiomic risk score (qRISSc) composed of 26 features that accurately predicted PFS and significantly improved upon clinical risk stratification parameters in multivariable Cox regression analyses in the pooled cohorts. A high qRISSc score, which identifies patients at risk for progression, was reverse translatable from human to experimental ILD and correlated with fibrotic pathway activation. CONCLUSIONS: Radiomics-based risk stratification using routine CT images provides complementary phenotypic, clinical and prognostic information significantly impacting clinical decision making in SSc-ILD.

Head and neck radiotherapy on the MR linac: a multicenter planning challenge amongst MRIdian platform users.

PURPOSE: Purpose of this study is to evaluate plan quality on the MRIdian (Viewray Inc., Oakwood Village, OH, USA) system for head and neck cancer (HNC) through comparison of planning approaches of several centers. METHODS: A total of 14 planners using the MRIdian planning system participated in this treatment challenge, centrally organized by ViewRay, for one contoured case of oropharyngeal carcinoma with standard constraints for organs at risk (OAR). Homogeneity, conformity, sparing of OARs, and other parameters were evaluated according to The International Commission on Radiation Units and Measurements (ICRU) recommendations anonymously, and then compared between centers. Differences amongst centers were assessed by means of Wilcoxon test. Each plan had to fulfil hard constraints based on dose-volume histogram (DVH) parameters and delivery time. A plan quality metric (PQM) was evaluated. The PQM was defined as the sum of 16 submetrics characterizing different DVH goals. RESULTS: For most dose parameters the median score of all centers was higher than the threshold that results in an ideal score. Six participants achieved the maximum number of points for the OAR dose parameters, and none had an unacceptable performance on any of the metrics. Each planner was able to achieve all the requirements except for one which exceeded delivery time. The number of segments correlated to improved PQM and inversely correlated to brainstem D0.1cc and to Planning Target Volume1 (PTV) D0.1cc. Total planning experience inversely correlated to spinal canal dose. CONCLUSION: Magnetic Resonance Image (MRI) linac-based planning for HNC is already feasible with good quality. Generally, an increased number of segments and increasing planning experience are able to provide better results regarding planning quality without significantly prolonging overall treatment time.

Management of multiple brain metastases: a patterns of care survey within the German Society for Radiation Oncology.

PURPOSE: The treatment of brain metastases (BM) has changed considerably in recent years and in particular, the management of multiple BM is currently undergoing a paradigm shift and treatment may differ from current guidelines. This survey was designed to analyze the patterns of care in the management of multiple BM. METHODS: An online survey consisting of 36 questions was distributed to the members of the German Society for Radiation Oncology (DEGRO). RESULTS: In total, 193 physicians out of 111 institutions within the German Society for Radiation oncology responded to the survey. Prognostic scores for decision making were not used regularly. Whole brain radiotherapy approaches (WBRT) are the preferred treatment option for patients with multiple BM, although stereotactic radiotherapy treatments are chosen by one third depending on prognostic scores and overall number of BM. Routine hippocampal avoidance (HA) in WBRT is only used by a minority. In multiple BM of driver-mutated non-small cell lung cancer origin up to 30% favor sole TKI therapy as upfront treatment and would defer upfront radiotherapy. CONCLUSION: In multiple BM WBRT without hippocampal avoidance is still the preferred treatment modality of choice regardless of GPA and mutational status, while SRT is only used in patients with good prognosis. Evidence for both, SRS and hippocampal avoidance radiotherapy, is growing albeit the debate over the appropriate treatment in multiple BM is yet not fully clarified. Further prospective assessment of BM management-ideally as randomized trials-is required to align evolving concepts with the proper evidence and to update current guidelines.

Radiomic biomarkers for head and neck squamous cell carcinoma.

