Search

Background: MR image classification in datasets collected from multiple sources is complicated by inconsistent and missing DICOM metadata. Therefore, we aimed to establish a method for the efficient automatic classification of MR brain sequences. Methods: Deep convolutional neural networks (DCNN) were trained as one-vs-all classifiers to differentiate between six classes: T1 weighted (w), contrast-enhanced T1w, T2w, T2w-FLAIR, ADC, and SWI. Each classifier yields a probability, allowing threshold-based and relative probability assignment while excluding images with low probability (label: unknown, open-set recognition problem). Data from three high-grade glioma (HGG) cohorts was assessed; C1 (320 patients, 20,101 MRI images) was used for training, while C2 (197, 11,333) and C3 (256, 3522) were for testing. Two raters manually checked images through an interactive labeling tool. Finally, MR-Class’ added value was evaluated via radiomics model performance for progression-free survival (PFS) prediction in C2, utilizing the concordance index (C-I). Results: Approximately 10% of annotation errors were observed in each cohort between the DICOM series descriptions and the derived labels. MR-Class accuracy was 96.7% [95% Cl: 95.8, 97.3] for C2 and 94.4% [93.6, 96.1] for C3. A total of 620 images were misclassified; manual assessment of those frequently showed motion artifacts or alterations of anatomy by large tumors. Implementation of MR-Class increased the PFS model C-I by 14.6% on average, compared to a model trained without MR-Class. Conclusions: We provide a DCNN-based method for the sequence classification of brain MR images and demonstrate its usability in two independent HGG datasets.

Purpose: This study investigates the impact of different intensity normalization (IN) methods on the overall survival (OS) radiomics models’ performance of MR sequences in primary (pHGG) and recurrent high-grade glioma (rHGG). Methods: MR scans acquired before radiotherapy were retrieved from two independent cohorts (rHGG C1: 197, pHGG C2: 141) from multiple scanners (15, 14). The sequences are T1 weighted (w), contrast-enhanced T1w (T1wce), T2w, and T2w-FLAIR. Sequence-specific significant features (SF) associated with OS, extracted from the tumour volume, were derived after applying 15 different IN methods. Survival analyses were conducted using Cox proportional hazard (CPH) and Poisson regression (POI) models. A ranking score was assigned based on the 10-fold cross-validated (CV) concordance index (C-I), mean square error (MSE), and the Akaike information criterion (AICs), to evaluate the methods’ performance. Results: Scatter plots of the 10-CV C-I and MSE against the AIC showed an impact on the survival predictions between the IN methods and MR sequences (C1/C2 C-I range: 0.62-0.71/0.61-0.72, MSE range: 0.20-0.42/0.13-0.22). White stripe showed stable results for T1wce (C1/C2 C-I: 0.71/0.65, MSE: 0.21/0.14). Combat (0.68/0.62, 0.22/0.15) and histogram matching (HM, 0.67/0.64, 0.22/0.15) showed consistent prediction results for T2w models. They were also the top-performing methods for T1w in C2 (Combat: 0.67, 0.13; HM: 0.67, 0.13), however, only HM achieved high predictions in C1 (0.66, 0.22). After eliminating IN impacted SF using Spearman’s rank-order correlation coefficient, a mean decrease in the C-I and MSE of 0.05 and 0.03 was observed in all four sequences. Conclusion: The IN method impacted the predictive power of survival models. Thus, performance is sequence-dependent.

