Fast personalized CT dose calculations with GPUMCD
Bibliographic record
Abstract
PURPOSE: The continuous increase of population dose due to ever-rising Computed Tomography (CT) examinations has called for more personalized dose estimations in medical imaging - a far from trivial task. This study aims to demonstrate a GPU-enabled pipeline combining automatic segmentation with GPU Monte Carlo Dose (GPUMCD) simulations to provide patient-specific dose-to-organ CT dosimetry reports using existing patient CT images. METHODS: A dynamic representation of the CT imaging process was reproduced within GPUMCD using information in DICOM headers, complemented by in-house exposure measurements, and validated in homogeneous and anthropomorphic phantoms. A dose pipeline was implemented using GPUMCD and a pre-trained open-source nnU-net model (TotalSegmentator). Dose-to-organ dosimetry was obtained for images from a lung cancer screening program and stored in DICOM-compliant Structured Reports. RESULTS: GPUMCD calculated dose values were within 5.5% of measurements for all phantoms and investigated conditions. Utilizing one A100-SXM4-40GB GPU, the average pipeline runtime was 6 min and 06 s per CT study. The GPU-driven simulation and segmentation operation took 46% (2 min and 7 s) of the total runtime, and data processing (file reading, conversion, and writing) occupied the remaining 54%. CONCLUSION: This work demonstrates the ability to generate patient-specific three-dimensional dose distributions in CT within a few seconds and the subsequent feasibility of performing fully automated mass personalized dose-to-organ calculations. The pipeline ingests and produces DICOM-compliant data compatible with clinical and research environments, enabling routine imaging dosimetry and large-scale retroactive dosimetry studies.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".