{"id":18299,"date":"2026-06-15T19:21:09","date_gmt":"2026-06-15T22:21:09","guid":{"rendered":"https:\/\/rtmedical.com.br\/tmp-en-1781562068989\/"},"modified":"2026-06-15T19:25:54","modified_gmt":"2026-06-15T22:25:54","slug":"doserad2026-monte-carlo-ai-dose-calculation","status":"publish","type":"post","link":"https:\/\/rtmedical.com.br\/en\/doserad2026-monte-carlo-ai-dose-calculation\/","title":{"rendered":"DoseRAD2026: Monte Carlo as Reference for AI Dose Calculation"},"content":{"rendered":"<p><a href=\"https:\/\/doserad2026.grand-challenge.org\/\" rel=\"noopener\" target=\"_blank\">DoseRAD2026<\/a> is important because it turns AI dose calculation into a measurable benchmark: given a CT or MRI volume and beam parameters, an algorithm must output a beam-specific 3D dose distribution.<\/p>\n<p>The key point is that the reference is not a subjective planning preference. The dataset provides Monte Carlo reference doses, allowing methods to be evaluated for both speed and error across photon and proton tasks.<\/p>\n<figure class=\"wp-block-image size-large dose-algorithm-infographic\"><img alt=\"DoseRAD2026 benchmark with CT, MRI, photons, protons, and Monte Carlo reference dose\" decoding=\"async\" data-src=\"https:\/\/rtmedical.com.br\/wp-content\/uploads\/2026\/06\/doserad2026-monte-carlo-benchmark.jpg\" src=\"data:image\/svg+xml;base64,PHN2ZyB3aWR0aD0iMSIgaGVpZ2h0PSIxIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciPjwvc3ZnPg==\" class=\"lazyload\" style=\"--smush-placeholder-width: 1600px; --smush-placeholder-aspect-ratio: 1600\/900;\" \/><figcaption>Original RT Medical Systems infographic for the AI-predicted dose cluster.<\/figcaption><\/figure>\n<figure class=\"wp-block-image size-large dose-source-figure\"><img alt=\"Public DoseRAD2026 challenge banner\" decoding=\"async\" data-src=\"https:\/\/public.grand-challenge-user-content.org\/b\/838\/Banner2x_koQAIYM.png\" src=\"data:image\/svg+xml;base64,PHN2ZyB3aWR0aD0iMSIgaGVpZ2h0PSIxIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciPjwvc3ZnPg==\" class=\"lazyload\" \/><figcaption>Public DoseRAD2026 banner on Grand Challenge. Source: <a href=\"https:\/\/doserad2026.grand-challenge.org\/\" rel=\"noopener\" target=\"_blank\">https:\/\/doserad2026.grand-challenge.org\/<\/a><\/figcaption><\/figure>\n<h2>What the challenge asks for<\/h2>\n<ul>\n<li>Photon dose on CT, relevant to VMAT and conventional planning.<\/li>\n<li>Photon dose on MRI, relevant to MR-Linac and online adaptive radiotherapy.<\/li>\n<li>Proton dose on CT, where range error can change clinical interpretation.<\/li>\n<li>Proton dose on MRI, connecting MRI-only workflows and MRI-guided proton research.<\/li>\n<\/ul>\n<p>Each task receives a 3D image and beam specification. Photon beams are VMAT-like control-point segments with MLC, gantry and isocenter information. Proton beams are pencil beam spots with position, energy and geometry.<\/p>\n<h2>Why Monte Carlo is the ground truth<\/h2>\n<p>The <a href=\"https:\/\/rtmedical.com.br\/en\/monte-carlo-radiotherapy-guide\/\">Monte Carlo radiotherapy<\/a> article explains the physics: MC models particle transport with high fidelity, but computational cost still limits workflows that need near-real-time response. DoseRAD2026 uses MC as the reference to test whether fast methods can approximate that physics with acceptable error.<\/p>\n<p>That does not mean that every model trained against MC is clinically approved. It means the evaluation target is stronger than only comparing against human-approved plans or a specific analytical TPS engine.