Tumor heterogeneity is a well-known prognostic factor in head and neck squamous cell carcinoma (HNSCC). A major limitation of tissue- and blood-derived tumor markers is the lack of spatial resolution to image tumor heterogeneity. Tissue markers derived from tumor biopsies usually represent only a small tumor subregion at a single timepoint and are therefore often not representative of the tumors' biology or the biological alterations during and after treatment. Similarly, liquid biopsies give an overall picture of the tumors' secreted factors but completely lack any spatial resolution. Radiomics has the potential to give complete three-dimensional information about the tumor. We conducted a comprehensive literature search to assess the correlation of radiomics to tumor biology and treatment outcome in HNSCC and to assess current limitations of the radiomic biomarkers. In total, 25 studies that explored the ability of radiomics to predict tumor biology and phenotype in HNSCC and 28 studies that explored radiomics to predict post-treatment events were identified. Out of these 53 studies, only three failed to show a significant correlation. The major technical challenges are currently artifacts due to metal implants, non-standardized contrast injection, and delineation uncertainties. All studies to date were retrospective and none of the above-mentioned radiomics signatures have been validated in an independent cohort using an independent software implementation, which shows that transferability due to the numerous technical challenges is currently a major limitation. However, radiomics is a very young field and these studies hopefully pave the way for clinical implementation of radiomics for HNSCC in the future.

Definition and quality requirements for stereotactic radiotherapy: consensus statement from the DEGRO/DGMP Working Group Stereotactic Radiotherapy and Radiosurgery.

Stereotactic radiotherapy with its forms of intracranial stereotactic radiosurgery (SRS), intracranial fractionated stereotactic radiotherapy (FSRT) and stereotactic body radiotherapy (SBRT) is today a guideline-recommended treatment for malignant or benign tumors as well as neurological or vascular functional disorders. The working groups for radiosurgery and stereotactic radiotherapy of the German Society for Radiation Oncology (DEGRO) and for physics and technology in stereotactic radiotherapy of the German Society for Medical Physics (DGMP) have established a consensus statement about the definition and minimal quality requirements for stereotactic radiotherapy to achieve best clinical outcome and treatment quality in the implementation into routine clinical practice.

CT radiomics and PET radiomics: ready for clinical implementation?

INTRODUCTION: Today, rapid technical and clinical developments result in an increasing number of treatment options for oncological diseases. Thus, decision support systems are needed to offer the right treatment to the right patient. Imaging biomarkers hold great promise in patient-individual treatment guidance. Routinely performed for diagnosis and staging, imaging datasets are expected to hold more information than used in the clinical practice. Radiomics describes the extraction of a large number of meaningful quantitative features from medical images, such as computed tomography (CT) and positron emission tomography (PET). Due to the non-invasive nature and ability to capture 3D image-based heterogeneity, radiomic features are potential surrogate markers of the cancer phenotype. Several radiomic studies are published per day, owing to encouraging results of many radiomics-based patient outcome models. Despite this comparably large number of studies, radiomics is mainly studied in proof of principle concept. Hence, a translation of radiomics from a hot topic research field into an essential clinical decision-making tool is lacking, but of high clinical interest. EVIDENCE ACQUISITION: Herein, we present a literature review addressing the clinical evidence of CT and PET radiomics. An extensive literature review was conducted in PubMed, including papers on robustness and clinical applications. EVIDENCE SYNTHESIS: We summarize image-modality related influences on the robustness of radiomic features and provide an overview of clinical evidence reported in the literature. Today, more evidence has been provided for CT imaging, however, PET imaging offers the promise of direct imaging of biological processes and functions. We provide a summary of future research directions, which needs to be addressed in order to successfully introduce radiomics into clinical medicine. In comparison to CT, more focus should be directed towards harmonization of PET acquisition and reconstruction protocols, which is important for transferable modelling. CONCLUSIONS: Both CT and PET radiomics are promising pre-treatment and intra-treatment biomarkers for outcome prediction. Most studies are performed in retrospective setting, however their validation in prospective data collections is ongoing.

The ideal couch tracking system-Requirements and evaluation of current systems.

