HEAD-QA is a multi-choice HEAlthcare Dataset. The questions come from exams to access a specialized position in the Spanish healthcare system, and are challenging even for highly specialized humans. They are designed by the Ministerio de Sanidad, Consumo y Bienestar Social.The dataset contains questions about following topics: medicine, nursing, psychology, chemistry, pharmacology and biology.

HeadQA is a multi-choice question answering testbed to encourage research on complex reasoning. The questions come from exams to access a specialized position in the Spanish healthcare system, and are challenging even for highly specialized humans.

Purpose: This study aimed to evaluate the utility of a new plan feature (planomics feature) for predicting the results of patient-specific quality assurance using the head and neck (H&N) volumetric modulated arc therapy (VMAT) plan.Methods: One hundred and thirty-one H&N VMAT plans in our institution from 2019 to 2021 were retrospectively collected. Dosimetric verification for all plans was carried out using the portal dosimetry system integrated into the Eclipse treatment planning system based on the electronic portal imaging devices. Gamma passing rates (GPR) were analyzed using three gamma indices of 3%/3 mm, 3%/2 mm, and 2%/2 mm with a 10% dose threshold. Forty-eight conventional features affecting the dose delivery accuracy were used in the study, and 2,476 planomics features were extracted based on the radiotherapy plan file. Three prediction and classification models using conventional features (CF), planomics features (PF), and hybrid features (HF) combining two sets of features were constructed by the gradient boosting regressor (GBR) and Ridge classifier for each GPR of 3%/3 mm, 3%/2 mm, and 2%/2 mm, respectively. The absolute prediction error (APE) and the area under the curve (AUC) were adopted for assessing the performance of prediction and classification models.Results: In the GPR prediction, the average APE of the models using CF, PF, and HF was 1.3 ± 1.2%/3.6 ± 3.0%, 1.7 ± 1.5%/3.8 ± 3.5%, and 1.1 ± 1.0%/4.1 ± 3.1% for 2%/2 mm; 0.7 ± 0.6%/2.0 ± 2.0%, 1.0±1.1%/2.2 ± 1.8%, and 0.6 ± 0.6%/2.2 ± 1.9% for 3%/2 mm; and 0.4 ± 0.3%/1.2 ± 1.2%, 0.4±0.5%/1.3 ± 1.0%, and 0.3±0.3%/1.2 ± 1.1% for 3%/3 mm, respectively. In the regression prediction, three models give a similar modeling performance for predicting the GPR. The classification results were 0.67 ± 0.03/0.66 ± 0.07, 0.77 ± 0.03/0.73 ± 0.06, and 0.78 ± 0.02/0.75 ± 0.04 for 3%/3 mm, respectively. For 3%/2 mm, the AUCs of the training and testing cohorts were 0.64 ± 0.03/0.62 ± 0.07, 0.70 ± 0.03/0.67 ± 0.06, and 0.75 ± 0.03/0.71 ± 0.07, respectively, and for 2%/2 mm, the average AUCs of the training and testing cohorts were 0.72 ± 0.03/0.72 ± 0.06, 0.78 ± 0.04/0.73 ± 0.07, and 0.81 ± 0.03/0.75 ± 0.06, respectively. In the classification, the PF model has a better classification performance than the CF model. Moreover, the HF model provides the best result among the three classifications models.Conclusions: The planomics features can be used for predicting and classifying the GPR results and for improving the model performance after combining the conventional features for the GPR classification.

The pass rate calculated in the gamma evaluation of the head and neck RapidArc plan calculated according to the criteria of dose difference and distance-to-agreement.

This repository contains resources, namely TempTabQA, developed for the paper: Gupta, V., Kandoi, P., Vora, M., Zhang, S., He, Y., Reinanda R., Srikumar V., TempTabQA: Temporal Question Answering for Semi-Structured Tables. In: Proceeding of the The 2023 Conference on Empirical Methods in Natural Language Processing, Dec 2023.

TempTabQA is a dataset which comprises 11,454 question-answer pairs extracted from Wikipedia Infobox tables. These question-answer pairs are annotated by human annotators. We provide two test sets instead of one: the Head set with popular frequent domains, and the Tail set with rarer domains.

Files to access the annotation follow the below structure:

Maindata

• qapairs: split into train, dev, head, and tail sets, in both csv and json formats
• Tables: Wikipedia category and tables metadata in csv, json and html formats

Carefully read the ```LICENCE``` for non-academic usage.

Note : Wherever required consider the year of 2022 as the build date for the dataset.

The relative differences of the dosimetric endpoints of head and neck cases between the calculated values in 3DVH under the intentional error conditions and the calculated values in the original plan.

The relative differences of the dosimetric endpoints of head and neck cases between the calculated values in MobiusFX under the intentional error conditions and the calculated values in the original plan.

