Inter-scanner super-resolution of 3D cine MRI using a transfer-learning network for MRgRT.

Objective. Deep-learning networks for super-resolution (SR) reconstruction enhance the spatial-resolution of 3D magnetic resonance imaging (MRI) for MR-guided radiotherapy (MRgRT). However, variations between MRI scanners and patients impact the quality of SR for real-time 3D low-resolution (LR) cine MRI. In this study, we present a personalized super-resolution (psSR) network that incorporates transfer-learning to overcome the challenges in inter-scanner SR of 3D cine MRI.Approach: Development of the proposed psSR network comprises two-stages: (1) a cohort-specific SR (csSR) network using clinical patient datasets, and (2) a psSR network using transfer-learning to target datasets. The csSR network was developed by training on breath-hold and respiratory-gated high-resolution (HR) 3D MRIs and their k-space down-sampled LR MRIs from 53 thoracoabdominal patients scanned at 1.5 T. The psSR network was developed through transfer-learning to retrain the csSR network using a single breath-hold HR MRI and a corresponding 3D cine MRI from 5 healthy volunteers scanned at 0.55 T. Image quality was evaluated using the peak-signal-noise-ratio (PSNR) and the structure-similarity-index-measure (SSIM). The clinical feasibility was assessed by liver contouring on the psSR MRI using an auto-segmentation network and quantified using the dice-similarity-coefficient (DSC).Results. Mean PSNR and SSIM values of psSR MRIs were increased by 57.2% (13.8-21.7) and 94.7% (0.38-0.74) compared to cine MRIs, with the reference 0.55 T breath-hold HR MRI. In the contour evaluation, DSC was increased by 15% (0.79-0.91). Average time consumed for transfer-learning was 90 s, psSR was 4.51 ms per volume, and auto-segmentation was 210 ms, respectively.Significance. The proposed psSR reconstruction substantially increased image and segmentation quality of cine MRI in an average of 215 ms across the scanners and patients with less than 2 min of prerequisite transfer-learning. This approach would be effective in overcoming cohort- and scanner-dependency of deep-learning for MRgRT.

Feasibility of surface-guidance combined with CBCT for intra-fractional breath-hold motion management during Ethos RT.

PURPOSE: High-quality CBCT and AI-enhanced adaptive planning techniques allow CBCT-guided stereotactic adaptive radiotherapy (CT-STAR) to account for inter-fractional anatomic changes. Studies of intra-fractional respiratory motion management with a surface imaging solution for CT-STAR have not been fully conducted. We investigated intra-fractional motion management in breath-hold Ethos-based CT-STAR and CT-SBRT (stereotactic body non-adaptive radiotherapy) using optical surface imaging combined with onboard CBCTs. METHODS: Ten cancer patients with mobile lower lung or upper abdominal malignancies participated in an IRB-approved clinical trial (Phase I) of optical surface image-guided Ethos CT-STAR/SBRT. In the clinical trial, a pre-configured gating window (± 2 mm in AP direction) on optical surface imaging was used for manually triggering intra-fractional CBCT acquisition and treatment beam irradiation during breath-hold (seven patients for the end of exhalation and three patients for the end of inhalation). Two inter-fractional CBCTs at the ends of exhalation and inhalation in each fraction were acquired to verify the primary direction and range of the tumor/imaging-surrogate (donut-shaped fiducial) motion. Intra-fractional CBCTs were used to quantify the residual motion of the tumor/imaging-surrogate within the pre-configured breath-hold window in the AP direction. Fifty fractions of Ethos RT were delivered under surface image-guidance: Thirty-two fractions with CT-STAR (adaptive RT) and 18 fractions with CT-SBRT (non-adaptive RT). The residual motion of the tumor was quantified by determining variations in the tumor centroid position. The dosimetric impact on target coverage was calculated based on the residual motion. RESULTS: We used 46 fractions for the analysis of intra-fractional residual motion and 43 fractions for the inter-fractional motion analysis due to study constraints. Using the image registration method, 43 pairs of inter-fractional CBCTs and 100 intra-fractional CBCTs attached to dose maps were analyzed. In the motion range study (image registration) from the inter-fractional CBCTs, the primary motion (mean ± std) was 16.6 ± 9.2 mm in the SI direction (magnitude: 26.4 ± 11.3 mm) for the tumors and 15.5 ± 7.3 mm in the AP direction (magnitude: 20.4 ± 7.0 mm) for the imaging-surrogate, respectively. The residual motion of the tumor (image registration) from intra-fractional breath-hold CBCTs was 2.2 ± 2.0 mm for SI, 1.4 ± 1.4 mm for RL, and 1.3 ± 1.3 mm for AP directions (magnitude: 3.5 ± 2.1 mm). The ratio of the actual dose coverage to 99%, 90%, and 50% of the target volume decreased by 0.95 ± 0.11, 0.96 ± 0.10, 0.99 ± 0.05, respectively. The mean percentage of the target volume covered by the prescribed dose decreased by 2.8 ± 4.4%. CONCLUSION: We demonstrated the intra-fractional motion-managed treatment strategy in breath-hold Ethos CT-STAR/SBRT using optical surface imaging and CBCT. While the controlled residual tumor motion measured at 3.5 mm exceeded the predetermined setup value of 2 mm, it is important to note that this motion still fell within the clinically acceptable range defined by the PTV margin of 5 mm. Nonetheless, additional caution is needed with intra-fractional motion management in breath-hold Ethos CT-STAR/SBRT using optical surface imaging and CBCT.