INTRODUCTION: Intrafractional motion can cause substantial uncertainty in precision radiotherapy. Traditionally, the target volume is defined to be sufficiently large to cover the tumor in every position. With the robotic treatment couch, a real-time motion compensation can improve tumor coverage and organ at risk sparing. However, this approach poses additional requirements, which are systematically developed and which allow the ideal robotic couch to be specified. METHODS AND MATERIALS: Data of intrafractional tumor motion were collected and analyzed regarding motion range, frequency, speed, and acceleration. Using this data, ideal couch requirements were formulated. The four robotic couches Protura, Perfect Pitch, RoboCouch, and RPSbase were tested with respect to these requirements. RESULTS: The data collected resulted in maximum speed requirements of 60 mm/s in all directions and maximum accelerations of 80 mm/s2 in the longitudinal, 60 mm/s2 in the lateral, and 30 mm/s2 in the vertical direction. While the two robotic couches RoboCouch and RPSbase completely met the requirements, even these two showed a substantial residual motion (40% of input amplitude), arguably due to their time delays. CONCLUSION: The requirements for the motion compensation by an ideal couch are formulated and found to be feasible for currently available robotic couches. However, the performance these couches can be improved further regarding the position control if the demanded speed and acceleration are taken into account as well.

Influence of inter-observer delineation variability on radiomics stability in different tumor sites.

BACKGROUND: Radiomics is a promising methodology for quantitative analysis and description of radiological images using advanced mathematics and statistics. Tumor delineation, which is still often done manually, is an essential step in radiomics, however, inter-observer variability is a well-known uncertainty in radiation oncology. This study investigated the impact of inter-observer variability (IOV) in manual tumor delineation on the reliability of radiomic features (RF). METHODS: Three different tumor types (head and neck squamous cell carcinoma (HNSCC), malignant pleural mesothelioma (MPM) and non-small cell lung cancer (NSCLC)) were included. For each site, eleven individual tumors were contoured on CT scans by three experienced radiation oncologists. Dice coefficients (DC) were calculated for quantification of delineation variability. RF were calculated with an in-house developed software implementation, which comprises 1404 features: shape (n = 18), histogram (n = 17), texture (n = 137) and wavelet (n = 1232). The IOV of RF was studied using the intraclass correlation coefficient (ICC). An ICC >0.8 indicates a good reproducibility. For the stable RF, an average linkage hierarchical clustering was performed to identify classes of uncorrelated features. RESULTS: Median DC was high for NSCLC (0.86, range 0.57-0.90) and HNSCC (0.72, 0.21-0.89), whereas it was low for MPM (0.26, 0-0.9) indicating substantial IOV. Stability rate of RF correlated with DC and depended on tumor site, showing a high stability in NSCLC (90% of total parameters), acceptable stability in HNSCC (59% of total parameters) and low stability in MPM (36% of total parameters). Shape features showed the weakest stability across all tumor types. Hierarchical clustering revealed 14 groups of correlated and stable features for NSCLC and 6 groups for both HNSCC and MPM. CONCLUSION: Inter-observer delineation variability has a relevant influence on radiomics analysis and is strongly influenced by tumor type. This leads to a reduced number of suitable imaging features.

Comparison of PET and CT radiomics for prediction of local tumor control in head and neck squamous cell carcinoma.