<\/p>\n<h2>Dataset and scale<\/h2>\n<figure class=\"wp-block-table\">\n<table>\n<thead>\n<tr>\n<th>Dimension<\/th>\n<th>Description<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Patients<\/td>\n<td>122 thoracic and abdominal cases with spatially aligned CT and MRI<\/td>\n<\/tr>\n<tr>\n<td>Training<\/td>\n<td>75 patients released in April 2026<\/td>\n<\/tr>\n<tr>\n<td>Testing<\/td>\n<td>40 private patients until March 2030 and 7 private external patients<\/td>\n<\/tr>\n<tr>\n<td>Photons<\/td>\n<td>40,500 training beam segments<\/td>\n<\/tr>\n<tr>\n<td>Protons<\/td>\n<td>81,000 training beamlets<\/td>\n<\/tr>\n<tr>\n<td>Reference<\/td>\n<td>Beam-level Geant4 Monte Carlo dose, reported as dose-to-medium in Gy<\/td>\n<\/tr>\n<tr>\n<td>License<\/td>\n<td>CC BY-NC 4.0 for research and education, non-commercial<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/figure>\n<h2>Metrics that matter<\/h2>\n<p>The <a href=\"https:\/\/doserad2026.grand-challenge.org\/metrics-and-ranking\/\" rel=\"noopener\" target=\"_blank\">metrics page<\/a> separates beam-level and plan-level evaluation. Beam-level metrics include masked mean absolute error in the high-dose region and integrated depth-dose curve distance. Plan-level metrics include stratified MAE, 3D local 1%\/1 mm gamma, and a DVH-based clinical score.<\/p>\n<p>The clinically interesting constraint is runtime. The challenge imposes an average limit below 1 second per beam, including loading and initialization, on an AWS g5 instance. That forces submissions to balance accuracy and speed.<\/p>\n<h2>What this changes clinically<\/h2>\n<ul>\n<li>It separates fast-dose research from commercial <a href=\"https:\/\/rtmedical.com.br\/en\/ai-predicted-dose-mvision-raystation-optiplan\/\">AI-assisted planning tools<\/a>.<\/li>\n<li>It connects directly to <a href=\"https:\/\/rtmedical.com.br\/en\/adaptive-radiotherapy-dose-recalculation-cbct-synthetic-ct\/\">adaptive dose recalculation on CBCT and synthetic CT<\/a>, where time and uncertainty matter.<\/li>\n<li>It exposes the difference between beamlet\/segment dose prediction and a clinically approvable treatment plan.<\/li>\n<li>It reinforces that <a href=\"https:\/\/rtmedical.com.br\/en\/validate-ai-predicted-dose-qa-commissioning\/\">validation and QA<\/a> must evaluate anatomy, beam geometry, material mapping, runtime, and DVH impact.<\/li>\n<\/ul>\n<h2>Interpretation risk<\/h2>\n<p>DoseRAD2026 is a benchmark, not a clinical authorization. It includes simplified linac and proton models, private test data, and challenge-specific submission rules. A winning method may be scientifically promising and still require engineering, regulation, cybersecurity, DICOM integration, and local validation before patient use.<\/p>\n<h2>FAQ<\/h2>\n<h3>Does DoseRAD2026 use Monte Carlo data for training?<\/h3>\n<p>Yes. For each beam or beamlet, the dataset provides a Monte Carlo reference dose distribution, along with CT, MRI, and beam configuration files.<\/p>\n<h3>Does the challenge evaluate full plans?<\/h3>\n<p>Participants output individual beam dose maps; the evaluation also reconstructs complete plans using clinical weights to compute MAE, gamma, and DVH metrics.<\/p>\n<h3>Why are there MRI tasks?<\/h3>\n<p>MRI does not directly provide electron density. That creates a dose-calculation problem for MRI-only, MR-Linac, and adaptive workflows that must infer or bypass material information.