Background: To report the final results of a prospective, one-armed, single-center phase I/II trial (NCT01566123). Methods: Between 2007 and 2017, 37 patients with primary or recurrent (N = 6) retroperitoneal sarcomas were enrolled. Treatment included preoperative IMRT of 45–50 Gy with a simultaneous integrated boost of 50–56 Gy, surgery and IORT. The primary endpoint was local control (LC) at 5 years. The most common histology was dedifferentiated liposarcoma (51%), followed by leiomyosarcoma (24%) and well-differentiated liposarcoma (14%). The majority of lesions were high-grade (FNCLCC G1: 30%, G2: 38%, G3: 27%, two missing). Five patients were excluded from LC analysis per protocol. Results: The minimum follow-up of the survivors was 62 months (median: 109; maximum 162). IORT was performed for 27 patients. Thirty-five patients underwent gross total resection; the pathological resection margin was mostly R+ (80%) and, less often, R0 (20%). We observed 10 local recurrences. The 5-year LC of the whole cohort was 59.6%. Eleven patients received a dose > 50 Gy plus IORT boost; LC was 64.8%; the difference, however, was not significant (p = 0.588). Of 37 patients, 15 were alive and 22 deceased at the time of final analysis. The 5-year OS was 59.5% (68.8% per protocol). Conclusions: The primary endpoint of a 5-year LC of 70% was not met. This might be explained by the inclusion of recurrent disease and the high rate of G3 lesions and leiomyosarcoma, which have been shown to profit less from radiotherapy. Stratification by grading and histology should be considered for future studies.

BackgroundSelective uptake of (18)F-fluoro-ethyl-tyrosine (18F-FET) is used in high-grade glioma (HGG) to assess tumor metabolic activity via positron emission tomography (PET). We aim to investigate its value for target volume definition, as a prognosticator, and associations with whole-blood transcriptome liquid biopsy (WBT lbx) for which we recently reported feasibility to mirror tumor characteristics and response to particle irradiation in recurrent HGG (rHGG).Methods18F-FET-PET data from n = 43 patients with primary glioblastoma (pGBM) and n = 33 patients with rHGG were assessed. pGBM patients were irradiated with photons and sequential proton/carbon boost, and rHGG patients were treated with carbon re-irradiation (CIR). WBT (Illumina HumanHT-12 Expression BeadChips) lbx was available for n = 9 patients from the rHGG cohort. PET isocontours (40%–70% SUVmax, 10% steps) and MRI-based treatment volumes (MRIvol) were compared using the conformity index (CI) (pGBM, n = 16; rHGG, n = 27). Associations with WBT lbx data were tested on gene expression level and inferred pathways activity scores (PROGENy) and from transcriptome estimated cell fractions (CIBERSORT, xCell).ResultsIn pGBM, median SUVmax was higher in PET acquired pre-radiotherapy (4.1, range (R) 1.5–7.8; n = 20) vs. during radiotherapy (3.3, R 1.5–5.7, n = 23; p = 0.03) and in non-resected (4.7, R 2.9–7.9; n = 11) vs. resected tumors (3.3, R 1.5–7.8, n = 32; p = 0.01). In rHGG, a trend toward higher SUVmax values in grade IV tumors was observed (p = 0.13). Median MRIvol was 32.34 (R 8.75–108.77) cm3 in pGBM (n = 16) and 20.77 (R 0.63–128.44) cm3 in rHGG patients (n = 27). The highest median CI was observed for 40% (pGBM, 0.31) and 50% (rHGG, 0.43, all tumors) isodose, with 70% (40%) isodose in grade III (IV) rHGG tumors (median CI, 0.38 and 0.49). High SUVmax was linked to shorter survival in pGBM (>3.3, p = 0.001, OR 6.0 [2.1–17.4]) and rHGG (>2.8, p = 0.02, OR 4.1 [1.2–13.9]). SUVmax showed associations with inferred monocyte fractions, hypoxia, and TGFbeta pathway activity and links to immune checkpoint gene expression from WBT lbx.ConclusionThe benefits of 18F-FET-PET imaging on gross tumor volume (GTV) definition for particle radiotherapy warrant further evaluation. SUVmax might assist in prognostic stratification of HGG patients for particle radiotherapy, highlights heterogeneity in rHGG, and is positively associated with unfavorable signatures in peripheral whole-blood transcriptomes.