The experimental setup utilized a co-axial color Charged Couple Device (CCD) camera, integrated into the laser deposition head. This camera operates at a frame rate of 30 frames per second and captures the morphology of the process area. The captured images consist of three RGB channels with a 640 × 480 pixels resolution. To enable the camera to capture the radiation from the process zone, a beam splitter is installed on Precitec's laser applicator head. An optical notch filter within the 650–675 nm range also blocks the laser wavelengths.

The dataset consists of four categories that covers the process map of DED process [.rar file].
The dataset consist of around 48,000 images that are labelled into 4 categories [P1-P2-P3-P4]. The images correspond to DED process zone captured co-axially
The categories are function of linear laser energy deposited. The folder is already split into Train and Test.

The dataset contains CT scans used as input for the algorithm developed in chapters 2 and 3 of the dissertation. Using a CT scan and a treatment plan as inputs, dose and dose change computations in regions of interest can be performed. Specifically, the dataset contains:

• a head and neck CT scan obtained from the CORT dataset [1],
• a prostate CT scan obtained from the Cancer Imaging Archive [2],
• and multiple self-made custom water box CT scans. In addition to a homogeneous water box CT scan (i.e., a cube with uniform 0 Hounsfield Units (HU) composition), there are scans where a slab with half the side-length of the cube and composition of either bone (1000 HU) or air (-1000 HU) is inserted in the water box at varying distances from the middle point.

All the scans consist of CT slices and are stored in the DICOM format. To correctly read, relate to each other and further process the different CT slices, appropriate DICOM reading software (e.g., the pydicom Python package) must be used.

References:

[1] - Craft, D., Bangert, M., Long, T., Papp, D., & Unkelbach, J. (2014). Supporting material for: "Shared data for IMRT optimization research: the CORT dataset" [Data set]. GigaScience Database. https://doi.org/10.5524/100110

[2] - Yorke, A. A., McDonald, G. C., Solis, D., & Guerrero, T. (2019). Pelvic Reference Data (Version 1) [Data set]. The Cancer Imaging Archive. https://doi.org/10.7937/TCIA.2019.WOSKQ5OO

In order to ensure the accuracy of the dose received by the patient in radiotherapy, it is usually necessary to verify the plan before treatment, and the water tank is widely used to achieve this purpose. However, the existing dose validation tanks can only be used for horizontal, vertical and 45° beamline. And those water tanks are inefficient, which cannot meet the multi-angle dose validation requirements of the advanced rotary Gantry beamline treatment rooms. This study aims to meet the beam detection requirements of multi-directional irradiation of Gantry beamline, a 3D water tank for multi-angle beam dose verification was developed. [Methods] The water tank box was made of Polymethyl Methacrylate (PMMA) material, which could be rotated around the isocenter under the drive of the motor. The structure of the water tank was simulated by using Solidworks Simulation software package, and the motion accuracy of the 3D motion mechanism was evaluated. The lateral profile dose distribution of the beam at different depths in the water was measured by a multi-strip ionization chamber, and a 3D dose distribution of the pencil beam can be obtained. The measured results were compared with those of a PTW water tank. [Results] According to the test results, the maximum position error of the probe is 0.132mm when the probe is moving in the depth direction, the maximum position error of the probe is 0.24mm in the Y and Z directions for the probe position adjustment, and the dose measurement deviation is 0.5%±1.18%. [Conclusions] By measuring the lateral profile dose distribution of the beam at different depths in the water, the water tank can quickly and accurately provide the 3D dose distribution of a pencil beam. This device can provide basic data for treatment planning systems and improve the efficiency of regular quality assurance practice. At the same time, with high precision of the 3D motion mechanism, the structure of the water tank is reliable, and the whole measuring device can be rotated around the isocenter of the treatment head. Therefore, this device can meet the beam detection requirements of multi-directional irradiation in the Gantry treatment rooms.

The global radiography test phantom market is experiencing robust growth, driven by the increasing demand for quality assurance and quality control in medical imaging. The rising prevalence of chronic diseases requiring frequent radiographic examinations, coupled with stringent regulatory requirements for medical device accuracy, are key factors fueling market expansion. Technological advancements leading to more sophisticated and versatile phantoms, capable of mimicking various anatomical structures and pathologies with greater precision, are further enhancing market attractiveness. The market is segmented by phantom type (trunk, head, abdomen, neck, others) and application (school, hospital, laboratory, others), reflecting the diverse needs of different user groups. Hospitals and laboratories represent the largest application segments, reflecting the significant role of quality control in clinical settings. North America currently holds a dominant market share, owing to the advanced healthcare infrastructure and high adoption rates of advanced imaging technologies. However, Asia Pacific is projected to witness the fastest growth, driven by increasing healthcare expenditure and rising awareness of the importance of quality assurance in developing economies. Key players in the market are investing heavily in research and development to introduce innovative products and expand their geographic reach, intensifying competition and fostering market growth. The competitive landscape is characterized by a mix of established players and emerging companies, each employing different strategies to gain a competitive edge. Established companies such as Fluke Biomedical and CIRS leverage their extensive experience and brand recognition to maintain market dominance, while smaller players are focusing on niche applications and technological innovations to carve out market share. The market is expected to witness continued consolidation through mergers and acquisitions as larger companies seek to expand their product portfolio and geographic reach. Future growth will be significantly influenced by technological advancements, regulatory changes, and the increasing adoption of advanced imaging modalities. The market's growth trajectory is expected to remain positive over the forecast period, driven by consistent demand and innovative product development.

