Evaluating the Ethos automated planning system for spatially fractionated radiotherapy
Bibliographic record
Abstract
PURPOSE: Lattice radiotherapy (LRT), a form of spatially fractionated radiation therapy (SFRT), has emerged as a promising approach for treating massive tumors. By delivering high-dose regions within the tumor while sparing surrounding healthy tissue, LRT offers distinct advantages over conventional radiotherapy. Recent advancements in treatment planning systems (TPS), particularly the integration of intelligent optimization engines (IOEs) with automated planning capabilities, have the potential to further refine and expand the clinical utility of LRT. This study aimed to comparatively evaluate the planning quality and clinical feasibility of lattice SFRT treatment plans generated using the Ethos planning system, equipped with an IOE and O-ring linear accelerator, versus the Eclipse planning system paired with a conventional C-arm TrueBeam linac, in patients with stage III non-small cell lung cancer (NSCLC). METHODS: Twenty retrospective stage III NSCLC cases (GTV > 200 cc) with available PET-CT imaging were selected. A total of 40 plans (20 Eclipse, 20 Ethos) were compared, incorporating lattice spheres (1 cm diameter, 2 cm spacing between spheres) placed in the tumor, FDG-PET/CT-informed intratumoral heterogeneity, prioritizing viable perinecrotic subregions while avoiding critical OARs. Plans aimed to deliver 15 Gy to lattice spheres, limit Valley (PTV minus spheres) doses to 2 Gy, and restrict doses to organs at risk (OARs) to ≤ 3 Gy. Dose conformity, OAR sparing, dose gradient parameters (PEDR, PVDR), planning time, and deliverability, which was evaluated using ArcCheck, EPID gamma analysis, and MLC log-file verification. RESULTS: : 7.62 vs. 7.41). For the valley target, Ethos plans demonstrated a lower mean dose (Dmean: 4.72 Gy vs. 4.91 Gy, p = 0.064), although not statistically significant, and achieved significantly improved dose gradient at V7.5 Gy (14.5% vs. 16.35%, p = 0.019), V5Gy (30.77% vs. 34.84%, p = 0.006), and V2Gy (99.77% vs. 97.79%, p < 0.001) compared to Eclipse. Ethos achieved significantly better OAR sparing, particularly for the bronchial tree, heart, spinal cord, esophagus, and great vessels (all p < 0.01). Furthermore, Ethos substantially reduced planning time (36.55 vs. 95.96 min, p < 0.001). Both planning systems achieved high gamma passing rates (> 95%), confirming the accuracy and deliverability of the treatment plans. CONCLUSION: The Ethos automated treatment planning demonstrated superior lattice dose conformity, enhanced OAR sparing, and significantly faster optimization compared to Eclipse. This automated optimization capability highlights the potential of Ethos for efficient and effective lattice radiotherapy in managing massive NSCLC tumors.
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 | 0.003 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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".