A TPS integrated machine learning tool for predicting patient-specific quality assurance outcomes in volumetric-modulated arc therapy.

PURPOSE: Machine learning (ML) models have been demonstrated to be beneficial for optimizing the workload of patient-specific quality assurance (PSQA). Implementing them in clinical routine frequently requires third-party applications beyond the treatment planning system (TPS), slowing down the workflow. To address this issue, a PSQA outcomes predictive model was carefully selected and validated before being fully integrated into the TPS. MATERIALS AND METHODS: Nine ML algorithms were evaluated using cross-validation. The learning database was built by calculating complexity metrics (CM) and binarizing PSQA results into "pass"/"fail" classes for 1767 VMAT arcs. The predictive performance was evaluated using area under the ROC curve (AUROC), sensitivity, and specificity. The ML model was integrated into the TPS via a C# script. Script-guided reoptimization impact on PSQA and dosimetric results was evaluated on ten VMAT plans with "fail"-predicted arcs. Workload reduction potential was also assessed. RESULTS: The selected model exhibited an AUROC of 0.88, with a sensitivity and specificity exceeding 50 % and 90 %, respectively. The script-guided reoptimization of the ten evaluated plans led to an average improvement of 1.4 ± 0.9 percentage points in PSQA results, while preserving the quality of the dose distribution. A yearly savings of about 140 h with the use of the script was estimated. CONCLUSIONS: The proposed script is a valuable complementary tool for PSQA measurement. It was efficiently integrated into the clinical workflow to enhance PSQA outcomes and reduce PSQA workload by decreasing the risk of failing QA and thereby, the need for repeated replanning and measurements.

Diversity within olfactory sensory derivatives revealed by the contribution of Dbx1 lineages.

In vertebrates, the embryonic olfactory epithelium contains progenitors that will give rise to distinct classes of neurons, including olfactory sensory neurons (OSNs; involved in odor detection), vomeronasal sensory neurons (VSNs; responsible for pheromone sensing), and gonadotropin-releasing hormone (GnRH) neurons that control the hypothalamic-pituitary-gonadal axis. Currently, these three neuronal lineages are usually believed to emerge from uniform pools of progenitors. Here, we found that the homeodomain transcription factor Dbx1 is expressed by neurogenic progenitors in the developing and adult mouse olfactory epithelium. We demonstrate that Dbx1 itself is dispensable for neuronal fate specification and global organization of the olfactory sensory system. Using lineage tracing, we characterize the contribution of Dbx1 lineages to OSN, VSN, and GnRH neuron populations and reveal an unexpected degree of diversity. Furthermore, we demonstrate that Dbx1-expressing progenitors remain neurogenic in the absence of the proneural gene Ascl1. Our work therefore points to the existence of distinct neurogenic programs in Dbx1-derived and other olfactory lineages.

p53/p21 pathway activation contributes to the ependymal fate decision downstream of GemC1.

Multiciliated ependymal cells and adult neural stem cells are components of the adult neurogenic niche, essential for brain homeostasis. These cells share a common glial cell lineage regulated by the Geminin family members Geminin and GemC1/Mcidas. Ependymal precursors require GemC1/Mcidas expression to massively amplify centrioles and become multiciliated cells. Here, we show that GemC1-dependent differentiation is initiated in actively cycling radial glial cells, in which a DNA damage response, including DNA replication-associated damage and dysfunctional telomeres, is induced, without affecting cell survival. Genotoxic stress is not sufficient by itself to induce ependymal cell differentiation, although the absence of p53 or p21 in progenitors hinders differentiation by maintaining cell division. Activation of the p53-p21 pathway downstream of GemC1 leads to cell-cycle slowdown/arrest, which permits timely onset of ependymal cell differentiation in progenitor cells.

Implementation of volumetric-modulated arc therapy for locally advanced breast cancer patients: Dosimetric comparison with deliverability consideration of planning techniques and predictions of patient-specific QA results via supervised machine learning.

PURPOSE: The aim of this study was to implement a clinically deliverable VMAT planning technique dedicated to advanced breast cancer, and to predict failed QA using a machine learning (ML) model to optimize the QA workload. METHODS: For three planning methods (2A: 2-partial arc, 2AS: 2-partial arc with splitting, 4A: 4-partial arc), dosimetric results were compared with patient-specific QA performed with the electronic portal imaging device of the linac. A dataset was built with the pass/fail status of the plans and complexity metrics. It was divided into training and testing sets. An ML metamodel combining predictions from six base classifiers was trained on the training set to predict plans as 'pass' or 'fail'. The predictive performances were evaluated using the unseen data of the testing set. RESULTS: The dosimetric comparison highlighted that 4A was the highest dosimetric performant method but also the poorest performant in the QA process. 2AS spared the best heart, but provided the highest dose to the contralateral breast and lowest node coverage. 2A provides a dosimetric compromise between organ at risk sparing and PTV coverage with satisfactory QA results. The metamodel had a median predictive sensitivity of 73% and a median specificity of 91%. CONCLUSIONS: The 2A method was selected to calculate clinically deliverable VMAT plans; however, the 2AS method was maintained when the heart was of particular importance and breath-hold techniques were not applicable. The metamodel provides promising predictive performance, and it is intended to be improved as a larger dataset becomes available.