Pass rates calculated for the gamma evaluation in the tumor target and OARs compared with a reference TPS dose with the calculated dose in 3DVH and compass (C-Recal.: Compass Recalculation, C-Recon.: Compass Reconstruction) for the Head-Neck plans.

Differences in dose metrics of tumor target and OARs calculated using 3DVH and compass (C-Recal.: Compass Recalculation, C-Recon.: Compass Reconstruction) for the Head-Neck plans compared with a reference dose calculated using Eclipse TPS.

PurposeThis study aims to develop a fully automated VMAT planning program for short-course radiotherapy (SCRT) in Locally Advanced Rectal Cancer (LARC) and assess its plan quality, feasibility, and efficiency.Materials and methodsThirty LARC patients who underwent short-course VMAT treatment were retrospectively selected from our institution for this study. An auto-planning program for neoadjuvant short-course radiotherapy (SCRT) in LARC was developed using the RayStation scripting platform integrated with the Python environment. The patients were re-planned using this auto-planning program. Subsequently, the differences between the automatic plans (APs) and existing manual plans (MPs) were compared in terms of plan quality, monitor units (MU), plan complexity, and other dosimetric parameters. Plan quality assurance (QA) was performed using the ArcCHECK dosimetric verification system.ResultsCompared to MPs, the APs achieved similar target coverage and conformity, while providing more rapid dose fall-off. Except for the V5Gy dose level, other dosimetric metrics (V25 Gy, V23 Gy, V15 Gy, Dmean, etc.) for the small bowel were significantly lower in the AP compared to the MP (p 

ObjectiveThis study aimed to develop and validate an Informer- Convolutional Neural Network (CNN) model to predict the gamma passing rate (GPR) for patient-specific quality assurance in volumetric modulated arc therapy (VMAT), enhancing treatment safety and efficacy by integrating multiple data sources.MethodsAnalyzing 465 VMAT treatment plans covering head & neck, chest, and abdomen, the study extracted data from 31 complexity indicators, 123 radiomics features, and 123 dosimetrics indices, along with daily linac performance data including 141 key performance indicators. A hybrid Informer-CNN architecture was used to handle both temporal and non-temporal data for predicting GPR.ResultsThe Informer-CNN model demonstrated superior predictive performance over traditional models like Convolutional Neural Networks (CNN), Long Short-Term Memory(LSTM), and Informer. Specifically, in the validation set, the model achieved a mean absolute error (MAE) of 0.0273 and a root mean square error (RMSE) of 0.0360 using the 3%/3mm criterion. In the test set, the MAE was 0.0327 and the RMSE was 0.0468. The model also showed high classification performance with AUC scores of 0.97 and 0.95 in test and validation sets, respectively.ConclusionThe developed Informer-CNN model significantly enhances the prediction accuracy and classification of gamma passing rates in VMAT treatment plans. It facilitates early integration of daily accelerator performance data, improving the assessment and verification of treatment plans for better patient-specific quality assurance.

BackgroundProton therapy offers precision in targeting tumors while minimizing damage to surrounding healthy tissues. Independent dose calculation is a secondary dose validation tool for patient-specific quality assurance (PSQA) using Monte Carlo simulations.PurposeTo implement independent dose calculation for PSQA in proton therapy and establish confidence limits, tolerance limits, and action limits.Methods and MaterialsThe point dose validation of independent dose calculation was performed by ionization chamber. The dose distributions between independent dose calculation and treatment planning calculation were compared in single and multiple energy plans. Fifty clinical plans covering five regions (head and neck, breast, chest, abdomen, and pelvis) were evaluated using the gamma analysis criteria of 3%, 3 mm, and 5%, 3 mm. Confidence limits, tolerance limits, and action limits were determined.ResultsThe dose differences between measurement and independent dose calculation for each energy level were within 1.0%. The results showing gamma passing rates of 99.4 ± 0.6% for single energy plans and over 98.0% for multiple energy plans. The average gamma passing rates for all treatment sites was 95.9 ± 2.7% with 3%/3 mm criteria, which increased to 97.9 ± 1.8% with 5%/3 mm criteria. The confidence limits, tolerance limits, and action limits showed 90.7%, 89.1%, and 85.4% with 3%/3 mm criteria and 94.3%, 93.2%, and 91.6% for 5%/3 mm criteria, respectively.ConclusionsThe independent dose calculation could potentially be implemented in PSQA. It is a secondary dose validation method for busy clinic. Particular attention should be paid to a confidence limit, tolerance limit, and action limit for reliable treatments.