PURPOSE: An association between radiomic features extracted from CT and local tumor control in the head and neck squamous cell carcinoma (HNSCC) has been shown. This study investigated the value of pretreatment functional imaging (18F-FDG PET) radiomics for modeling of local tumor control. MATERIAL AND METHODS: Data from HNSCC patients (n = 121) treated with definitive radiochemotherapy were used for model training. In total, 569 radiomic features were extracted from both contrast-enhanced CT and 18F-FDG PET images in the primary tumor region. CT, PET and combined PET/CT radiomic models to assess local tumor control were trained separately. Five feature selection and three classification methods were implemented. The performance of the models was quantified using concordance index (CI) in 5-fold cross validation in the training cohort. The best models, per image modality, were compared and verified in the independent validation cohort (n = 51). The difference in CI was investigated using bootstrapping. Additionally, the observed and radiomics-based estimated probabilities of local tumor control were compared between two risk groups. RESULTS: The feature selection using principal component analysis and the classification based on the multivariabale Cox regression with backward selection of the variables resulted in the best models for all image modalities (CICT = 0.72, CIPET = 0.74, CIPET/CT = 0.77). Tumors more homogenous in CT density (decreased GLSZMsize_zone_entropy) and with a focused region of high FDG uptake (higher GLSZMSZLGE) indicated better prognosis. No significant difference in the performance of the models in the validation cohort was observed (CICT = 0.73, CIPET = 0.71, CIPET/CT = 0.73). However, the CT radiomics-based model overestimated the probability of tumor control in the poor prognostic group (predicted = 68%, observed = 56%). CONCLUSIONS: Both CT and PET radiomics showed equally good discriminative power for local tumor control modeling in HNSCC. However, CT-based predictions overestimated the local control rate in the poor prognostic validation cohort, and thus, we recommend to base the local control modeling on the 18F-FDG PET.

The Future of MR-Guided Radiation Therapy.

Magnetic resonance image guided radiation therapy (MRIgRT) is a relatively new technology that has already shown outcomes benefits but that has not yet reached its clinical potential. The improved soft-tissue contrast provided with MR, coupled with the immediacy of image acquisition with respect to the treatment, enables expansion of on-table adaptive protocols, currently at a cost of increased treatment complexity, use of human resources, and longer treatment slot times, which translate to decreased throughput. Many approaches are being investigated to meet these challenges, including the development of artificial intelligence (AI) algorithms to accelerate and automate much of the workflow and improved technology that parallelizes workflow tasks, as well as improvements in image acquisition speed and quality. This article summarizes limitations of current available integrated MRIgRT systems and gives an outlook about scientific developments to further expand the use of MRIgRT.

Automatized self-supervised learning for skin lesion screening.

Melanoma, the deadliest form of skin cancer, has seen a steady increase in incidence rates worldwide, posing a significant challenge to dermatologists. Early detection is crucial for improving patient survival rates. However, performing total body screening (TBS), i.e., identifying suspicious lesions or ugly ducklings (UDs) by visual inspection, can be challenging and often requires sound expertise in pigmented lesions. To assist users of varying expertise levels, an artificial intelligence (AI) decision support tool was developed. Our solution identifies and characterizes UDs from real-world wide-field patient images. It employs a state-of-the-art object detection algorithm to locate and isolate all skin lesions present in a patient's total body images. These lesions are then sorted based on their level of suspiciousness using a self-supervised AI approach, tailored to the specific context of the patient under examination. A clinical validation study was conducted to evaluate the tool's performance. The results demonstrated an average sensitivity of 95% for the top-10 AI-identified UDs on skin lesions selected by the majority of experts in pigmented skin lesions. The study also found that the tool increased dermatologists' confidence when formulating a diagnosis, and the average majority agreement with the top-10 AI-identified UDs reached 100% when assisted by our tool. With the development of this AI-based decision support tool, we aim to address the shortage of specialists, enable faster consultation times for patients, and demonstrate the impact and usability of AI-assisted screening. Future developments will include expanding the dataset to include histologically confirmed melanoma and validating the tool for additional body regions.

An in-silico planning study of stereotactic body radiation therapy for polymetastatic patients with more than ten extra-cranial lesions.