<\/p>\n<section class=\"dose-ai-references\">\n<h2>References<\/h2>\n<ol>\n<li>DoseRAD2026 Grand Challenge. <a href=\"https:\/\/doserad2026.grand-challenge.org\/\" rel=\"noopener\" target=\"_blank\">https:\/\/doserad2026.grand-challenge.org\/<\/a><\/li>\n<li>DoseRAD2026 dataset. <a href=\"https:\/\/doserad2026.grand-challenge.org\/data\/\" rel=\"noopener\" target=\"_blank\">https:\/\/doserad2026.grand-challenge.org\/data\/<\/a><\/li>\n<li>DoseRAD2026 metrics and ranking. <a href=\"https:\/\/doserad2026.grand-challenge.org\/metrics-and-ranking\/\" rel=\"noopener\" target=\"_blank\">https:\/\/doserad2026.grand-challenge.org\/metrics-and-ranking\/<\/a><\/li>\n<li>DoseRAD2026 rules. <a href=\"https:\/\/doserad2026.grand-challenge.org\/timeline-and-rules\/\" rel=\"noopener\" target=\"_blank\">https:\/\/doserad2026.grand-challenge.org\/timeline-and-rules\/<\/a><\/li>\n<li>DoseRAD2026 Hugging Face dataset. <a href=\"https:\/\/huggingface.co\/datasets\/LMUK-RADONC-PHYS-RES\/DoseRAD2026\" rel=\"noopener\" target=\"_blank\">https:\/\/huggingface.co\/datasets\/LMUK-RADONC-PHYS-RES\/DoseRAD2026<\/a><\/li>\n<li>DoseRAD2026 Zenodo DOI. <a href=\"https:\/\/doi.org\/10.5281\/zenodo.19347848\" rel=\"noopener\" target=\"_blank\">https:\/\/doi.org\/10.5281\/zenodo.19347848<\/a><\/li>\n<li>DoseRAD2026 dataset paper. <a href=\"https:\/\/doi.org\/10.48550\/arXiv.2604.12778\" rel=\"noopener\" target=\"_blank\">https:\/\/doi.org\/10.48550\/arXiv.2604.12778<\/a><\/li>\n<\/ol>\n<\/section>\n<aside aria-label=\"AI dose prediction series\" class=\"dose-ai-series\">\n<h2>Series: AI-predicted dose<\/h2>\n<ul>\n<li><a href=\"https:\/\/rtmedical.com.br\/en\/ai-radiotherapy-dose-calculation-monte-carlo\/\">Hub: AI dose calculation<\/a><\/li>\n<li><a href=\"https:\/\/rtmedical.com.br\/en\/ai-predicted-dose-mvision-raystation-optiplan\/\">MVision, RayStation, and OptiPlan<\/a><\/li>\n<li><strong>DoseRAD2026 and Monte Carlo<\/strong><\/li>\n<li><a href=\"https:\/\/rtmedical.com.br\/en\/validate-ai-predicted-dose-qa-commissioning\/\">Validation, QA, and commissioning<\/a><\/li>\n<\/ul>\n<\/aside>\n<aside aria-label=\"Dose-calculation algorithm map\" class=\"dose-cluster-nav\">\n<h2>Dose-calculation algorithm map<\/h2>\n<h3>Methods and algorithms<\/h3>\n<ul>\n<li><a href=\"https:\/\/rtmedical.com.br\/en\/photon-dose-calculation-algorithms\/\">Complete guide<\/a><\/li>\n<li><a href=\"https:\/\/rtmedical.com.br\/en\/empirical-broad-beam-dose-calculation\/\">Empirical methods and Batho<\/a><\/li>\n<li><a href=\"https:\/\/rtmedical.com.br\/en\/superposition-clarkson-terma-dose\/\">Clarkson, superposition, and TERMA<\/a><\/li>\n<li><a href=\"https:\/\/rtmedical.com.br\/en\/pencil-beam-radiotherapy-limitations\/\">Pencil Beam<\/a><\/li>\n<li><a href=\"https:\/\/rtmedical.com.br\/en\/collapsed-cone-convolution-kernels\/\">Collapsed Cone<\/a><\/li>\n<li><a href=\"https:\/\/rtmedical.com.br\/en\/aaa-eclipse-algorithm-explained\/\">AAA<\/a><\/li>\n<li><a href=\"https:\/\/rtmedical.com.br\/en\/acuros-xb-lbte-dose-calculation\/\">Acuros XB<\/a><\/li>\n<li><a href=\"https:\/\/rtmedical.com.br\/en\/dose-to-medium-vs-dose-to-water-radiotherapy\/\">Dose to medium vs dose to water<\/a><\/li>\n<li><a href=\"https:\/\/rtmedical.com.br\/en\/monte-carlo-radiotherapy-guide\/\">Monte Carlo<\/a><\/li>\n<\/ul>\n<h3>Advanced applications<\/h3>\n<ul>\n<li><a href=\"https:\/\/rtmedical.com.br\/en\/monaco-gpumcd-dose-to-medium-dose-to-water\/\">Monaco and GPUMCD<\/a><\/li>\n<li><a href=\"https:\/\/rtmedical.com.br\/en\/electron-dose-algorithms-pencil-beam-emc-monte-carlo\/\">Electron dose algorithms<\/a><\/li>\n<li><a href=\"https:\/\/rtmedical.com.br\/en\/protons-pencil-beam-vs-monte-carlo-dose-calculation\/\">Protons: Pencil Beam vs Monte Carlo<\/a><\/li>\n<li><a href=\"https:\/\/rtmedical.com.br\/en\/mr-linac-magnetic-field-dose-calculation-monte-carlo\/\">MR-Linac