Expression of histone deacetylase (HDAC) family members in bortezomib-refractory multiple myeloma and modulation by panobinostat.

AIM: Multiple myeloma (MM) is a hematological malignancy of antibody-producing mature B cells or plasma cells. The proteasome inhibitor, bortezomib, was the first-in-class compound to be FDA approved for MM and is frequently utilized in induction therapy. However, bortezomib refractory disease is a major clinical concern, and the efficacy of the pan-histone deacetylase inhibitor (HDACi), panobinostat, in bortezomib refractory disease indicates that HDAC targeting is a viable strategy. Here, we utilized isogenic bortezomib resistant models to profile HDAC expression and define baseline and HDACi-induced expression patterns of individual HDAC family members in sensitive vs. resistant cells to better understanding the potential for targeting these enzymes. METHODS: Gene expression of HDAC family members in two sets of isogenic bortezomib sensitive or resistant myeloma cell lines was examined. These cell lines were subsequently treated with HDAC inhibitors: panobinostat or vorinostat, and HDAC expression was evaluated. CRISPR/Cas9 knockdown and pharmacological inhibition of specific HDAC family members were conducted. RESULTS: Interestingly, HDAC6 and HDAC7 were significantly upregulated and downregulated, respectively, in bortezomib-resistant cells. Panobinostat was effective at inducing cell death in these lines and modulated HDAC expression in cell lines and patient samples. Knockdown of HDAC7 inhibited cell growth while pharmacologically inhibiting HDAC6 augmented cell death by panobinostat. CONCLUSION: Our data revealed heterogeneous expression of individual HDACs in bortezomib sensitive vs. resistant isogenic cell lines and patient samples treated with panobinostat. Cumulatively our findings highlight distinct roles for HDAC6 and HDAC7 in regulating cell death in the context of bortezomib resistance.

Novel Autosegmentation Spatial Similarity Metrics Capture the Time Required to Correct Segmentations Better Than Traditional Metrics in a Thoracic Cavity Segmentation Workflow.