Background and purpose: Limited data is available about the feasibility of stereotactic body radiation therapy (SBRT) for treating more than five extra-cranial metastases, and almost no data for treating more than ten. The aim of this study was to investigate the feasibility of SBRT in this polymetatstatic setting. Materials and methods: Consecutive metastatic melanoma patients with more than ten extra-cranial metastases and a maximum lesion diameter below 11 cm were selected from a single-center prospective registry for this in-silico planning study. For each patient, SBRT plans were generated to treat all metastases with a prescribed dose of 5x7Gy, and dose-limiting organs (OARs) were analyzed. A cell-kill based inverse planning approach was used to automatically determine the maximum deliverable dose to each lesion individually, while respecting all OARs constraints. Results: A total of 23 polymetastatic patients with a medium of 17 metastases (range, 11-51) per patient were selected. SBRT plans with sufficient target coverage and respected OARs dose constraints were achieved in 16 out of 23 patients. In the remaining seven patients, the lungs V5Gy < 80 % and the liver D700 cm3 < 15Gy were most frequently the dose-limiting constraints. The cell-kill based planning approach allowed optimizing the dose administration depending on metastases total volume and location. Conclusion: This retrospective planning study shows the feasibility of definitive SBRT for 70% of polymetastatic patients with more than ten extra-cranial lesions and proposes the cell-killing planning approach as an approach to individualize treatment planning in polymetastatic patients'.

Magnetic resonance imaging radiomic features stability in brain metastases: Impact of image preprocessing, image-, and feature-level harmonization.

Background and purpose: Magnetic resonance imaging (MRI) scans are highly sensitive to acquisition and reconstruction parameters which affect feature stability and model generalizability in radiomic research. This work aims to investigate the effect of image pre-processing and harmonization methods on the stability of brain MRI radiomic features and the prediction performance of radiomic models in patients with brain metastases (BMs). Materials and methods: Two T1 contrast enhanced brain MRI data-sets were used in this study. The first contained 25 BMs patients with scans at two different time points and was used for features stability analysis. The effect of gray level discretization (GLD), intensity normalization (Z-score, Nyul, WhiteStripe, and in house-developed method named N-Peaks), and ComBat harmonization on features stability was investigated and features with intraclass correlation coefficient >0.8 were considered as stable. The second data-set containing 64 BMs patients was used for a classification task to investigate the informativeness of stable features and the effects of harmonization methods on radiomic model performance. Results: Applying fixed bin number (FBN) GLD, resulted in higher number of stable features compare to fixed bin size (FBS) discretization (10 ± 5.5 % higher). `Harmonization in feature domain improved the stability for non-normalized and normalized images with Z-score and WhiteStripe methods. For the classification task, keeping the stable features resulted in good performance only for normalized images with N-Peaks along with FBS discretization. Conclusions: To develop a robust MRI based radiomic model we recommend using an intensity normalization method based on a reference tissue (e.g N-Peaks) and then using FBS discretization.

Stereotactic body radiotherapy for oligoprogression with or without switch of systemic therapy.

Background: Oligoprogression is defined as cancer progression of a limited number of metastases under active systemic therapy. The role of metastasis-directed therapy, using stereotactic body radiotherapy (SBRT), is controversial as is the continuation versus switch of systemic therapy. We report outcomes of oligoprogressive patients after SBRT, and compare those patients that continued or switched their current line of systemic therapy. Material/Methods: We included patients who developed up to 5 progressive extracranial metastases under systemic therapy for any solid organ malignancy and were treated with SBRT to all lesions at our institution between 01/2014 and 12/2019. Overall survival (OS) and progression-free survival (PFS) were analyzed using the Kaplan-Meier method, and the interval to the next systemic therapy line determined using cumulative incidence functions. Multivariable Cox regression models were used to analyze the influence of baseline and post-progression variables on OS, PFS and survival with the next systemic therapy after SBRT. Results: Among 135 patients with oligoprogressive disease of which the most common primary tumor was lung cancer (n = 46, 34.1 %), 96 continued their current line of systemic therapy after oligoprogression. Among 39 who switched systemic therapy, 28 (71.8 %) paused or discontinued, while 11 (28.2 %) immediately started another systemic treatment. After a median follow-up of 27.2 months, patients that switched and those who continued systemic therapy after oligoprogression had comparable median OS (32.1 vs. 38.2 months, p = 0.47) and PFS (4.3 vs. 3.4 months, p = 0.6). The intervals to the next systemic therapy line were comparable between both cohorts (p = 0.6). An ECOG performance status of 2 and immediately starting a new systemic therapy after oligoprogression were associated with a poorer survival without next systemic therapy, while the de-novo OMD state was associated with better survival without next systemic therapy compared to the induced state. Conclusion: Oncological outcomes of patients that continued or switched systemic therapy after SBRT for oligoprogression were comparable, potentially indicating that further lines of treatment may be safely delayed in selected cases.