Single-cell transcriptomics of the early developing mouse cerebral cortex disentangle the spatial and temporal components of neuronal fate acquisition.

In the developing cerebral cortex, how progenitors that seemingly display limited diversity end up producing a vast array of neurons remains a puzzling question. The prevailing model suggests that temporal maturation of progenitors is a key driver in the diversification of the neuronal output. However, temporal constraints are unlikely to account for all diversity, especially in the ventral and lateral pallium where neuronal types significantly differ from their dorsal neocortical counterparts born at the same time. In this study, we implemented single-cell RNAseq to sample the diversity of progenitors and neurons along the dorso-ventral axis of the early developing pallium. We first identified neuronal types, mapped them on the tissue and determined their origin through genetic tracing. We characterised progenitor diversity and disentangled the gene modules underlying temporal versus spatial regulations of neuronal specification. Finally, we reconstructed the developmental trajectories followed by ventral and dorsal pallial neurons to identify lineage-specific gene waves. Our data suggest a model by which discrete neuronal fate acquisition from a continuous gradient of progenitors results from the superimposition of spatial information and temporal maturation.

A GATE/Geant4 Monte Carlo toolkit for surface dose calculation in VMAT breast cancer radiotherapy.

The accuracy of superficial dose calculations for breast cancer treatments with Volumetric Modulated Arc Therapy (VMAT) is of major importance. For target volumes close to the surface, the inverse dosimetric planning can lead to very high fluences in the build-up region to properly cover the volume to be treated. Various radiotherapy modalities are currently used in parallel with additional protocols to enable a better control on the dose delivery (bolus, target volume margins). One of the difficulties currently facing medical physicists is the lack of available tools to test the impact of these different solutions on the superficial dose distribution. We present a new open source toolkit to assist medical physicists in evaluating the 3D distributions of superficial dose in VMAT breast cancer treatments. This tool is based on the GATE Monte Carlo software, a Geant4 application dedicated to medical physics. A set of macros has been developed to simulate in an easy way a full VMAT plan from the information available in the DICOM-RT files (image, plan, structure and dose). The toolkit has been tested on a 6 MV Varian NovalisTx™ accelerator. The paper presents a precise comparison of 3D surface dose distributions from experimental measurements (EBT3 films), TPS (Varian Eclipse) and Monte Carlo simulation (GATE). The comparison made it possible to highlight both the TPS biases for the surface dose calculation and the good performances of the developed toolkit. The simulation of surface dose distributions on a real patient has also been performed to illustrate the potential clinical applications.

18F-FDOPA PET/CT Combined with MRI for Gross Tumor Volume Delineation in Patients with Skull Base Paraganglioma.

In this simulation study, we assessed differences in gross tumor volume (GTV) in a series of skull base paragangliomas (SBPGLs) using magnetic resonance imaging (MRI), 18F-dihydroxyphenylalanine (18F-FDOPA) combined positron emission tomography/computed tomography (PET/CT), and 18F-FDOPA PET/MRI images obtained by rigid alignment of PET and MRI. GTV was delineated in 16 patients with SBPGLs on MRI (GTVMRI), 18F-FDOPA PET/CT (GTVPET), and combined PET/MRI (GTVPET/MRI). GTVPET/MRI was the union of GTVMRI and GTVPET after visual adjustment. Three observers delineated GTVMRI and GTVPET/MRI independently. Excellent interobserver reproducibility was found for both GTVMRI and GTVPET/MRI. GTVPET and GTVMRI were not significantly different. However, there was some spatial difference between the locations of GTVMRI, GTVPET, and GTVPET/MRI. The Dice similarity coefficient median value was 0.4 between PET/CT and MRI, and 0.8 between MRI and PET/MRI. The combined use of PET/MRI produced a larger GTV than MRI alone. Nevertheless, both the target-delivered dose and organs-at-risk conservancy were respected when treatment was planned on the PET/MRI-matched data set. Future integration of 18F-FDOPA PET/CT into clinical practice will be necessary to evaluate the influence of this diagnostic modality on SBPGL therapeutic management. If the clinical utility of 18F-FDOPA PET/CT and/or PET/MRI is confirmed, GTVPET/MRI should be considered for tailored radiotherapy planning in patients with SBPGL.