Automated segmentation templates can save clinicians time compared to de novo segmentation but may still take substantial time to review and correct. It has not been thoroughly investigated which automated segmentation-corrected segmentation similarity metrics best predict clinician correction time. Bilateral thoracic cavity volumes in 329 CT scans were segmented by a UNet-inspired deep learning segmentation tool and subsequently corrected by a fourth-year medical student. Eight spatial similarity metrics were calculated between the automated and corrected segmentations and associated with correction times using Spearman's rank correlation coefficients. Nine clinical variables were also associated with metrics and correction times using Spearman's rank correlation coefficients or Mann-Whitney U tests. The added path length, false negative path length, and surface Dice similarity coefficient correlated better with correction time than traditional metrics, including the popular volumetric Dice similarity coefficient (respectively ρ = 0.69, ρ = 0.65, ρ = - 0.48 versus ρ = - 0.25; correlation p values < 0.001). Clinical variables poorly represented in the autosegmentation tool's training data were often associated with decreased accuracy but not necessarily with prolonged correction time. Metrics used to develop and evaluate autosegmentation tools should correlate with clinical time saved. To our knowledge, this is only the second investigation of which metrics correlate with time saved. Validation of our findings is indicated in other anatomic sites and clinical workflows. Novel spatial similarity metrics may be preferable to traditional metrics for developing and evaluating autosegmentation tools that are intended to save clinicians time.

Segmenting Thoracic Cavities with Neoplastic Lesions: A Head-to-head Benchmark with Fully Convolutional Neural Networks.

Automatic segmentation of thoracic cavity structures in computer tomography (CT) is a key step for applications ranging from radiotherapy planning to imaging biomarker discovery with radiomics approaches. State-of-the-art segmentation can be provided by fully convolutional neural networks such as the U-Net or V-Net. However, there is a very limited body of work on a comparative analysis of the performance of these architectures for chest CTs with significant neoplastic disease. In this work, we compared four different types of fully convolutional architectures using the same pre-processing and post-processing pipelines. These methods were evaluated using a dataset of CT images and thoracic cavity segmentations from 402 cancer patients. We found that these methods achieved very high segmentation performance by benchmarks of three evaluation criteria, i.e. Dice coefficient, average symmetric surface distance and 95% Hausdorff distance. Overall, the two-stage 3D U-Net model performed slightly better than other models, with Dice coefficients for left and right lung reaching 0.947 and 0.952, respectively. However, 3D U-Net model achieved the best performance under the evaluation of HD95 for right lung and ASSD for both left and right lung. These results demonstrate that the current state-of-art deep learning models can work very well for segmenting not only healthy lungs but also the lung containing different stages of cancerous lesions. The comprehensive types of lung masks from these evaluated methods enabled the creation of imaging-based biomarkers representing both healthy lung parenchyma and neoplastic lesions, allowing us to utilize these segmented areas for the downstream analysis, e.g. treatment planning, prognosis and survival prediction.

PleThora: Pleural effusion and thoracic cavity segmentations in diseased lungs for benchmarking chest CT processing pipelines.

This manuscript describes a dataset of thoracic cavity segmentations and discrete pleural effusion segmentations we have annotated on 402 computed tomography (CT) scans acquired from patients with non-small cell lung cancer. The segmentation of these anatomic regions precedes fundamental tasks in image analysis pipelines such as lung structure segmentation, lesion detection, and radiomics feature extraction. Bilateral thoracic cavity volumes and pleural effusion volumes were manually segmented on CT scans acquired from The Cancer Imaging Archive "NSCLC Radiomics" data collection. Four hundred and two thoracic segmentations were first generated automatically by a U-Net based algorithm trained on chest CTs without cancer, manually corrected by a medical student to include the complete thoracic cavity (normal, pathologic, and atelectatic lung parenchyma, lung hilum, pleural effusion, fibrosis, nodules, tumor, and other anatomic anomalies), and revised by a radiation oncologist or a radiologist. Seventy-eight pleural effusions were manually segmented by a medical student and revised by a radiologist or radiation oncologist. Interobserver agreement between the radiation oncologist and radiologist corrections was acceptable. All expert-vetted segmentations are publicly available in NIfTI format through The Cancer Imaging Archive at https://doi.org/10.7937/tcia.2020.6c7y-gq39. Tabular data detailing clinical and technical metadata linked to segmentation cases are also available. Thoracic cavity segmentations will be valuable for developing image analysis pipelines on pathologic lungs - where current automated algorithms struggle most. In conjunction with gross tumor volume segmentations already available from "NSCLC Radiomics," pleural effusion segmentations may be valuable for investigating radiomics profile differences between effusion and primary tumor or training algorithms to discriminate between them.