Multicenter privacy-preserving model training for deep learning brain metastases autosegmentation.

OBJECTIVES: This work aims to explore the impact of multicenter data heterogeneity on deep learning brain metastases (BM) autosegmentation performance, and assess the efficacy of an incremental transfer learning technique, namely learning without forgetting (LWF), to improve model generalizability without sharing raw data. MATERIALS AND METHODS: A total of six BM datasets from University Hospital Erlangen (UKER), University Hospital Zurich (USZ), Stanford, UCSF, New York University (NYU), and BraTS Challenge 2023 were used. First, the performance of the DeepMedic network for BM autosegmentation was established for exclusive single-center training and mixed multicenter training, respectively. Subsequently privacy-preserving bilateral collaboration was evaluated, where a pretrained model is shared to another center for further training using transfer learning (TL) either with or without LWF. RESULTS: For single-center training, average F1 scores of BM detection range from 0.625 (NYU) to 0.876 (UKER) on respective single-center test data. Mixed multicenter training notably improves F1 scores at Stanford and NYU, with negligible improvement at other centers. When the UKER pretrained model is applied to USZ, LWF achieves a higher average F1 score (0.839) than naive TL (0.570) and single-center training (0.688) on combined UKER and USZ test data. Naive TL improves sensitivity and contouring accuracy, but compromises precision. Conversely, LWF demonstrates commendable sensitivity, precision and contouring accuracy. When applied to Stanford, similar performance was observed. CONCLUSION: Data heterogeneity (e.g., variations in metastases density, spatial distribution, and image spatial resolution across centers) results in varying performance in BM autosegmentation, posing challenges to model generalizability. LWF is a promising approach to peer-to-peer privacy-preserving model training.

Validation of echo planar imaging based diffusion-weighted magnetic resonance imaging on a 0.35 T MR-Linac.

Background and Purpose: The feasibility of acquiring diffusion-weighted imaging (DWI) images on an MR-Linac for quantitative response assessment during radiotherapy was explored. DWI data obtained with a Spin Echo Echo Planar Imaging sequence adapted for a 0.35 T MR-Linac were examined and compared with DWI data from a conventional 3 T scanner. Materials and Methods: Apparent diffusion coefficient (ADC) measurements and a distortion correction technique were investigated using DWI-calibrated phantoms and in the brains of seven volunteers. All DWI utilized two phase-encoding directions for distortion correction and off-resonance field estimation. ADC maps in the brain were analyzed for automatically segmented normal tissues. Results: Phantom ADC measurements on the MR-Linac were within a 3 % margin of those recorded by the 3 T scanner. The maximum distortion observed in the phantom was 2.0 mm prior to correction and 1.1 mm post-correction on the MR-Linac, compared to 6.0 mm before correction and 3.6 mm after correction at 3 T. In vivo, the average ADC values for gray and white matter exhibited variations of 14 % and 4 %, respectively, for different selections of b-values on the MR-Linac. Distortions in brain images before correction, estimated through the off-resonance field, reached 2.7 mm on the MR-Linac and 12 mm at 3 T. Conclusion: Accurate ADC measurements are achievable on a 0.35 T MR-Linac, both in phantom and in vivo. The selection of b-values significantly influences ADC values in vivo. DWI on the MR-Linac demonstrated lower distortion levels, with a maximum distortion reduced to 1.1 mm after correction.