Purpose: To develop a model to accurately segment mouse lungs with varying levels of fibrosis and investigate its applicability to mouse images with different resolutions.Materials and Methods: In this experimental retrospective study, a U-Net was trained to automatically segment lungs on mouse CT images. The model was trained (n = 1200), validated (n = 300), and tested (n = 154) on longitudinally acquired and semiautomatically segmented CT images, which included both healthy and irradiated mice (group A). A second independent group of 237 mice (group B) was used for external testing. The Dice score coefficient (DSC) and Hausdorff distance (HD) were used as metrics to quantify segmentation accuracy. Transfer learning was applied to adapt the model to high-spatial-resolution mouse micro-CT segmentation (n = 20; group C [n = 16 for training and n = 4 for testing]).Results: The trained model yielded a high median DSC in both test datasets: 0.984 (interquartile range [IQR], 0.977-0.988) in group A and 0.966 (IQR, 0.955-0.972) in group B. The median HD in both test datasets was 0.47 mm (IQR, 0-0.51 mm [group A]) and 0.31 mm (IQR, 0.30-0.32 mm [group B]). Spatially resolved quantification of differences toward reference masks revealed two hot spots close to the air-tissue interfaces, which are particularly prone to deviation. Finally, for the higher-resolution mouse CT images, the median DSC was 0.905 (IQR, 0.902-0.929) and the median 95th percentile of the HD was 0.33 mm (IQR, 2.61-2.78 mm).Conclusion: The developed deep learning-based method for mouse lung segmentation performed well independently of disease state (healthy, fibrotic, emphysematous lungs) and CT resolution.Keywords: Deep Learning, Lung Fibrosis, Radiation Therapy, Segmentation, Animal Studies, CT, Thorax, Lung Supplemental material is available for this article. Published under a CC BY 4.0 license.

Background To investigate the role of combined ion-beam radiotherapy (CIBRT) with protons and carbon ions in a multimodal treatment strategy of inoperable osteosarcoma; final analysis of a one-armed, single center phase I/II trial. Methods Between August 2011 until September 2018, 20 patients with primary (N = 18), metastatic (N = 3), or recurrent (N = 2) inoperable pelvic (70%) or craniofacial (30%) osteosarcoma were treated with protons up to 54 Gy (RBE) and a carbon ion boost of 18 Gy (RBE) and followed until May 2019. A Fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) was performed before CIBRT in search for a prognostic factor. The primary endpoint was toxicity. Secondary endpoints included treatment response, global, local and distant progression free survival (PFS, LPFS and DPFS) and overall (OS), among others. Results The median age was 20; all patients finished treatment per protocol. LPFS, DPFS, PFS and OS were 73%, 74%, 60% and 75% after one year and 55%, 65% 65.3%, 45% and 68% after two years, respectively. The median clinical target volume (CTV) was 1042 cc and 415 cc for the primary and boost plan, respectively. Craniofacial localization, lower uptake of FDG in PET/CT and boost plan CTV ≤ median were associated with improved overall survival (p = 0.039, p = 0.016 and p = 0.0043, respectively). No acute toxicities > grade III were observed. We observed one case of secondary acute myeloid leukemia (AML) seven months after CIBRT for recurrent disease and one case of hearing loss. Conclusion CIBRT shows a favorable toxicity profile and promising results particularly for patients with inoperable craniofacial osteosarcoma.

2041 Background: Efficacy of PD-L1 immune checkpoint inhibitor therapy in Glioblastoma multiforme (GBM) is limited and the prognostic value of PD-L1 in GBM is an active field of research. We therefore sought to identify a MR based surrogate for PD-L1 expression in GBM. Methods: T1 post contrast images (T1ce) acquired immediately before surgery of 121 subjects with primary GBM (RTK I, II and mesenchymal subtype, as determined from Illumina Human Methylation array data) were analyzed. Following standard pre-processing (bias filed correction, brain extraction), 1150 radiomics features were calculated from gross tumor volumes (GTV). The cohort was then divided into training/validation (70%/30%). Cross-validation and model-selection were applied to identify features associated with PD-L1-M expression (estimated from methylation data and highly correlated with PD-L1 RNA-sequencing based measure, as recently reported). Features were used to identify two groups of tumors differing in PD-L1-M expression (PD-L1-R high and low), for which a logistic regression model was trained. Overall survival was assessed between PD-L1-R high/low. Results: PD-L1-R high and low groups showed significant differences in PD-L1-M values (training: p=0.002, validation: p=0.04, full cohort: p