Imaging for Response Assessment in Radiation Oncology: Current and Emerging Techniques.

Imaging in radiation oncology is essential for the evaluation of treatment response in tumors and organs at risk. This influences further treatment decisions and could possibly be used to adapt therapy. This review article focuses on the currently used imaging modalities for response assessment in radiation oncology and gives an overview of new and promising techniques within this field.

"Après Mois, Le Déluge": Preparing for the Coming Data Flood in the MRI-Guided Radiotherapy Era.

Magnetic resonance imaging provides a sea of quantitative and semi-quantitative data. While radiation oncologists already navigate a pool of clinical (semantic) and imaging data, the tide will swell with the advent of hybrid MRI/linear accelerator devices and increasing interest in MRI-guided radiotherapy (MRIgRT), including adaptive MRIgRT. The variety of MR sequences (of greater complexity than the single parameter Hounsfield unit of CT scanning routinely used in radiotherapy), the workflow of adaptive fractionation, and the sheer quantity of daily images acquired are challenges for scaling this technology. Biomedical informatics, which is the science of information in biomedicine, can provide helpful insights for this looming transition. Funneling MRIgRT data into clinically meaningful information streams requires committing to the flow of inter-institutional data accessibility and interoperability initiatives, standardizing MRIgRT dosimetry methods, streamlining MR linear accelerator workflow, and standardizing MRI acquisition and post-processing. This review will attempt to conceptually ford these topics using clinical informatics approaches as a theoretical bridge.

Prospective quantitative quality assurance and deformation estimation of MRI-CT image registration in simulation of head and neck radiotherapy patients.

BACKGROUND: MRI-guided radiotherapy planning (MRIgRT) may be superior to CT-guided planning in some instances owing to its improved soft tissue contrast. However, MR images do not communicate tissue electron density information necessary for dose calculation and therefore must either be co-registered to CT or algorithmically converted to synthetic CT. No robust quality assessment of commercially available MR-CT registration algorithms is yet available; thus we sought to quantify MR-CT registration formally. METHODS: Head and neck non-contrast CT and T2 MRI scans acquired with standard treatment immobilization techniques were prospectively acquired from 15 patients. Per scan, 35 anatomic regions of interest (ROIs) were manually segmented. MRIs were registered to CT rigidly (RIR) and by three commercially available deformable registration algorithms (DIR). Dice similarity coefficient (DSC), Hausdorff distance mean (HD mean) and Hausdorff distance max (HD max) metrics were calculated to assess concordance between MRI and CT segmentations. Each DIR algorithm was compared to DIR using the nonparametric Steel test with control for individual ROIs (n = 105 tests) and for all ROIs in aggregate (n = 3 tests). The influence of tissue type on registration fidelity was assessed using nonparametric Wilcoxon pairwise tests between ROIs grouped by tissue type (n = 12 tests). Bonferroni corrections were applied for multiple comparisons. RESULTS: No DIR algorithm improved the segmentation quality over RIR for any ROI nor all ROIs in aggregate (all p values >0.05). Muscle and gland ROIs were significantly more concordant than vessel and bone, but DIR remained non-different from RIR. CONCLUSIONS: For MR-CT co-registration, our results question the utility and applicability of commercially available DIR over RIR alone. The poor overall performance also questions the feasibility of translating tissue electron density information to MRI by CT registration, rather than addressing this need with synthetic CT generation or bulk-density assignment.