In helical tomotherapy (HT), the beam intensity is modulated by controlling the leaf open time (LOT) of a binary multileaf collimator (MLC), represented as sinograms. Comparing planned and recorded sinograms enables the evaluation of MLC delivery errors. This study proposes a novel sinogram difference metric—the time difference rate (TDR)— and evaluates its association with treatment planning parameters and the Patient-specific quality assurance gamma passing rate (GPR). Treatment plans of 153 patients with head and neck cancer who underwent IMRT with HT were retrospectively analyzed. Planned and recorded sinograms were compared to calculate relative and absolute TDRs, defined as the percentage of active sinogram elements exceeding predefined LOT difference thresholds. Relative TDR thresholds were 2 TDR_3% and TDR_5% showed weak but significant correlations with GPRs, with Spearman’s rank correlation coefficients ranging from − 0.241 to − 0.175. Among the absolute metrics, TDR_10ms , TDR_15ms , and TDR_20ms showed weak but significant negative correlations with GPR 3 TDR_3% and TDR_5% may complement conventional PSQA by directly evaluating MLC delivery accuracy from recorded sinograms.
Rapid and accurate detection of renal trauma is essential in emergency medicine. This study aimed to automatically classify renal trauma using 2D convolutional neural network (CNN) and vision transformer (ViT) models on arterial- and venous-phase computed tomography (CT) images. We analyzed CT images from 94 patients, including 47 without renal trauma and 47 with renal trauma (30,951 and 15,086 images, respectively). Arterial- and venous-phase CT images were reconstructed into axial, coronal, and sagittal images, with the renal regions cropped to construct the image datasets. Five pretrained CNN-based and five pretrained ViT-based 2D models were fine-tuned to classify renal trauma, and their performance was evaluated at the slice and patient levels using the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. At the slice level, the sagittal Inception-V3 model achieved the highest AUC values of 0.986 for venous-phase and 0.975 for arterial-phase images. At the patient level, the coronal Inception-V3 model achieved the highest AUC values of 0.991 for venous-phase and 0.945 for arterial-phase images. CNN-based models outperformed ViT-based models at both levels, with slice-level mean AUC values of 0.971 and 0.940 for venous-phase and 0.942 and 0.914 for arterial-phase images and patient-level values of 0.947 and 0.928 for venous-phase and 0.914 and 0.886 for arterial-phase images, respectively. The 2D models demonstrated high diagnostic performance for renal trauma, even when using arterial-phase images alone, supporting their potential for rapid decision-making in emergency settings.
In Gamma Knife stereotactic radiosurgery (SRS), achieving optimal dosimetric outcomes is physically constrained by complex tumor geometry. While the Gradient Index (GI) and Conformity Index (CI) define plan quality, the volume receiving 12Gy(V_12Gy) and Shot Density dictate patient safety and efficiency. Current volumetric heuristics fail to capture the topological irregularities that govern these parameters. This study introduces a physics-aware Geometric Deep Learning framework to simultaneously predict quality, safety, and complexity metrics directly from surface topology. Methods: Utilizing the Vestibular-Schwannoma-SEG dataset (n=100) , tumor manifolds were converted into physics-aware point clouds enriched with 12-dimensional feature vectors, including surface normals and radial curvature. A multi-task PointNet-based architecture, termed “GammaPoint-Net,” was developed to regress GI, CI, V_12Gy , and Shot Density. The framework was benchmarked against 3D Voxel-based CNNs, standard volumetric regression, conventional machine-learning regressors trained on handcrafted 3D shape descriptors (Random Forest, Support Vector Regression, and XGBoost), and point-based architectures using 5-fold cross-validation. GammaPoint-Net achieved superior predictive accuracy across all objectives ( R_GI^2=0.79,R_V12^2=0.75 ), significantly outperforming volumetric baselines (R^2<0.25) . Ablation studies confirmed that incorporating differential geometric features reduced the mean absolute error by 46 R^2=0.72 ; paired Wilcoxon p=0.038 ). Saliency mapping demonstrated that the network autonomously identifies high-curvature surface protrusions as the primary drivers of dosimetric degradation. GammaPoint-Net demonstrates that surface topology, rather than volume, is the fundamental determinant of radiosurgical plan quality. This framework provides an instantaneous, interpretable pre-planning assessment, enabling physicists to anticipate plan difficulty and toxicity risks prior to optimization.
Our study aimed to perform a comprehensive end-to-end (E2E) dosimetric and geometric evaluation of the newly commissioned Varian Edge linear accelerator (LINAC) with the HyperArc™ VMAT system for multi-target stereotactic radiosurgery (SRS) to ensure clinical accuracy and safety in the treatment of multiple brain metastases. E2E testing was conducted using the MAX-EA anthropomorphic phantom, incorporating ion chamber and film inserts. The phantom was immobilized with a Q-fix Encompass system and scanned with a 0.625 mm CT protocol. Five spherical PTVs range between (0.3–9.2 cc) were planned using Eclipse™ v18.01 with 6 MV-FFF beams and optimized via the Photon Optimizer algorithm with Acuros XB (1.25 mm grid). A HyperArc™ plan prescribing 15 Gy to each target was generated. Ionization chamber, Gafchromic EBT-XD film, portal dosimetry (EPID), and Multi-Target Winston-Lutz (W-L) tests were used to evaluate dosimetric and geometric accuracy. The measured-to-calculated dose difference was − 3.3