dose calculation<\/a><\/li>\n<li><a href=\"https:\/\/rtmedical.com.br\/en\/adaptive-radiotherapy-dose-recalculation-cbct-synthetic-ct\/\">Adaptive recalculation on CBCT and synthetic CT<\/a><\/li>\n<li><a href=\"https:\/\/rtmedical.com.br\/en\/ai-radiotherapy-dose-calculation-monte-carlo\/\">AI dose calculation<\/a><\/li>\n<li><a href=\"https:\/\/rtmedical.com.br\/en\/commissioning-qa-dose-algorithm-comparison\/\">Commissioning and QA<\/a><\/li>\n<\/ul>\n<\/aside>\n","protected":false},"excerpt":{"rendered":"<p>What the DoseRAD2026 challenge teaches about fast dose models trained and evaluated against Monte Carlo simulations.<\/p>\n","protected":false},"author":1,"featured_media":18287,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"om_disable_all_campaigns":false,"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"ngg_post_thumbnail":0,"fifu_image_url":"","fifu_image_alt":"","footnotes":""},"categories":[99,230],"tags":[],"class_list":{"0":"post-18299","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-radiotherapy","8":"category-software-en"},"aioseo_notices":[],"rt_seo":{"title":"DoseRAD2026: Monte Carlo as Reference for AI Dose Calculatio","description":"DoseRAD2026 uses CT, MRI, photons, protons, and Monte Carlo doses to evaluate fast AI dose calculation in radiotherapy.","canonical":"https:\/\/rtmedical.com.br\/en\/doserad2026-monte-carlo-ai-dose-calculation\/","og_image":"https:\/\/rtmedical.com.br\/wp-content\/uploads\/2026\/06\/doserad2026-monte-carlo-benchmark.jpg","robots":"index,follow","schema_type":"Article","include_in_llms":true,"llms_label":"Technical guide","llms_summary":"What the DoseRAD2026 challenge teaches about fast dose models trained and evaluated against Monte Carlo simulations.","faq_items":[{"q":"Does DoseRAD2026 use Monte Carlo data for training?","a":"Yes. The dataset provides Monte Carlo reference dose per beam or beamlet, along with CT, MRI, and beam configuration."},{"q":"Does the challenge evaluate complete plans?","a":"Participants output beam dose maps; evaluation reconstructs complete plans with clinical weights to compute MAE, gamma, and DVH metrics."},{"q":"Why are there MRI tasks?","a":"MRI does not directly provide electron density, creating a problem for MRI-only, MR-Linac, and adaptive workflows."}],"video":[],"gtin":"","mpn":"","brand":"","aggregate_rating":[]},"_links":{"self":[{"href":"https:\/\/rtmedical.com.br\/en\/wp-json\/wp\/v2\/posts\/18299\/"}],"collection":[{"href":"https:\/\/rtmedical.com.br\/en\/wp-json\/wp\/v2\/posts\/"}],"about":[{"href":"https:\/\/rtmedical.com.br\/en\/wp-json\/wp\/v2\/types\/post\/"}],"author":[{"embeddable":true,"href":"https:\/\/rtmedical.com.br\/en\/wp-json\/wp\/v2\/users\/1\/"}],"replies":[{"embeddable":true,"href":"https:\/\/rtmedical.com.br\/en\/wp-json\/wp\/v2\/comments\/?post=18299"}],"version-history":[{"count":1,"href":"https:\/\/rtmedical.com.br\/en\/wp-json\/wp\/v2\/posts\/18299\/revisions\/"}],"predecessor-version":[{"id":18301,"href":"https:\/\/rtmedical.com.br\/en\/wp-json\/wp\/v2\/posts\/18299\/revisions\/18301\/"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/rtmedical.com.br\/en\/wp-json\/wp\/v2\/media\/18287\/"}],"wp:attachment":[{"href":"https:\/\/rtmedical.com.br\/en\/wp-json\/wp\/v2\/media\/?parent=18299"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/rtmedical.com.br\/en\/wp-json\/wp\/v2\/categories\/?post=18299"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/rtmedical.com.br\/en\/wp-json\/wp\/v2\/tags\/?post=18299"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}